店铺新增字段计算 导出增加判断 空分区不执行

Pyspark_job/sqoop_export/dwt_fb_base_report.py

@@ -6,7 +6,7 @@ sys.path.append(os.path.dirname(sys.path[0]))
 from utils.db_util import DBUtil
 from utils.ssh_util import SSHUtil
 from utils.common_util import CommonUtil
-
+from utils.hdfs_utils import HdfsUtils
 if __name__ == '__main__':
     site_name = CommonUtil.get_sys_arg(1, None)
     date_type = CommonUtil.get_sys_arg(2, None)
@@ -36,6 +36,15 @@ if __name__ == '__main__':
     # 获取数据库连接
     engine = DBUtil.get_db_engine(db_type, site_name)
 
+    # 导出前校验 Hive 分区是否有数据，避免空分区触发交换导致 PG 数据被清空
+    hive_partition_path = f"/home/big_data_selection/dwt/dwt_aba_st_analytics/site_name={site_name}/date_type={date_type}/date_info={date_info}"
+    hive_files = HdfsUtils.read_list(hive_partition_path)
+    if not hive_files:
+        print(f"[ERROR] Hive 分区无数据文件，路径：{hive_partition_path}，跳过导出，请先检查 DWT 计算任务是否正常写入！")
+        engine.dispose()
+        sys.exit(1)
+    print(f"Hive 分区文件数：{len(hive_files)}，路径：{hive_partition_path}，继续导出")
+
     # 保证幂等性，先删除原始表同周期的数据
     sql = f"""
          drop table if exists {export_tb};
@@ -92,7 +101,36 @@ if __name__ == '__main__':
             "rating_30_day_num",
             "rating_90_day_num",
             "rating_1_year_num",
-            "rating_lifetime_num"
+            "rating_lifetime_num",
+            # 功能1：销量展示
+            "fb_shop_total_sales",
+            "fb_shop_home_sales",
+            "fb_shop_home_null_flag",
+            # 功能2：FBM 占比
+            "fb_fbm_asin_num",
+            "fb_fbm_valid_asin_num",
+            "fb_fbm_rate",
+            "fb_fbm_valid_rate",
+            # 功能3：Hot New 榜单
+            "fb_nsr_asin_num",
+            "fb_nsr_rate",
+            # 功能4：Best Seller 榜单
+            "fb_bs_asin_num",
+            "fb_bs_rate",
+            # 功能5：新品销量占比 / 新品数量占比（流量选品口径）
+            "fb_new_asin_sales_rate",
+            # 功能6：新品/老品平均利润率
+            "fb_new_ocean_profit_rate",
+            "fb_new_air_profit_rate",
+            "fb_old_ocean_profit_rate",
+            "fb_old_air_profit_rate",
+            "fb_flow_new_asin_rate",
+            # 功能7：店铺综合评分（各星级占比）
+            "fb_star_5_pct",
+            "fb_star_4_pct",
+            "fb_star_3_pct",
+            "fb_star_2_pct",
+            "fb_star_1_pct"
         ],
         partition_dict={
             "site_name": site_name,
@@ -117,8 +155,8 @@ if __name__ == '__main__':
         cp_index_flag=False,
     )
 
-    update_workflow_sql = f"""                
-        update selection.workflow_progress set `status`='导出pg集群完成', status_val=6, over_date=CURRENT_TIME, is_end='是' where page='店铺Feedback' 
+    update_workflow_sql = f"""
+        update selection.workflow_progress set `status`='导出pg集群完成', status_val=6, over_date=CURRENT_TIME, is_end='是' where page='店铺Feedback'
         and `date_info`='{date_info}' and date_type='{date_type}' and site_name='{site_name}'
     """
     CommonUtil.modify_export_workflow_status(update_workflow_sql, site_name, date_type, date_info)

Pyspark_job/sqoop_import/ods_seller_account_feedback.py

@@ -33,9 +33,10 @@ if __name__ == '__main__':
             num,
             created_at,
             updated_at,
-            regexp_replace(seller_address, E'[\\r\\n\\t]+', ' ', 'g') as seller_address,
-            regexp_replace(seller_rating,  E'[\\r\\n\\t]+', ' ', 'g') as seller_rating,
-            regexp_replace(feedback_histogram,  E'[\\r\\n\\t]+', ' ', 'g') as feedback_histogram
+            regexp_replace(seller_address,     E'[\\r\\n\\t]+', ' ', 'g') as seller_address,
+            regexp_replace(seller_rating,      E'[\\r\\n\\t]+', ' ', 'g') as seller_rating,
+            regexp_replace(feedback_histogram, E'[\\r\\n\\t]+', ' ', 'g') as feedback_histogram,
+            regexp_replace(metadata_json,      E'[\\r\\n\\t]+', ' ', 'g') as metadata_json
         from {import_table} 
         where 1=1
         and \$CONDITIONS