店铺+搜索词增加兜底 历史回刷读取原数据/快照

Pyspark_job/dwt/dwt_aba_st_analytics.py

@@ -362,12 +362,13 @@ class DwtAbaStAnalytics(Templates):
         # self.df_asin_detail.show(10, truncate=True)
 
         # 仅获取 asin和country_name,对country_name进行了聚合处理
+        # dim_fb_asin_info 从 2026-06 开始有分区，历史月读 2026-06
+        asin_info_date = self.date_info if self.date_info >= '2026-06' else '2026-06'
         sql = f"""
-        select
-            asin,
+        select asin,
             concat_ws(\",\",collect_list(cast(fb_country_name as string))) as country_name
         from dim_fb_asin_info
-        where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{self.date_info}'
+        where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{asin_info_date}'
         group by asin;
         """
         self.df_seller_asin_country = self.spark.sql(sqlQuery=sql)
@@ -375,14 +376,11 @@ class DwtAbaStAnalytics(Templates):
         print("self.df_seller_asin_country:")
         # self.df_seller_asin_country.show(10, truncate=True)
 
-        # 获取 dim_fd_asin_info 表
+        # 获取卖家-asin 信息
         sql = f"""
-        select
-            asin,
-            seller_id as account_id,
-            fb_country_name as country_name
+        select asin, seller_id as account_id, fb_country_name as country_name
         from dim_fb_asin_info
-        where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{self.date_info}'
+        where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{asin_info_date}'
         """
         self.df_seller_asin_info = self.spark.sql(sqlQuery=sql)
         self.df_seller_asin_info = self.df_seller_asin_info.drop_duplicates(['asin']).repartition(80, 'asin').cache()
@@ -1073,7 +1071,7 @@ class DwtAbaStAnalytics(Templates):
             select 
                 word, 
                 langs 
-            from big_data_selection.tmp_lang_word_frequency;
+            from big_data_selection.lang_word_frequency;
         """
         lang_word_list = self.spark.sql(sql).collect()
         # 转为map

Pyspark_job/dwt/dwt_aba_st_analytics_report.py

@@ -324,7 +324,9 @@ class DwtAbaStAnalyticsReport(Templates):
         self.df_asin_measure = self.spark.sql(sql).repartition(80, 'asin').cache()
         self.df_asin_measure = self.df_asin_measure.na.fill({"asin_bsr_orders": 0})
 
-        print("1.7 读取dim_seller_asin_history_info系列表")
+        # dim_fb_asin_info 从 2026-06 开始有分区，历史月读 2026-06
+        print("1.7 读取dim_fb_asin_info卖家国家信息")
+        asin_info_date = self.date_info if self.date_info >= '2026-06' else '2026-06'
         sql = f"""
             select asin,
             case when upper(fb_country_name) = 'US' then 'US'
@@ -333,7 +335,7 @@ class DwtAbaStAnalyticsReport(Templates):
             when upper(fb_country_name) = 'FR' then 'FR'
             when upper(fb_country_name) = 'DE' then 'DE'
             else 'OTHER' end as seller_name
-            from dim_fb_asin_info where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{self.date_info}';
+            from dim_fb_asin_info where site_name = '{self.site_name}' and date_type = '{self.date_type}' and date_info = '{asin_info_date}';
         """
         print("sql:", sql)
         self.df_seller_asin = self.spark.sql(sql).repartition(80, 'asin').cache()

Pyspark_job/dwt/dwt_fb_top20_asin_info.py

@@ -76,13 +76,15 @@ class DwtFbTop20Info(object):
         print(sql)
 
         # account_name 从 dim_fb_detail 取(替代 ods_seller_account_syn)
-        print("获取 dim_fb_detail (account_name)")
+        # dim_fb_detail 从 2026-06 开始有分区，历史月读 2026-06
+        detail_date = self.date_info if self.date_info >= '2026-06' else '2026-06'
+        print(f"获取 dim_fb_detail (account_name, date_info={detail_date})")
         sql = f"""
             select seller_id, account_name
             from dim_fb_detail
             where site_name = '{self.site_name}'
               and date_type = '{self.date_type}'
-              and date_info = '{self.date_info}'
+              and date_info = '{detail_date}'
         """
         self.df_seller_account = self.spark.sql(sqlQuery=sql)
         print(sql)