修改mysql连接

Pyspark_job/dwt/dwt_st_theme_agg.py

@@ -260,20 +260,20 @@ class DwtStThemeAgg(object):
         """
         self.df_pattern_words_base = self.spark.sql(sql)
         # 提前处理给叠词打上标签，并对不需要的叠词直接过滤
-        self.df_pattern_words_base = self.df_pattern_words_base.withColumn('twin_words_flag',self.u_judge_twin_words(F.col('search_term')))
+        self.df_pattern_words_base = self.df_pattern_words_base.withColumn('twin_words_flag', self.u_judge_twin_words(F.col('search_term')))
         self.df_pattern_words_base = self.df_pattern_words_base.filter(" twin_words_flag == 0").cache()
 
         sql = f"""
             select 
-               st_key, 
-               search_term, 
-               theme_ch, 
-               theme_en, 
-               theme_label_ch, 
-               theme_label_en,
-               pattern_type,
-               theme_label_num_info,
-               theme_label_unit_info 
+                st_key, 
+                search_term, 
+                theme_ch, 
+                theme_en, 
+                theme_label_ch, 
+                theme_label_en,
+                pattern_type,
+                theme_label_num_info,
+                theme_label_unit_info 
             from big_data_selection.dws_st_theme
             where site_name = '{self.site_name}'
               and date_type = '{self.date_type}'
@@ -283,15 +283,15 @@ class DwtStThemeAgg(object):
 
         # 获取主题词
         sql = f"""
-                    select  
-                        search_term, 
-                        concat_ws(",",collect_list(theme_label_en)) as pattern_list
-                    from big_data_selection.dws_st_theme
-                    where site_name = '{self.site_name}'
-                      and date_type = '{self.date_type}'
-                      and date_info = '{self.date_info}'
-                    group by st_key,search_term
-                                """
+            select  
+                search_term, 
+                concat_ws(",",collect_list(theme_label_en)) as pattern_list
+            from big_data_selection.dws_st_theme
+            where site_name = '{self.site_name}'
+              and date_type = '{self.date_type}'
+              and date_info = '{self.date_info}'
+            group by st_key,search_term
+        """
         self.df_theme = self.spark.sql(sql).cache()
 
         # sql获取最终品牌词匹配需保留得品牌词库

Pyspark_job/utils/db_util.py

@@ -34,8 +34,8 @@ class DBUtil(object):
     # mysql连接参数
     __mysql_host__ = "rm-wz9yg9bsb2zf01ea4yo.mysql.rds.aliyuncs.com"
     __mysql_port__ = "3306"
-    __mysql_username__ = "adv_yswg"
-    __mysql_pwd__ = "HCL1zcUgQesaaXNLbL37O5KhpSAy0c"
+    __mysql_username__ = "XP_Yswg2025"
+    __mysql_pwd__ = "Xp_Yswg2025@300"
 
     # pg连接参数正式库-h15
     __pgsql_host__ = "192.168.10.224"