merchantwords日志数据完善

Pyspark_job/dim/dim_merchantwords_detail.py

@@ -45,6 +45,8 @@ class DimMerchantwordsDetail(object):
         ])
         self.save_cols = ['keyword', 'volume', 'avg3m', 'avg12m', 'trend', 'depth', 'strength',
                           'prominence', 'appearance', 'in_latest_batch', 'create_time']
+        # 待爬取keyword总量，用于计算覆盖度
+        self.total_keyword_count = 222894900
         self.last_date_info = None
         self.df_today   = None
         self.df_history = None
@@ -171,7 +173,9 @@ class DimMerchantwordsDetail(object):
             f"SELECT COUNT(1) AS cnt FROM {self.hive_table} "
             f"WHERE site_name='{self.site_name}' AND date_info='{self.date_info}'"
         ).collect()[0]['cnt']
-        print(f"实际写入行数 written_count={written_count:,}，预期 new_count={new_count:,}")
+        print(f"历史数据量 old_count={old_count:,}，最新数据量 new_count={new_count:,}，"
+              f"新增keyword数量={new_count - old_count:,}，"
+              f"覆盖度={new_count / self.total_keyword_count:.2%}（{new_count:,}/{self.total_keyword_count:,}）")
         if written_count != new_count:
             print(f"❌ 写入校验失败 written_count={written_count} != new_count={new_count}，保留历史分区不删！")
             return