mdbq 1.0.2__tar.gz → 1.0.4__tar.gz

{mdbq-1.0.2 → mdbq-1.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.0.2
+Version: 1.0.4
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/aggregation/aggregation.py

@@ -685,7 +685,7 @@ class DatabaseUpdate:
                             collection_name=collection_name,
                             is_file_dtype=True,  # 默认本地文件优先: True
                         )
-                        m.df_to_mysql(df=df, db_name=db_name, tabel_name=collection_name)
+                        m.df_to_mysql(df=df, db_name=db_name, table_name=collection_name)
                 df_to_json.as_json_file()  # 写入 json 文件, 包含数据的 dtypes 信息
 
     def new_unzip(self, path=None, is_move=None):
@@ -896,8 +896,8 @@ def upload(path, db_name, collection_name):
                         df = df.astype(dtypes)
 
                     d.df_to_mongo(df=df, db_name=db_name, collection_name=collection_name)
-                    m.df_to_mysql(df=df, db_name=db_name, tabel_name=collection_name)
-                    nas.df_to_mysql(df=df, db_name=db_name, tabel_name=collection_name)
+                    m.df_to_mysql(df=df, db_name=db_name, table_name=collection_name)
+                    nas.df_to_mysql(df=df, db_name=db_name, table_name=collection_name)
                 except Exception as e:
                     print(name, e)
     if d.client:

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/aggregation/mysql_types.py

@@ -64,18 +64,18 @@ class DataTypes:
             json_ = json.load(f)
             self.datas.update(json_)
 
-    def get_mysql_types(self, cl, dtypes, db_name, tabel_name, is_file_dtype=True):
+    def get_mysql_types(self, cl, dtypes, db_name, table_name, is_file_dtype=True):
         """ 更新 mysql 的 types 信息到 json 文件 """
         if cl in self.datas.keys():
             if db_name in list(self.datas[cl].keys()):  # ['京东数据2', '天猫数据2', '生意参谋数据2', '生意经2']
-                if tabel_name in list(self.datas[cl][db_name].keys()):
+                if table_name in list(self.datas[cl][db_name].keys()):
                     if is_file_dtype:  # 旧数据优先
                         # # 用 dtypes 更新, 允许手动指定 json 文件里面的数据类型
-                        dtypes[cl][db_name][tabel_name].update(self.datas[cl][db_name][tabel_name])
+                        dtypes[cl][db_name][table_name].update(self.datas[cl][db_name][table_name])
                         # 将 dtypes 更新进去，使 self.datas 包含新旧信息
-                        self.datas[cl][db_name][tabel_name].update(dtypes[cl][db_name][tabel_name])
+                        self.datas[cl][db_name][table_name].update(dtypes[cl][db_name][table_name])
                     else:  # 新数据优先
-                        self.datas[cl][db_name][tabel_name].update(dtypes[cl][db_name][tabel_name])
+                        self.datas[cl][db_name][table_name].update(dtypes[cl][db_name][table_name])
                 else:
                     if is_file_dtype:  # 旧数据优先
                         dtypes[cl][db_name].update(self.datas[cl][db_name])
@@ -125,18 +125,18 @@ class DataTypes:
             )
         time.sleep(1)
 
-    def load_dtypes(self, db_name, tabel_name, cl='mysql', ):
+    def load_dtypes(self, db_name, table_name, cl='mysql', ):
         """
         mysql.py 程序从本地文件中读取 dtype 信息
         如果缺失 dtypes 信息，则执行 mysql_all_dtypes 以便更新所有数据库 dtypes 信息到 json 文件
         """
         if cl in self.datas.keys():
             if db_name in list(self.datas[cl].keys()):
-                if tabel_name in list(self.datas[cl][db_name].keys()):
-                    return self.datas[cl][db_name][tabel_name]
+                if table_name in list(self.datas[cl][db_name].keys()):
+                    return self.datas[cl][db_name][table_name]
                 else:
-                    print(f'不存在的集合名信息: {tabel_name}, 文件位置: {self.json_file}')
-                    mysql_all_dtypes(db_name=db_name, table_name=tabel_name)   # 更新一个表的 dtypes
+                    print(f'不存在的集合名信息: {table_name}, 文件位置: {self.json_file}')
+                    mysql_all_dtypes(db_name=db_name, table_name=table_name)   # 更新一个表的 dtypes
                     return {}
             else:
                 print(f'不存在的数据库信息: {db_name}, 文件位置: {self.json_file}')
@@ -206,28 +206,28 @@ def mysql_all_dtypes(db_name=None, table_name=None, path=None):
 
     d = DataTypes()
     for result in results:
-        for db_n, tabel_n in result.items():
+        for db_n, table_n in result.items():
             if db_name and table_name:  # 下载一个指定的数据表
-                if db_name != db_n or tabel_name != tabel_n:
+                if db_name != db_n or table_name != table_n:
                     continue
             elif db_name:  # 下载一个数据库的所有数据表
                 if db_name != db_n:
                     continue
             # 如果 db_name 和 table_name 都不指定，则下载所有数据库的所有数据表
-            print(f'获取列信息 数据库: < {db_n} >, 数据表: < {tabel_n} >')
-            # d.mysql_dtypes_to_json(db_name=db_n, tabel_name=tabel_n, path=path)
+            print(f'获取列信息 数据库: < {db_n} >, 数据表: < {table_n} >')
+            # d.mysql_dtypes_to_json(db_name=db_n, table_name=table_n, path=path)
             sq = s_query.QueryDatas(username=username, password=password, host=host, port=port)
             # 获取数据表的指定列, 返回列表
             # [{'视频bv号': 'BV1Dm4y1S7BU', '下载进度': 1}, {'视频bv号': 'BV1ov411c7US', '下载进度': 1}]
-            name_type = sq.dtypes_to_list(db_name=db_n, tabel_name=tabel_n)
+            name_type = sq.dtypes_to_list(db_name=db_n, table_name=table_n)
             if name_type:
                 dtypes = {item['COLUMN_NAME']: item['COLUMN_TYPE'] for item in name_type}
-                dtypes = {'mysql': {db_n: {tabel_n: dtypes}}}
+                dtypes = {'mysql': {db_n: {table_n: dtypes}}}
                 d.get_mysql_types(
                     dtypes=dtypes, 
                     cl='mysql', 
                     db_name=db_n,
-                    tabel_name=tabel_n,
+                    table_name=table_n,
                     is_file_dtype=True
                 )
             else:
@@ -235,5 +235,4 @@ def mysql_all_dtypes(db_name=None, table_name=None, path=None):
     d.as_json_file()
 
 if __name__ == '__main__':
-    # mysql_all_dtypes()  # 更新 mysql 中所有数据库的 dtypes 信息到本地 json
-    get_one_dtypes(db_name='京东数据2', tabel_name='sku_商品明细')
+    mysql_all_dtypes()  # 更新 mysql 中所有数据库的 dtypes 信息到本地 json

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/aggregation/query_data.py

@@ -100,7 +100,7 @@ class MysqlDatasQuery:
         }
         df = self.download.data_to_df(
             db_name='天猫数据2',
-            tabel_name='推广数据_宝贝主体报表',
+            table_name='推广数据_宝贝主体报表',
             start_date=start_date,
             end_date=end_date,
             projection=projection,
@@ -124,7 +124,7 @@ class MysqlDatasQuery:
         }
         df = self.download.data_to_df(
             db_name='生意经2',
-            tabel_name='宝贝指标',
+            table_name='宝贝指标',
             start_date=start_date,
             end_date=end_date,
             projection=projection,
@@ -135,7 +135,7 @@ class MysqlDatasQuery:
         """ 用生意经日数据制作商品 id 和编码对照表 """
         data_values = self.download.columns_to_list(
             db_name='生意经2',
-            tabel_name='宝贝指标',
+            table_name='宝贝指标',
             columns_name=['宝贝id', '商家编码', '行业类目'],
         )
         df = pd.DataFrame(data=data_values)
@@ -145,7 +145,7 @@ class MysqlDatasQuery:
         """ 用生意经日数据制作商品 id 和编码对照表 """
         data_values = self.download.columns_to_list(
             db_name='属性设置2',
-            tabel_name='商品素材导出',
+            table_name='商品素材导出',
             columns_name=['日期', '商品id', '商品白底图', '方版场景图'],
         )
         df = pd.DataFrame(data=data_values)
@@ -166,7 +166,7 @@ class MysqlDatasQuery:
         }
         df = self.download.data_to_df(
             db_name='生意参谋数据2',
-            tabel_name='店铺来源_日数据',
+            table_name='店铺来源_日数据',
             start_date=start_date,
             end_date=end_date,
             projection=projection,
@@ -177,7 +177,7 @@ class MysqlDatasQuery:
         """ 电商定价 """
         data_values = self.download.columns_to_list(
             db_name='属性设置2',
-            tabel_name='电商定价',
+            table_name='电商定价',
             columns_name=['日期', '款号', '年份季节', '吊牌价', '商家平台', '成本价', '天猫页面价', '天猫中促价'],
         )
         df = pd.DataFrame(data=data_values)
@@ -207,12 +207,18 @@ class GroupBy:
             self.output = os.path.join('数据中心/数据库导出')
         self.data_tgyj = {}  # 推广综合聚合数据表
 
-    def groupby(self, df, tabel_name, is_maximize=True):
+    def groupby(self, df, table_name, is_maximize=True):
         """
         self.is_maximize: 是否最大转化数据
         """
-
-        if '宝贝主体报表' in tabel_name:
+        if isinstance(df, pd.DataFrame):
+            if len(df) == 0:
+                print(f' query_data.groupby函数中 {table_name} 传入的 df 数据长度为0')
+                return pd.DataFrame()
+        else:
+            print(f'query_data.groupby函数中 {table_name} 传入的 df 不是 dataframe 结构')
+            return pd.DataFrame()
+        if '宝贝主体报表' in table_name:
             df.rename(columns={
                 '场景名字': '营销场景',
                 '主体id': '商品id',
@@ -265,11 +271,11 @@ class GroupBy:
                 )
             self.data_tgyj.update(
                 {
-                    tabel_name: df_new,
+                    table_name: df_new,
                 }
             )
             return df
-        elif '宝贝指标' in tabel_name:
+        elif '宝贝指标' in table_name:
             """ 聚合时不可以加商家编码，编码有些是空白，有些是 0 """
             df.fillna(0, inplace=True)
             # df = df[(df['销售额'] != 0) | (df['退款额'] != 0)]  # 注释掉, 因为后续使用生意经作为基准合并推广表，需确保所有商品id 齐全
@@ -294,13 +300,13 @@ class GroupBy:
             )
             self.data_tgyj.update(
                 {
-                    tabel_name: df[['日期', '宝贝id', '销售额', '销售量', '退款额（发货后）', '退货量（发货后）']],
+                    table_name: df[['日期', '宝贝id', '销售额', '销售量', '退款额（发货后）', '退货量（发货后）']],
                 }
             )
             return df
-        elif '店铺来源_日数据' in tabel_name:
+        elif '店铺来源_日数据' in table_name:
             return df
-        elif '商品id编码表' in tabel_name:
+        elif '商品id编码表' in table_name:
             df.drop_duplicates(subset='宝贝id', keep='last', inplace=True, ignore_index=True)
             # df['行业类目'] = df['行业类目'].apply(lambda x: re.sub(' ', '', x))
             try:
@@ -315,11 +321,11 @@ class GroupBy:
             df = df[(df['宝贝id'] != '973') & (df['宝贝id'] != '973')]
             self.data_tgyj.update(
                 {
-                    tabel_name: df[['宝贝id', '商家编码']],
+                    table_name: df[['宝贝id', '商家编码']],
                 }
             )
             return df
-        elif '商品id图片对照表' in tabel_name:
+        elif '商品id图片对照表' in table_name:
             df['商品id'] = df['商品id'].astype('int64')
             df['日期'] = df['日期'].astype('datetime64[ns]')
             df = df[(df['商品白底图'] != '0') | (df['方版场景图'] != '0')]
@@ -337,21 +343,21 @@ class GroupBy:
             df.sort_values(by='商品id', ascending=False, ignore_index=True, inplace=True)  # ascending=False 降序排列
             self.data_tgyj.update(
                 {
-                    tabel_name: df[['商品id', '商品图片']],
+                    table_name: df[['商品id', '商品图片']],
                 }
             )
             return df
-        elif '商品成本' in tabel_name:
+        elif '商品成本' in table_name:
             df.sort_values(by=['款号', '日期'], ascending=[False, True], ignore_index=True, inplace=True)
             df.drop_duplicates(subset=['款号'], keep='last', inplace=True, ignore_index=True)
             self.data_tgyj.update(
                 {
-                    tabel_name: df[['款号', '成本价']],
+                    table_name: df[['款号', '成本价']],
                 }
             )
             return df
         else:
-            print(f'<{tabel_name}>: Groupby 类尚未配置，数据为空')
+            print(f'<{table_name}>: Groupby 类尚未配置，数据为空')
             return pd.DataFrame({})
 
     def performance(self, bb_tg=True):
@@ -512,14 +518,14 @@ def data_aggregation(service_databases=[{}]):
                 },
             ]
             for items in data_dict:
-                db_name, tabel_name, df = items['数据库名'], items['集合名'], items['数据主体']
-                df = g.groupby(df=df, tabel_name=tabel_name, is_maximize=True)  # 2. 聚合数据
-                # g.as_csv(df=df, filename=tabel_name + '.csv')
-                m.df_to_mysql(df=df, db_name=db_name, tabel_name=tabel_name)  # 3. 回传数据库
+                db_name, table_name, df = items['数据库名'], items['集合名'], items['数据主体']
+                df = g.groupby(df=df, table_name=table_name, is_maximize=True)  # 2. 聚合数据
+                # g.as_csv(df=df, filename=table_name + '.csv')
+                m.df_to_mysql(df=df, db_name=db_name, table_name=table_name)  # 3. 回传数据库
             res = g.performance(bb_tg=True)   # 盈亏表，依赖其他表，单独做
-            m.df_to_mysql(df=res, db_name='聚合数据', tabel_name='_全店商品销售')
+            m.df_to_mysql(df=res, db_name='聚合数据', table_name='_全店商品销售')
             res = g.performance(bb_tg=False)  # 盈亏表，依赖其他表，单独做
-            m.df_to_mysql(df=res, db_name='聚合数据', tabel_name='_推广商品销售')
+            m.df_to_mysql(df=res, db_name='聚合数据', table_name='_推广商品销售')
 
     # optimize_data.op_data(service_databases=service_databases, days=3650)  # 立即启动对聚合数据的清理工作
 

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/config/products.py

@@ -111,7 +111,7 @@ class Products:
             host=host,
             port=port,
         )
-        m.df_to_mysql(df=df, db_name='属性设置2', tabel_name='货品年份基准')
+        m.df_to_mysql(df=df, db_name='属性设置2', table_name='货品年份基准')
 
 
 def main():

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/mysql/mysql.py

@@ -36,13 +36,20 @@ class MysqlUpload:
             'cursorclass': pymysql.cursors.DictCursor,
         }
 
-    def df_to_mysql(self, df, tabel_name, db_name='远程数据源', drop_duplicates=False):
+    def df_to_mysql(self, df, table_name, db_name='远程数据源', drop_duplicates=False):
         """
         将 df 写入数据库
         db_name: 数据库名称
-        tabel_name: 集合/表名称
+        table_name: 集合/表名称
         drop_duplicates：仅限于聚合数据使用，其他情况不要设置
         """
+        if isinstance(df, pd.DataFrame):
+            if len(df) == 0:
+                print(f'{db_name}: {table_name} 传入的 df 数据长度为0')
+                return
+        else:
+            print(f'{db_name}: {table_name} 传入的 df 不是 dataframe 结构')
+            return
         cv = converter.DataFrameConverter()
         df = cv.convert_df_cols(df=df)  # 清理 dataframe 非法值
 
@@ -67,18 +74,18 @@ class MysqlUpload:
         connection = pymysql.connect(**self.config)  # 重新连接数据库
         with connection.cursor() as cursor:
             # 1. 查询表, 不存在则创建一个空表
-            sql = f"SHOW TABLES LIKE '{tabel_name}';"  # 有特殊字符不需转义
+            sql = f"SHOW TABLES LIKE '{table_name}';"  # 有特殊字符不需转义
             cursor.execute(sql)
             if not cursor.fetchone():
-                sql = f"CREATE TABLE IF NOT EXISTS `{tabel_name}` (id INT AUTO_INCREMENT PRIMARY KEY)"
+                sql = f"CREATE TABLE IF NOT EXISTS `{table_name}` (id INT AUTO_INCREMENT PRIMARY KEY)"
                 cursor.execute(sql)
-                print(f'创建 mysql 表: {tabel_name}')
+                print(f'创建 mysql 表: {table_name}')
 
             # 2. 列数据类型转换，将 df 数据类型转换为 mysql 的数据类型
-            dtypes = self.convert_dtypes(df=df, db_name=db_name, tabel_name=tabel_name)
+            dtypes = self.convert_dtypes(df=df, db_name=db_name, table_name=table_name)
 
             #  有特殊字符不需转义
-            sql = f"SELECT COLUMN_NAME FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = '{db_name}' AND TABLE_NAME = '{tabel_name}';"
+            sql = f"SELECT COLUMN_NAME FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = '{db_name}' AND TABLE_NAME = '{table_name}';"
             cursor.execute(sql)
             col_exist = [item['COLUMN_NAME'] for item in cursor.fetchall()]
             cols = df.columns.tolist()
@@ -88,16 +95,16 @@ class MysqlUpload:
                 for col in col_not_exist:
                     try:
                         #  创建列，需转义
-                        sql = f"ALTER TABLE `{tabel_name}` ADD COLUMN `{col}` {dtypes[col]} DEFAULT NULL;"
+                        sql = f"ALTER TABLE `{table_name}` ADD COLUMN `{col}` {dtypes[col]} DEFAULT NULL;"
                         cursor.execute(sql)
                         print(f"添加列: {col}({dtypes[col]})")  # 添加列并指定数据类型
 
                         # 创建索引
                         if col == '日期':
-                            cursor.execute(f"SHOW INDEXES FROM `{tabel_name}` WHERE `Column_name` = '{col}'")
+                            cursor.execute(f"SHOW INDEXES FROM `{table_name}` WHERE `Column_name` = '{col}'")
                             result = cursor.fetchone()  # 检查索引是否存在
                             if not result:
-                                cursor.execute(f"CREATE INDEX index_name ON `{tabel_name}`(`{col}`)")
+                                cursor.execute(f"CREATE INDEX index_name ON `{table_name}`(`{col}`)")
                     except:
                         pass
             connection.commit()  # 提交事务
@@ -107,13 +114,13 @@ class MysqlUpload:
                 dates = df['日期'].values.tolist()
                 start_date = pd.to_datetime(min(dates)).strftime('%Y-%m-%d')
                 end_date = (pd.to_datetime(max(dates)) + datetime.timedelta(days=1)).strftime('%Y-%m-%d')
-                sql = f"DELETE FROM `{tabel_name}` WHERE {'日期'} BETWEEN '%s' AND '%s'" % (start_date, end_date)
+                sql = f"DELETE FROM `{table_name}` WHERE {'日期'} BETWEEN '%s' AND '%s'" % (start_date, end_date)
                 cursor.execute(sql)
                 connection.commit()
 
             # 5. 更新插入数据
             now = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S ")
-            print(f'{now}正在更新 mysql ({self.host}:{self.port}) {db_name}/{tabel_name}')
+            print(f'{now}正在更新 mysql ({self.host}:{self.port}) {db_name}/{table_name}')
             datas = df.to_dict(orient='records')
             for data in datas:
                 try:
@@ -126,17 +133,17 @@ class MysqlUpload:
                     condition = ' AND '.join(condition)  # 构建查询条件
                     # print(condition)
 
-                    sql = f"SELECT {cols} FROM `{tabel_name}` WHERE {condition}"
+                    sql = f"SELECT {cols} FROM `{table_name}` WHERE {condition}"
                     cursor.execute(sql)
                     result = cursor.fetchall()  # 获取查询结果, 如果有结果返回 list，没有则返回空元组 tuple
                     if not result:  # 数据不存在则插入
-                        sql = f"INSERT INTO `{tabel_name}` ({cols}) VALUES ({values});"
+                        sql = f"INSERT INTO `{table_name}` ({cols}) VALUES ({values});"
                         cursor.execute(sql)
                 except:
                     pass
         connection.commit()  # 提交事务
 
-    def convert_dtypes(self, df, db_name, tabel_name):
+    def convert_dtypes(self, df, db_name, table_name):
         """
         根据本地已经存在的记录着 mysql dtypes 的 json 文件转换 df 的类型为 mysql 专有的数据类型
         允许通过 json 文件指定列的数据类型
@@ -148,7 +155,7 @@ class MysqlUpload:
         # path = set_support.SetSupport(dirname='support').dirname
         d = mysql_types.DataTypes()
         # 从本地文件中读取 dtype 信息
-        dtypes = d.load_dtypes(cl='mysql', db_name=db_name, tabel_name=tabel_name)
+        dtypes = d.load_dtypes(cl='mysql', db_name=db_name, table_name=table_name)
         # 可能会因为没有 json 文件, 返回 None
         if dtypes:
             # 按照文件记录更新 dtypes
@@ -199,7 +206,7 @@ class MysqlUpload:
             return 'mediumtext'
 
     # @try_except
-    def read_mysql(self, tabel_name, start_date, end_date, db_name='远程数据源', ):
+    def read_mysql(self, table_name, start_date, end_date, db_name='远程数据源', ):
         start_date = pd.to_datetime(start_date).strftime('%Y-%m-%d')
         end_date = pd.to_datetime(end_date).strftime('%Y-%m-%d')
         df = pd.DataFrame()
@@ -214,7 +221,7 @@ class MysqlUpload:
                     return df
                 else:
                     now = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S ")
-                    print(f'{now}mysql 正在查询表: {tabel_name}, 范围: {start_date}~{end_date}')
+                    print(f'{now}mysql 正在查询表: {table_name}, 范围: {start_date}~{end_date}')
         except:
             return df
         finally:
@@ -227,25 +234,25 @@ class MysqlUpload:
         try:
             with connection.cursor() as cursor:
                 # 获取指定日期范围的数据
-                sql = f"SELECT * FROM {db_name}.{tabel_name} WHERE {'日期'} BETWEEN '%s' AND '%s'" % (start_date, end_date)
+                sql = f"SELECT * FROM {db_name}.{table_name} WHERE {'日期'} BETWEEN '%s' AND '%s'" % (start_date, end_date)
                 cursor.execute(sql)
                 rows = cursor.fetchall()  # 获取查询结果
                 columns = [desc[0] for desc in cursor.description]
                 df = pd.DataFrame(rows, columns=columns)  # 转为 df
         except Exception as e:
-            print(f'{e} {db_name} -> {tabel_name} 表不存在')
+            print(f'{e} {db_name} -> {table_name} 表不存在')
             return df
         finally:
             connection.close()
 
         if len(df) == 0:
-            print(f'database: {db_name}, table: {tabel_name} 查询的数据为空')
+            print(f'database: {db_name}, table: {table_name} 查询的数据为空')
         else:
             now = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S ")
             cost_time = int(time.time() - before_time)
             if cost_time < 1:
                 cost_time = round(time.time() - before_time, 2)
-            print(f'{now}mysql ({self.host}) 表: {tabel_name} 获取数据长度: {len(df)}, 用时: {cost_time} 秒')
+            print(f'{now}mysql ({self.host}) 表: {table_name} 获取数据长度: {len(df)}, 用时: {cost_time} 秒')
         return df
 
     def upload_pandas(self, update_path, db_name, days=None):
@@ -281,7 +288,7 @@ class MysqlUpload:
                                 df = df[df['日期'] >= start_date]
                             if len(df) == 0:
                                 continue
-                            self.df_to_mysql(df=df, db_name=db_name, tabel_name=root_file)
+                            self.df_to_mysql(df=df, db_name=db_name, table_name=root_file)
             elif os.path.isfile(f_path):
                 if f_path.endswith('.csv') and 'baidu' not in f_path:
                     df = pd.read_csv(f_path, encoding='utf-8_sig', header=0, na_filter=False)
@@ -295,7 +302,7 @@ class MysqlUpload:
                     if len(df) == 0:
                         continue
                     table = f'{os.path.splitext(root_file)[0]}_f'  # 这里定义了文件表会加 _f 后缀
-                    self.df_to_mysql(df=df, db_name=db_name, tabel_name=table)
+                    self.df_to_mysql(df=df, db_name=db_name, table_name=table)
 
 
 class OptimizeDatas:
@@ -621,7 +628,7 @@ def year_month_day(start_date, end_date):
     return results  # start_date至end_date之间的所有年月日
 
 
-def download_datas(tabel_name, save_path, start_date):
+def download_datas(table_name, save_path, start_date):
     username, password, host, port = get_myconf.select_config_values(target_service='home_lx', database='mysql')
     print(username, password, host, port)
     m = MysqlUpload(username=username, password=password, host=host, port=port)
@@ -632,10 +639,10 @@ def download_datas(tabel_name, save_path, start_date):
         start_date = result['起始日期']
         end_date = result['结束日期']
         # print(start_date, end_date)
-        df = m.read_mysql(db_name='天猫数据1', tabel_name=tabel_name, start_date=start_date, end_date=end_date)
+        df = m.read_mysql(db_name='天猫数据1', table_name=table_name, start_date=start_date, end_date=end_date)
         if len(df) == 0:
             continue
-        path = os.path.join(save_path, f'{tabel_name}_{str(start_date)}_{str(end_date)}.csv')
+        path = os.path.join(save_path, f'{table_name}_{str(start_date)}_{str(end_date)}.csv')
         df['日期'] = df['日期'].apply(lambda x: re.sub(' .*', '', str(x)))
         df.to_csv(path, index=False, encoding='utf-8_sig', header=True)
 
@@ -647,7 +654,7 @@ if __name__ == '__main__':
     df = pd.read_csv('/Users/xigua/Downloads/余额查询.csv', encoding='utf-8_sig', header=0, na_filter=False)
     # df = df.to_dict(orient='records')
     m = MysqlUpload(username=username, password=password, host=host, port=port)
-    m.df_to_mysql_new(df=df, db_name='te2- %s t', tabel_name='测 -sdf @%试 表')
+    m.df_to_mysql_new(df=df, db_name='te2- %s t', table_name='测 -sdf @%试 表')
 
 
 

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq/mysql/s_query.py

@@ -34,13 +34,13 @@ class QueryDatas:
             'cursorclass': pymysql.cursors.DictCursor,
         }
 
-    def data_to_df(self, db_name, tabel_name, start_date, end_date, projection: dict=[]):
+    def data_to_df(self, db_name, table_name, start_date, end_date, projection: dict=[]):
 
         start_date = pd.to_datetime(start_date).strftime('%Y-%m-%d')
         end_date = pd.to_datetime(end_date).strftime('%Y-%m-%d')
         df = pd.DataFrame()  # 初始化df
 
-        if self.check_infos(db_name, tabel_name) == False:
+        if self.check_infos(db_name, table_name) == False:
             return df
 
         self.config.update({'database': db_name})
@@ -49,7 +49,7 @@ class QueryDatas:
             with connection.cursor() as cursor:
                 # 3. 获取数据表的所有列信息
                 sql = 'SELECT COLUMN_NAME FROM information_schema.columns WHERE table_schema = %s AND table_name = %s'
-                cursor.execute(sql, (db_name, {tabel_name}))
+                cursor.execute(sql, (db_name, {table_name}))
                 columns = cursor.fetchall()
                 cols_exist = [col['COLUMN_NAME'] for col in columns]  # 数据表的所有列, 返回 list
 
@@ -61,17 +61,17 @@ class QueryDatas:
                             columns_in.append(key)  # 提取值为 1 的键并清理不在数据表的键
                     columns_in = ', '.join(columns_in)
                     if '日期' in cols_exist:  # 不论是否指定, 只要数据表有日期，则执行
-                        sql = (f"SELECT {columns_in} FROM {db_name}.{tabel_name} "
+                        sql = (f"SELECT {columns_in} FROM {db_name}.{table_name} "
                                f"WHERE {'日期'} BETWEEN '{start_date}' AND '{end_date}'")
                     else:  # 数据表没有日期列时，返回指定列的所有数据
-                        sql = f"SELECT {columns_in} FROM {db_name}.{tabel_name}"
+                        sql = f"SELECT {columns_in} FROM {db_name}.{table_name}"
                 else:  # 没有指定获取列时
                     if '日期' in cols_exist:  # 但数据表有日期，仍然执行
                         columns_in = ', '.join(cols_exist)
-                        sql = (f"SELECT {columns_in} FROM {db_name}.{tabel_name} "
+                        sql = (f"SELECT {columns_in} FROM {db_name}.{table_name} "
                                f"WHERE {'日期'} BETWEEN '{start_date}' AND '{end_date}'")
                     else:  # 没有指定获取列，且数据表也没有日期列，则返回全部列的全部数据
-                        sql = f"SELECT * FROM {db_name}.{tabel_name}"
+                        sql = f"SELECT * FROM {db_name}.{table_name}"
                 cursor.execute(sql)
                 rows = cursor.fetchall()  # 获取查询结果
                 columns = [desc[0] for desc in cursor.description]
@@ -83,15 +83,15 @@ class QueryDatas:
             connection.close()
 
         if len(df) == 0:
-            print(f'database: {db_name}, table: {tabel_name} 查询的数据为空')
+            print(f'database: {db_name}, table: {table_name} 查询的数据为空')
         return df
 
-    def columns_to_list(self, db_name, tabel_name,  columns_name) -> list:
+    def columns_to_list(self, db_name, table_name,  columns_name) -> list:
         """
         获取数据表的指定列, 返回列表
         [{'视频bv号': 'BV1Dm4y1S7BU', '下载进度': 1}, {'视频bv号': 'BV1ov411c7US', '下载进度': 1}]
         """
-        if self.check_infos(db_name, tabel_name) == False:  # 检查传入的数据库和数据表是否存在
+        if self.check_infos(db_name, table_name) == False:  # 检查传入的数据库和数据表是否存在
             return []
 
         self.config.update({'database': db_name})
@@ -99,26 +99,26 @@ class QueryDatas:
         with connection.cursor() as cursor:
             # 3. 获取数据表的所有列信息
             sql = 'SELECT COLUMN_NAME FROM information_schema.columns WHERE table_schema = %s AND table_name = %s'
-            cursor.execute(sql, (db_name, {tabel_name}))
+            cursor.execute(sql, (db_name, {table_name}))
             columns = cursor.fetchall()
             cols_exist = [col['COLUMN_NAME'] for col in columns]  # 数据表的所有列, 返回 list
             columns_name = [item for item in columns_name if item in cols_exist]
             if len(columns_name) == 0:
                 return []
             columns_in = ', '.join(columns_name)
-            sql = (f"SELECT {columns_in} FROM {db_name}.{tabel_name} ")
+            sql = (f"SELECT {columns_in} FROM {db_name}.{table_name} ")
             cursor.execute(sql)
             column_values = cursor.fetchall()  # 返回指定列，结果是[dict, dict, dict, ...]
             # column_values = [item[column_name] for item in column_values]  # 提取字典的值, 组成列表
         connection.close()
         return column_values
 
-    def dtypes_to_list(self, db_name, tabel_name) -> list:
+    def dtypes_to_list(self, db_name, table_name) -> list:
         """
         获取数据表的指定列, 返回列表
         [{'视频bv号': 'BV1Dm4y1S7BU', '下载进度': 1}, {'视频bv号': 'BV1ov411c7US', '下载进度': 1}]
         """
-        if self.check_infos(db_name, tabel_name) == False:  # 检查传入的数据库和数据表是否存在
+        if self.check_infos(db_name, table_name) == False:  # 检查传入的数据库和数据表是否存在
             return []
 
         self.config.update({'database': db_name})
@@ -126,12 +126,12 @@ class QueryDatas:
         with connection.cursor() as cursor:
             # 3. 获取数据表的所有列信息
             sql = 'SELECT COLUMN_NAME, COLUMN_TYPE FROM information_schema.columns WHERE table_schema = %s AND table_name = %s'
-            cursor.execute(sql, (db_name, {tabel_name}))
+            cursor.execute(sql, (db_name, {table_name}))
             column_name_and_type = cursor.fetchall()
         connection.close()
         return column_name_and_type
 
-    def check_infos(self, db_name, tabel_name) -> bool:
+    def check_infos(self, db_name, table_name) -> bool:
         """ 检查数据库、数据表是否存在 """
         connection = pymysql.connect(**self.config)  # 连接数据库
         try:
@@ -150,10 +150,10 @@ class QueryDatas:
         try:
             with connection.cursor() as cursor:
                 # 2. 查询表是否存在
-                sql = f"SHOW TABLES LIKE '{tabel_name}'"
+                sql = f"SHOW TABLES LIKE '{table_name}'"
                 cursor.execute(sql)
                 if not cursor.fetchone():
-                    print(f'{db_name} -> <{tabel_name}>: 表不存在')
+                    print(f'{db_name} -> <{table_name}>: 表不存在')
                     return False
                 return True
         except Exception as e:
@@ -168,5 +168,5 @@ if __name__ == '__main__':
     print(username, password, host, port)
 
     q = QueryDatas(username, password, host, port)
-    res = q.columns_to_list(db_name='视频数据', tabel_name='bilibili视频', columns_name=['视频bv号', '下载进度'])
+    res = q.columns_to_list(db_name='视频数据', table_name='bilibili视频', columns_name=['视频bv号', '下载进度'])
     print(res)

{mdbq-1.0.2 → mdbq-1.0.4}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.0.2
+Version: 1.0.4
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.0.2 → mdbq-1.0.4}/setup.py

@@ -3,7 +3,7 @@
 from setuptools import setup, find_packages
 
 setup(name='mdbq',
-      version='1.0.2',
+      version='1.0.4',
       author='xigua, ',
       author_email="2587125111@qq.com",
       url='https://pypi.org/project/mdbsql',