@@ -29,7 +29,17 @@ from pyspark.sql import SparkSession, DataFrame
# from pyspark.sql.functions import lit
# import pytispark.pytispark as pti
fromelasticsearchimportElasticsearch
exists_es_dic={}
es=Elasticsearch([
{
'host':'172.16.31.17',
'port':9200,
},{
'host':'172.16.31.11',
'port':9200,
}])
defcon_sql(sql):
# 从数据库的表里获取数据
...
...
@@ -78,81 +88,10 @@ spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF
spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
huidu_device_id_sql=r"""
select t2.device_id from
--(select distinct(first_device) as device_id from online.ml_user_history_detail where partition_date = {today_str} and last_active_date >= {last_30_day_str}) t2
(select device_id from online.ml_device_day_active_status where partition_date = '{today_str}' and active_type in (1,2)) t2
LEFT JOIN
(
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d --去除机构刷单设备，即作弊设备（浏览和曝光事件去除）
WHERE partition_day='{today_str}'
union all
select distinct device_id
from dim.dim_device_user_staff --去除内网用户
)spam_pv
on spam_pv.device_id=t2.device_id
LEFT JOIN
(
SELECT partition_date,device_id
FROM
(--找出user_id当天活跃的第一个设备id
SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
FROM online.ml_user_updates
WHERE partition_date='{today_str}'
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = '{today_str}'
--马甲账号/模特用户
UNION ALL
SELECT user_id
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = '{today_str}'
AND (is_puppet = 'true' or is_classifyuser = 'true')
UNION ALL
--公司内网覆盖用户
select distinct user_id
from dim.dim_device_user_staff
UNION ALL
--登陆过医生设备
SELECT distinct t1.user_id
FROM
(
SELECT user_id, v.device_id as device_id
FROM online.ml_user_history_detail
LATERAL VIEW EXPLODE(device_history_list) v AS device_id
