# -*- 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 query
, all_search_uv as all_search_uv --全部搜索uv
, t3.all_search_pv as all_search_pv --全部搜索pv
FROM (
--搜索pvuv
SELECT query
, count(click.cl_id) as all_search_pv
, count(distinct click.cl_id) as all_search_uv
FROM (
SELECT cl_id,
partition_date,
action,
params['page_name'] as page_name,
params['input_type'] as input_type,
app_version,
params['query'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND ((action = 'do_search' AND params['input_type'] <> 'everyone_watch') or
action = 'search_result_click_search')
UNION all
SELECT cl_id,
partition_date,
action,
params['page_name'] as page_name,
params['input_type'] as input_type,
app_version,
params['query'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND action = 'do_search'
and params['input_type'] = 'everyone_watch'
and params['tab'] = '精选'
and page_name = 'home'
AND params['query'] not in ('AI测颜值', 'AI测肤质') --这两个词不跳转搜索结果页
union all
SELECT cl_id,
partition_date,
action,
'search_home' as page_name,
'' as input_type,
app_version,
params['query'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND action = 'on_click_card'
AND params['page_name'] = 'search_home'
union all
SELECT cl_id,
partition_date,
action,
'home' as page_name,
'首页-猜你喜欢' as input_type,
app_version,
params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND action = 'on_click_card'
AND params['in_page_pos'] = '猜你喜欢'
--AND params['tab_name']='精选'
AND params['card_type'] = 'search_word'
AND params['card_name'] not in ('AI测颜值', 'AI测肤质') --这两个词不跳转搜索结果页
--AND page_name='home' android的page_name为空
union all
SELECT cl_id,
partition_date,
action,
params['page_name'] as page_name,
'美购首页-大家都在搜' as input_type,
app_version,
params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND action = 'on_click_card'
AND params['page_name'] = 'welfare_home'
AND params['card_type'] = 'search_word'
AND params['in_page_pos'] = '大家都在搜'
union all
SELECT cl_id,
partition_date,
action,
params['page_name'] as page_name,
'高亮词' as input_type,
app_version,
params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '{start_date}'
AND partition_date < '{end_date}'
AND action = 'on_click_card'
AND params['card_type'] = 'highlight_word'
) click
GROUP BY query
) t3 order by all_search_uv asc
""".format(start_date='20201017',end_date='20201116')
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
# )