update

tasks/crawler_week_report.py

@@ -395,6 +395,13 @@ WHERE partition_date>='{start_date}' AND partition_date<'{end_date}' and page_na
     device_df = spark.sql(baoguang_sql)
     device_df.show(1, False)
     sql_res = device_df.collect()
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
+    print("-----------------------------------------------------------------------------")
     for res in sql_res:
         print(res)
         print(res.query)
@@ -402,17 +409,19 @@ WHERE partition_date>='{start_date}' AND partition_date<'{end_date}' and page_na
     # for data in hive.cursor.fetchall():
     #     data_dic[data[0]] = data[1]
     # --query词曝光
-    query_sql = """
-SELECT params['query_words']
-FROM bl_hdfs_maidian_updates
-WHERE partition_date>='{start_date}' AND partition_date<'{end_date}'
-AND action = 'report_status'
-AND page_name in ('search_home','search_home_more','search_home_welfare','search_home_diary','search_home_wiki','search_home_post','search_home_hospital','search_home_doctor')
-    """.format(start_date=start_date_str,end_date=end_date_str)
-
-    device_df = spark.sql(baoguang_sql)
-    device_df.show(1, False)
-    device_df.collect()
+#     query_sql = """
+# SELECT params['query_words']
+# FROM online.bl_hdfs_maidian_updates
+# WHERE partition_date>='{start_date}' AND partition_date<'{end_date}'
+# AND action = 'report_status'
+# AND page_name in ('search_home','search_home_more','search_home_welfare','search_home_diary','search_home_wiki','search_home_post','search_home_hospital','search_home_doctor')
+#     """.format(start_date=start_date_str,end_date=end_date_str)
+#
+#     device_df = spark.sql(baoguang_sql)
+#     device_df.show(1, False)
+#     sql_res = device_df.collect()
+#     for res in sql_res:
+#         print(res)
     #     for single_keyword in device_df[0]:
     #         data_count = data_dic.get(single_keyword)
     #         if data_count: