no message

Pyspark_job/dwd/dwd_nsr_bsr_keepa_asin.py

@@ -36,7 +36,7 @@ class DwdNsrBsrKeepaAsin(Templates):
         self.df_asin_keepa = self.spark.sql(f"select 1+1;")
         self.partitions_by = ['site_name', 'date_type', 'date_info']
         self.reset_partitions(partitions_num=5)
-
+        self.get_date_info_tuple()
 
     @staticmethod
     def get_date_30_days_ago(date_str: str, date_format: str = "%Y-%m-%d") -> str:
@@ -65,19 +65,28 @@ class DwdNsrBsrKeepaAsin(Templates):
     # print(is_saturday("2026-02-06"))  # False
 
     def read_data(self):
+        if self.date_type == 'day':
             thirty_days_ago = self.get_date_30_days_ago(date_str=self.date_info)
+        else:
+            thirty_days_ago = ''
         print(f"1.1 读取最近30天的bsr的asin")
         sql_bsr = f"select asin, date_info, 1 as asin_cate_flag from dim_bsr_asin_rank_history where site_name='{self.site_name}' and date_info between '{thirty_days_ago}' and '{self.date_info}'"
+        if self.date_type == 'month':
+            sql_bsr = f"select asin, date_info, 1 as asin_cate_flag from dim_bsr_asin_rank_history where site_name='{self.site_name}' and date_info in {self.date_info_tuple}"
         print("sql_bsr:", sql_bsr)
         self.df_asin_bsr = self.spark.sql(sqlQuery=sql_bsr).cache()
         self.df_asin_bsr.show(10, truncate=False)
         print(f"1.2 读取最近30天的nsr的asin")
         sql_nsr = f"select asin, date_info, 2 as asin_cate_flag from dim_nsr_asin_rank_history where site_name='{self.site_name}' and date_info between '{thirty_days_ago}' and '{self.date_info}'"
+        if self.date_type == 'month':
+            sql_nsr = f"select asin, date_info, 2 as asin_cate_flag from dim_nsr_asin_rank_history where site_name='{self.site_name}' and date_info in {self.date_info_tuple}"
         print("sql_nsr:", sql_nsr)
         self.df_asin_nsr = self.spark.sql(sqlQuery=sql_nsr).cache()
         self.df_asin_nsr.show(10, truncate=False)
         print(f"1.3 读取最近30天的keepa的asin")
         sql_keepa = f"select distinct(asin), date_info, 3 as asin_cate_flag from ods_keepa_finder_asin where site_name='{self.site_name}' and date_info between '{thirty_days_ago}' and '{self.date_info}'"
+        if self.date_type == 'month':
+            sql_keepa = f"select asin, date_info, 3 as asin_cate_flag from ods_keepa_finder_asin where site_name='{self.site_name}' and date_info in {self.date_info_tuple}"
         print("sql_keepa:", sql_keepa)
         self.df_asin_keepa = self.spark.sql(sqlQuery=sql_keepa).cache()
         self.df_asin_keepa.show(10, truncate=False)
@@ -134,7 +143,7 @@ class DwdNsrBsrKeepaAsin(Templates):
         # self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_info", F.lit(self.date_info))
 
         # df_asin_today = self.df_save.filter(f"date_info='{self.date_info}'")
-        is_saturday_flag = self.is_saturday(self.date_info)
+        is_saturday_flag = True if self.date_type =='month' else self.is_saturday(self.date_info)
         self.df_save = self.df_asin_bsr.unionByName(self.df_asin_nsr, allowMissingColumns=True).unionByName(self.df_asin_keepa, allowMissingColumns=True)
         window = Window.partitionBy(['asin']).orderBy(F.asc("date_info"))
         self.df_save = self.df_save.withColumn(
@@ -162,6 +171,7 @@ class DwdNsrBsrKeepaAsin(Templates):
         content = f"整合asin完成--等待导出到pg提供爬虫使用--数量: {self.df_save.count()}"
         CommonUtil().send_wx_msg(users=users, title=title, content=content)
 
+        if self.date_type == 'day':
             # 更新30day分区
             hdfs_day = CommonUtil.build_hdfs_path(self.db_save_cate, {"site_name": self.site_name, "date_type": self.date_type, "date_info": self.date_info})
             hdfs_30day = CommonUtil.build_hdfs_path(self.db_save_cate, {"site_name": self.site_name, "date_type": "30day", "date_info": "1970-01"})