com.taobao.taobao_iqiyi_3

azkaban/dm/pseudo_package_to_other_business/com_eg_android_AlipayGphone_reyun.sh

@@ -8,6 +8,7 @@ source ../../dmp_env.sh
 dt_today=$(date -d "$ScheduleTime 1 days ago" +"%Y%m%d")
 dt_slash_today=$(date -d "$ScheduleTime 1 days ago" +"%Y/%m/%d")
 update=$(date -d "$ScheduleTime 15 days ago" +"%Y-%m-%d")
+update02=$(date -d "$ScheduleTime 3 days ago" +"%Y-%m-%d")
 
 check_await "${TMP_EGGPLANTS_OUTPUT_PATH}/${dt_slash_today}"
 
@@ -36,8 +37,8 @@ spark-submit --class mobvista.dmp.datasource.dm.ComEgAndroidAlipayGphoneReyun \
  --conf spark.sql.shuffle.partitions=3000 \
  --conf spark.driver.maxResultSize=4g \
  --conf spark.network.timeout=720s \
- --master yarn --deploy-mode cluster  --executor-memory 8g --driver-memory 6g  --executor-cores 5  --num-executors 10 \
- ../../${JAR} -dt_today ${dt_today}    -output1 ${OUTPUT_PATH1}  -output2 ${OUTPUT_PATH2} -update ${update}  \
+ --master yarn --deploy-mode cluster  --executor-memory 8g --driver-memory 6g  --executor-cores 5  --num-executors 20 \
+ ../../${JAR} -dt_today ${dt_today}    -output1 ${OUTPUT_PATH1}  -output2 ${OUTPUT_PATH2} -update ${update}  -update02 ${update02} \
   -coalesce 200
 
 
@@ -57,4 +58,7 @@ com.ss.android.ugc.aweme_reyun
 com.taobao.litetao_btop
 com.ss.android.ugc.aweme_btop
 天级别入库dmp的business=other分区
+更新
+获取过去3天的爱奇艺淘宝安装包名的设备入库，针对com.taobao.taobao_iqiyi，
+限制过去三天活跃的设备伪包名入库。人群包名称可定为com.taobao.taobao_iqiyi_3
 '
\ No newline at end of file

src/main/scala/mobvista/dmp/datasource/dm/ComEgAndroidAlipayGphoneReyun.scala

@@ -29,6 +29,7 @@ class ComEgAndroidAlipayGphoneReyun extends CommonSparkJob with Serializable {
     options.addOption("output2", true, "[must] output2")
     options.addOption("dt_today", true, "[must] dt_today")
     options.addOption("update", true, "[must] update")
+    options.addOption("update02", true, "[must] update02")
     options
   }
 
@@ -44,6 +45,7 @@ class ComEgAndroidAlipayGphoneReyun extends CommonSparkJob with Serializable {
     val output2 = commandLine.getOptionValue("output2")
     val dt_today = commandLine.getOptionValue("dt_today")
     val update = commandLine.getOptionValue("update")
+    val update02 = commandLine.getOptionValue("update02")
 
     val spark = SparkSession.builder()
       .appName("ComEgAndroidAlipayGphoneReyun")
@@ -88,6 +90,15 @@ class ComEgAndroidAlipayGphoneReyun extends CommonSparkJob with Serializable {
            |    and package_name in ('com.taobao.litetao','com.ss.android.ugc.aweme')
            |    and device_type  in ('imei','gaid','oaid','idfa','imeimd5','gaidmd5','oaidmd5','idfamd5')
            |    and  update_date >= "${update}"
+           |union
+           |select
+           |    device_id, device_type ,concat("[\\"",package_name,"_3","\\"]")  as  package_name
+           |from
+           |    dwh.dm_install_list_v2
+           |where dt='${dt_today}' and business in ('dsp_req')
+           |    and package_name in ('com.taobao.taobao_iqiyi')
+           |    and device_type  in ('imei','gaid','oaid','idfa','imeimd5','gaidmd5','oaidmd5','idfamd5')
+           |    and  update_date >= "${update02}"
         """.stripMargin
 
       val df01: DataFrame = spark.sql(sql1).persist(StorageLevel.MEMORY_AND_DISK_SER)