mdbq 3.8.14__py3-none-any.whl → 3.8.16__py3-none-any.whl

mdbq/__version__.py

@@ -1 +1 @@
-VERSION = '3.8.14'
+VERSION = '3.8.16'

mdbq/aggregation/query_data.py

@@ -3906,9 +3906,6 @@ def date_table():
         table_name='日期表',
         move_insert=True,  # 先删除，再插入
         df_sql=False,  # 值为 True 时使用 df.to_sql 函数上传整个表, 不会排重
-        drop_duplicates=False,  # 值为 True 时检查重复数据再插入，反之直接上传，会比较慢
-        count=None,
-        filename=None,  # 用来追踪处理进度
         set_typ=set_typ,
     )
 

mdbq/mysql/mysql.py

@@ -191,7 +191,7 @@ class MysqlUpload:
         with connection.cursor() as cursor:
             # 1. 查询表, 不存在则创建一个空表
             sql = "SHOW TABLES LIKE %s;"  # 有特殊字符不需转义
-            cursor.execute(sql, (table_name))
+            cursor.execute(sql, (table_name,))
             if not cursor.fetchone():
                 sql = f"CREATE TABLE IF NOT EXISTS `{table_name}` (id INT AUTO_INCREMENT PRIMARY KEY);"
                 cursor.execute(sql)
@@ -201,7 +201,7 @@ class MysqlUpload:
             dtypes, dict_data = self.cover_dict_dtypes(dict_data=dict_data)  # {'店铺名称': 'varchar(100)',...}
             if set_typ:
                 # 更新自定义的列数据类型
-                for k, v in dtypes.items():
+                for k, v in dtypes.copy().items():
                     # 确保传进来的 set_typ 键存在于实际的 df 列才 update
                     [dtypes.update({k: inside_v}) for inside_k, inside_v in set_typ.items() if k == inside_k]
 
@@ -239,48 +239,49 @@ class MysqlUpload:
                     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
-                    update_col = [item for item in cols_exist if item not in icm_update and item != 'id']  # 除了主键外的其他列
-
-                    # 构造查询条件（参数化）
-                    condition = ' AND '.join([f'`{up_col}` = %s' for up_col in icm_update])
-                    condition_values = [dict_data[up_col] for up_col in icm_update]
-
-                    # 执行查询（参数化）
-                    sql = f"SELECT {','.join([f'`{col}`' for col in update_col])} FROM `{table_name}` WHERE {condition}"
-                    cursor.execute(sql, condition_values)
+                    # 保留原始列名，不提前转义
+                    raw_update_col = [item for item in cols_exist if item not in icm_update and item != 'id']  # 除了主键外的其他列
+
+                    # 构建条件参数（使用原始列名）
+                    condition_params = []
+                    condition_parts = []
+                    for up_col in icm_update:
+                        condition_parts.append(f"`{up_col}` = %s")  # SQL 转义
+                        condition_params.append(dict_data[up_col])  # 原始列名用于访问数据
+
+                    # 动态转义列名生成 SQL 查询字段
+                    escaped_update_col = [f'`{col}`' for col in raw_update_col]
+                    sql = f"""SELECT {','.join(escaped_update_col)} FROM `{table_name}` WHERE {' AND '.join(condition_parts)}"""
+                    cursor.execute(sql, condition_params)
                     results = cursor.fetchall()
 
-                    if results:  # 有数据返回，再进行增量检查
-                        for result in results:  # results 是数据库数据, dict_data 是传进来的数据
-                            change_col = []  # 发生变化的列名
-                            change_values = []  # 发生变化的数据
-                            for col in update_col:
-                                # 因为 mysql 里面有 decimal 数据类型，要移除末尾的 0 再做比较（df 默认将 5.00 小数截断为 5.0）
-                                df_value = str(dict_data[col])
-                                mysql_value = str(result[col])
+                    if results:
+                        for result in results:
+                            change_col = []
+                            change_placeholders = []
+                            set_params = []
+                            for raw_col in raw_update_col:
+                                # 使用原始列名访问数据
+                                df_value = str(dict_data[raw_col])
+                                mysql_value = str(result[raw_col])
+
+                                # 清理小数点后多余的零
                                 if '.' in df_value:
-                                    df_value = re.sub(r'0+$', '', df_value)
-                                    df_value = re.sub(r'\.$', '', df_value)
+                                    df_value = re.sub(r'0+$', '', df_value).rstrip('.')
                                 if '.' in mysql_value:
-                                    mysql_value = re.sub(r'0+$', '', mysql_value)
-                                    mysql_value = re.sub(r'\.$', '', mysql_value)
-                                if df_value != mysql_value:  # 传进来的数据和数据库比较, 有变化
-                                    change_values += [f"`{col}` = \"{str(dict_data[col])}\""]
-                                    change_col.append(col)
-                            not_change_col = [item for item in update_col if item not in change_col]
-
-                            # 构造更新语句（参数化）
-                            if change_values:
-                                set_clause = ', '.join([f'`{col}` = %s' for col in change_col])
-                                update_values = [dict_data[col] for col in change_col]
-                                # 添加未变化列的查询条件
-                                if not_change_col:
-                                    not_change_condition = ' AND '.join([f'`{col}` = %s' for col in not_change_col])
-                                    condition += f' AND {not_change_condition}'
-                                    condition_values += [dict_data[col] for col in not_change_col]
-                                # 执行更新
-                                sql = f"UPDATE `{table_name}` SET {set_clause} WHERE {condition}"
-                                cursor.execute(sql, update_values + condition_values)
+                                    mysql_value = re.sub(r'0+$', '', mysql_value).rstrip('.')
+
+                                if df_value != mysql_value:
+                                    change_placeholders.append(f"`{raw_col}` = %s")  # 动态转义列名
+                                    set_params.append(dict_data[raw_col])
+                                    change_col.append(raw_col)
+
+                            if change_placeholders:
+                                full_params = set_params + condition_params
+                                sql = f"""UPDATE `{table_name}` 
+                                             SET {','.join(change_placeholders)} 
+                                             WHERE {' AND '.join(condition_parts)}"""
+                                cursor.execute(sql, full_params)
                     else:  # 没有数据返回，则直接插入数据
                         # 参数化插入
                         cols = ', '.join([f'`{k}`' for k in dict_data.keys()])
@@ -308,7 +309,7 @@ class MysqlUpload:
                     connection.rollback()
         connection.close()
 
-    @try_except
+    # @try_except
     def dict_to_mysql(self, db_name, table_name, dict_data, icm_update=None, index_length=100, set_typ=None, allow_not_null=False, cut_data=None):
         """
         插入字典数据
@@ -355,7 +356,7 @@ class MysqlUpload:
         with connection.cursor() as cursor:
             # 1. 查询表, 不存在则创建一个空表
             sql = "SHOW TABLES LIKE %s;"  # 有特殊字符不需转义
-            cursor.execute(sql, (table_name))
+            cursor.execute(sql, (table_name,))
             if not cursor.fetchone():
                 sql = f"CREATE TABLE IF NOT EXISTS `{table_name}` (id INT AUTO_INCREMENT PRIMARY KEY);"
                 cursor.execute(sql)
@@ -365,7 +366,7 @@ class MysqlUpload:
             dtypes, dict_data = self.cover_dict_dtypes(dict_data=dict_data)  # {'店铺名称': 'varchar(100)',...}
             if set_typ:
                 # 更新自定义的列数据类型
-                for k, v in dtypes.items():
+                for k, v in dtypes.copy().items():
                     # 确保传进来的 set_typ 键存在于实际的 df 列才 update
                     [dtypes.update({k: inside_v}) for inside_k, inside_v in set_typ.items() if k == inside_k]
 
@@ -398,43 +399,49 @@ class MysqlUpload:
                 sql = """SELECT COLUMN_NAME FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_SCHEMA = %s AND TABLE_NAME = %s"""
                 cursor.execute(sql, (db_name, table_name))
                 cols_exist = [col['COLUMN_NAME'] for col in cursor.fetchall()] # 数据表的所有列, 返回 list
-                update_col = [item for item in cols_exist if item not in icm_update and item != 'id']  # 除了主键外的其他列
 
-                # 参数化构建查询条件
+                # 保留原始列名，不提前转义
+                raw_update_col = [item for item in cols_exist if item not in icm_update and item != 'id']
+
+                # 构建条件参数（使用原始列名）
                 condition_params = []
                 condition_parts = []
                 for up_col in icm_update:
-                    condition_parts.append(f"`{up_col}` = %s")
-                    condition_params.append(dict_data[up_col])
+                    condition_parts.append(f"`{up_col}` = %s")  # SQL 转义
+                    condition_params.append(dict_data[up_col])  # 原始列名访问数据
 
-                sql = f"""SELECT `{','.join(update_col)}` FROM `{table_name}` WHERE {' AND '.join(condition_parts)}"""
+                # 动态转义列名生成 SQL 查询字段
+                escaped_update_col = [f'`{col}`' for col in raw_update_col]
+                sql = f"""SELECT {','.join(escaped_update_col)} FROM `{table_name}` WHERE {' AND '.join(condition_parts)}"""
                 cursor.execute(sql, condition_params)
                 results = cursor.fetchall()
-                if results:  # 有数据返回，再进行增量检查
-                    for result in results:  # results 是数据库数据, dict_data 是传进来的数据
-                        change_col = []  # 发生变化的列名
-                        change_values = []  # 发生变化的数据
-                        for col in update_col:
-                            # 因为 mysql 里面有 decimal 数据类型，要移除末尾的 0 再做比较（df 默认将 5.00 小数截断为 5.0）
-                            df_value = str(dict_data[col])
-                            mysql_value = str(result[col])
+
+                if results:
+                    for result in results:
+                        change_col = []
+                        change_placeholders = []
+                        set_params = []
+                        for raw_col in raw_update_col:
+                            # 使用原始列名访问数据
+                            df_value = str(dict_data[raw_col])
+                            mysql_value = str(result[raw_col])
+
+                            # 清理小数点后多余的零
                             if '.' in df_value:
-                                df_value = re.sub(r'0+$', '', df_value)
-                                df_value = re.sub(r'\.$', '', df_value)
+                                df_value = re.sub(r'0+$', '', df_value).rstrip('.')
                             if '.' in mysql_value:
-                                mysql_value = re.sub(r'0+$', '', mysql_value)
-                                mysql_value = re.sub(r'\.$', '', mysql_value)
-                            if df_value != mysql_value:  # 传进来的数据和数据库比较, 有变化
-                                change_values += [f"`{col}` = \"{str(dict_data[col])}\""]
-                                change_col.append(col)
-                        # change_values 是 df 传进来且和数据库对比后，发生了变化的数据，值示例： [`品销宝余额` = '9999.0', `短信剩余` = '888']
-                        if change_values:  # change_values 有数据返回，表示值需要更新
-                            set_params = [dict_data[col] for col in change_col]
-                            full_params = set_params + condition_params  # 正确顺序
+                                mysql_value = re.sub(r'0+$', '', mysql_value).rstrip('.')
+
+                            if df_value != mysql_value:
+                                change_placeholders.append(f"`{raw_col}` = %s")  # 动态转义列名
+                                set_params.append(dict_data[raw_col])
+                                change_col.append(raw_col)
 
+                        if change_placeholders:
+                            full_params = set_params + condition_params
                             sql = f"""UPDATE `{table_name}` 
-                                    SET {','.join(set_parts)} 
-                                    WHERE {' AND '.join(condition_parts)}"""
+                                         SET {','.join(change_placeholders)} 
+                                         WHERE {' AND '.join(condition_parts)}"""
                             cursor.execute(sql, full_params)
                 else:  # 没有数据返回，则直接插入数据
                     # 参数化插入语句
@@ -524,7 +531,7 @@ class MysqlUpload:
         [pd.to_numeric(df[col], errors='ignore') for col in df.columns.tolist()]
         dtypes = df.dtypes.to_dict()
         __res_dict = {}
-        for k, v in dtypes.items():
+        for k, v in dtypes.copy().items():
             result1 = re.findall(r'编码|_?id|货号|款号|文件大小', k, re.IGNORECASE)
             result2 = re.findall(r'占比$|投产$|产出$|roi$|率$', k, re.IGNORECASE)
             result3 = re.findall(r'同比$|环比$', k, re.IGNORECASE)
@@ -611,7 +618,7 @@ class MysqlUpload:
         dtypes, df = self.convert_df_dtypes(df)
         if set_typ:
             # 更新自定义的列数据类型
-            for k, v in dtypes.items():
+            for k, v in dtypes.copy().items():
                 # 确保传进来的 set_typ 键存在于实际的 df 列才 update
                 [dtypes.update({k: inside_v}) for inside_k, inside_v in set_typ.items() if k == inside_k]
 
@@ -635,7 +642,7 @@ class MysqlUpload:
         with connection.cursor() as cursor:
             # 1. 查询表, 不存在则创建一个空表
             sql = "SHOW TABLES LIKE %s;"  # 有特殊字符不需转义
-            cursor.execute(sql, (table_name))
+            cursor.execute(sql, (table_name,))
             if not cursor.fetchone():
                 create_table_sql = f"CREATE TABLE IF NOT EXISTS `{table_name}` (id INT AUTO_INCREMENT PRIMARY KEY)"
                 cursor.execute(create_table_sql)
@@ -661,7 +668,7 @@ class MysqlUpload:
                     # 创建索引
                     if col == '日期':
                         sql = f"SHOW INDEXES FROM `{table_name}` WHERE `Column_name` = %s"
-                        cursor.execute(sql, (col))
+                        cursor.execute(sql, (col,))
                         result = cursor.fetchone()  # 检查索引是否存在
                         if not result:
                             cursor.execute(f"CREATE INDEX index_name ON `{table_name}`(`{col}`)")

{mdbq-3.8.14.dist-info → mdbq-3.8.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mdbq
-Version: 3.8.14
+Version: 3.8.16
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-3.8.14.dist-info → mdbq-3.8.16.dist-info}/RECORD

@@ -1,13 +1,13 @@
 mdbq/__init__.py,sha256=Il5Q9ATdX8yXqVxtP_nYqUhExzxPC_qk_WXQ_4h0exg,16
-mdbq/__version__.py,sha256=5G-_mHmo-5FjfAe99IHqW_10kybGnZlf2oRqK_oW9UA,18
+mdbq/__version__.py,sha256=VUh6syxyz3BeTHjQrrlUgLdyX1-2SRQdP5locYySmCQ,18
 mdbq/aggregation/__init__.py,sha256=EeDqX2Aml6SPx8363J-v1lz0EcZtgwIBYyCJV6CcEDU,40
-mdbq/aggregation/query_data.py,sha256=xJ4YeShUGEpYqEKO0HKqfD7nT6AEUEujVb_3Ea_QTBw,179995
+mdbq/aggregation/query_data.py,sha256=5_OzjGR5Sq00q-EgAYmSE5V9i4Solw9y4hkldl4mvt8,179808
 mdbq/config/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/config/config.py,sha256=eaTfrfXQ65xLqjr5I8-HkZd_jEY1JkGinEgv3TSLeoQ,3170
 mdbq/log/__init__.py,sha256=Mpbrav0s0ifLL7lVDAuePEi1hJKiSHhxcv1byBKDl5E,15
 mdbq/log/spider_logging.py,sha256=-ozWWEGm3HVv604ozs_OOvVwumjokmUPwbaodesUrPY,1664
 mdbq/mysql/__init__.py,sha256=A_DPJyAoEvTSFojiI2e94zP0FKtCkkwKP1kYUCSyQzo,11
-mdbq/mysql/mysql.py,sha256=zYIpxKJWrb4PS13a51n4gTSTn2rRfzAB-yWDoJL49y8,55802
+mdbq/mysql/mysql.py,sha256=4N6srlRYomoSHdK4Y84fxkIW_eL5xFkb3Jo06sebSi0,55031
 mdbq/mysql/s_query.py,sha256=X055aLRAgxVvueXx4NbfNjp6MyBI02_XBb1pTKw09L0,8660
 mdbq/other/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/other/download_sku_picture.py,sha256=YU8DxKMXbdeE1OOKEA848WVp62jYHw5O4tXTjUdq9H0,44832
@@ -21,7 +21,7 @@ mdbq/redis/__init__.py,sha256=YtgBlVSMDphtpwYX248wGge1x-Ex_mMufz4-8W0XRmA,12
 mdbq/redis/getredis.py,sha256=Uk8-cOWT0JU1qRyIVqdbYokSLvkDIAfcokmYj1ebw8k,24104
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
 mdbq/spider/aikucun.py,sha256=m7ZIvrc9pqoGCYEH3FtgKTwqhX7QB6qzgc2twDzhX4w,19962
-mdbq-3.8.14.dist-info/METADATA,sha256=huDrR4rNqxqoau4lxivHl6AOxG7kpiG5a2rUrTK9Tfo,364
-mdbq-3.8.14.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-mdbq-3.8.14.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-3.8.14.dist-info/RECORD,,
+mdbq-3.8.16.dist-info/METADATA,sha256=TS9KZw82-cE9gTPtfKSLzhwWzda-8ZnZ6384Vm0xU4I,364
+mdbq-3.8.16.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mdbq-3.8.16.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-3.8.16.dist-info/RECORD,,