# -*- coding:UTF-8 -*- # @Time : 2020/9/8 13:39 # @File : spark_test.py # @email : litao@igengmei.com # @author : litao # -*- coding:UTF-8 -*- # @Time : 2020/9/4 17:07 # @File : search_meigou_ctr.py # @email : litao@igengmei.com # @author : litao import hashlib import json import pymysql import xlwt, datetime import redis # from pyhive import hive from maintenance.func_send_email_with_file import send_file_email from typing import Dict, List from elasticsearch_7 import Elasticsearch from elasticsearch_7.helpers import scan import sys import time from pyspark import SparkConf from pyspark.sql import SparkSession, DataFrame # from pyspark.sql.functions import lit # import pytispark.pytispark as pti from elasticsearch import Elasticsearch exists_es_dic = {} es = Elasticsearch([ { 'host': '172.16.31.17', 'port': 9200, }, { 'host': '172.16.31.11', 'port': 9200, }]) def con_sql(sql): # 从数据库的表里获取数据 db = pymysql.connect(host='172.16.40.158', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy', db='jerry_prod') cursor = db.cursor() cursor.execute(sql) result = cursor.fetchall() db.close() return result startTime = time.time() sparkConf = SparkConf() sparkConf.set("spark.sql.crossJoin.enabled", True) sparkConf.set("spark.debug.maxToStringFields", "100") sparkConf.set("spark.tispark.plan.allow_index_double_read", False) sparkConf.set("spark.tispark.plan.allow_index_read", True) sparkConf.set("spark.hive.mapred.supports.subdirectories", True) sparkConf.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", True) sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer") sparkConf.set("mapreduce.output.fileoutputformat.compress", False) sparkConf.set("mapreduce.map.output.compress", False) sparkConf.set("prod.gold.jdbcuri", "jdbc:mysql://172.16.30.136/doris_prod?user=doris&password=o5gbA27hXHHm&rewriteBatchedStatements=true") sparkConf.set("prod.mimas.jdbcuri", "jdbc:mysql://172.16.30.138/mimas_prod?user=mimas&password=GJL3UJe1Ck9ggL6aKnZCq4cRvM&rewriteBatchedStatements=true") sparkConf.set("prod.gaia.jdbcuri", "jdbc:mysql://172.16.30.143/zhengxing?user=work&password=BJQaT9VzDcuPBqkd&rewriteBatchedStatements=true") sparkConf.set("prod.tidb.jdbcuri", "jdbc:mysql://172.16.40.158:4000/eagle?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true") sparkConf.set("prod.jerry.jdbcuri", "jdbc:mysql://172.16.40.158:4000/jerry_prod?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true") sparkConf.set("prod.tispark.pd.addresses", "172.16.40.158:2379") sparkConf.set("prod.tispark.pd.addresses", "172.16.40.170:4000") sparkConf.set("prod.tidb.database", "jerry_prod") sparkConf.setAppName("test") spark = (SparkSession.builder.config(conf=sparkConf).config("spark.sql.extensions", "org.apache.spark.sql.TiExtensions") .config("spark.tispark.pd.addresses", "172.16.40.170:2379").enableHiveSupport().getOrCreate()) spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar") spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar") 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'") # print(huidu_device_id_sql) # huidu_device_id_df = spark.sql(huidu_device_id_sql) # huidu_device_id_df.createOrReplaceTempView("dev_view") sql_search_ctr = r""" select count(1),avg(session_pv),avg(session_pv2) from (SELECT partition_date, cl_id, v.recommend_type, count(distinct app_session_id) as session_pv , count(app_session_id) as session_pv1, count(card_id) as session_pv2 FROM ( SELECT partition_date, cl_id, case when card_content_type in ('qa','answer') then 'qa' when card_content_type in ('special_pool') then 'special' else card_content_type end as card_content_type, CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计') when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计') WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr') ) THEN array('ctr预估','合计') when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计') WHEN transaction_type like '%cvr' THEN array('cvr预估','合计') WHEN transaction_type in ('-1','smr') THEN array('smr','合计') when transaction_type in ('pgc','hotspot') then array('热点卡片') when transaction_type in ('newdata') then array('保量卡片') when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计') when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计') when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计') when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计') when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计') when transaction_type like 'deeplink%' then array('deeplink策略','合计') end AS recommend_type, card_id, app_session_id from online.ml_community_precise_exposure_detail WHERE partition_date='20201105' AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure AND is_exposure = '1' ----精准曝光 AND page_name ='home' AND tab_name = '精选' AND (transaction_type in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO') or transaction_type like '%ctr' or transaction_type like '%cvr' or transaction_type like 'deeplink%') AND card_content_type in ('qa','diary','user_post','answer','special_pool') group by partition_date, case when card_content_type in ('qa','answer') then 'qa' when card_content_type in ('special_pool') then 'special' else card_content_type end, cl_id, CASE when transaction_type in ('fmctr','samecity_fmctr') then array('fmctr','合计') when transaction_type in ('high_quality_fmctr') then array('high_quality_fmctr','合计') WHEN (transaction_type like '%ctr' and transaction_type not in ('high_quality_ctr','high_quality_fmctr','fmctr','samecity_fmctr')) THEN array('ctr预估','合计') when transaction_type in ('high_quality_ctr') then array('high_quality_ctr','合计') WHEN transaction_type like '%cvr' THEN array('cvr预估','合计') WHEN transaction_type in ('-1','smr') THEN array('smr','合计') when transaction_type in ('pgc','hotspot') then array('热点卡片') when transaction_type in ('newdata') then array('保量卡片') when transaction_type in ('hotspot_feed') then array('hotspot_feed','合计') when transaction_type in ('aistragegy') then array('新用户AI帖优先','合计') when transaction_type in ('excestragegy') then array('新用户精华帖优先','合计') when transaction_type in ('FIXEDSTRATEGY') then array('新氧新用户策略一','合计') when transaction_type in ('FIXEDSTRATEGY_VIDEO') then array('新氧新用户策略二','合计') when transaction_type like 'deeplink%' then array('deeplink策略','合计') end, card_id, app_session_id )a LATERAL VIEW explode (a.recommend_type) v as recommend_type group by partition_date,card_content_type,cl_id,v.recommend_type having session_pv2 >0) """.format(start_date='20201018',end_date='20201025') print(sql_search_ctr) search_ctr_df = spark.sql(sql_search_ctr) # spam_pv_df.createOrReplaceTempView("dev_view") search_ctr_df.show(1) sql_res = search_ctr_df.collect() print("-------------------------------") for res in sql_res: print(res) # print(res.query,res.search_pv) # results = es.search( # index='gm-dbmw-diary-read', # doc_type='diary', # timeout='10s', # body=body # )