欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识！
您现在的位置是： 首页

用户行为数据仓库 第 4 节 DWD层数据解析脚本

程序员文章站 2024-03-17 13:38:52
...

上篇：用户行为数据仓库 第 3 节 数仓搭建之DWD层

1、脚本编写

（1）在hadoop1的/home/MrZhou/bin目录下创建脚本

[root@hadoop1 bin]# vim dwd_base_log.sh

//在脚本中编写如下内容
# 定义变量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
	do_date=$1
else 
	do_date=`date -d "-1 day" +%F`  
fi 

sql="
	add jar /opt/module/hive/hivefunction-1.0-SNAPSHOT.jar;

	create temporary function base_analizer as 'com.atguigu.udf.BaseFieldUDF';
	create temporary function flat_analizer as 'com.atguigu.udtf.EventJsonUDTF';

 	set hive.exec.dynamic.partition.mode=nonstrict;

	insert overwrite table "$APP".dwd_base_event_log 
	PARTITION (dt='$do_date')
	select
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source ,
	os ,
	area ,
	model ,
	brand ,
	sdk_version ,
	gmail ,
	height_width ,
	network ,
	lng ,
	lat ,
	app_time ,
	event_name , 
	event_json , 
	server_time  
	from
	(
	select
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[0]   as mid_id,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[1]   as user_id,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[2]   as version_code,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[3]   as version_name,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[4]   as lang,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[5]   as source,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[6]   as os,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[7]   as area,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[8]   as model,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[9]   as brand,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[10]   as sdk_version,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[11]  as gmail,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[12]  as height_width,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[13]  as app_time,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[14]  as network,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[15]  as lng,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[16]  as lat,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[17]  as ops,
	split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[18]  as server_time
	from "$APP".ods_event_log where dt='$do_date'  and base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la')<>'' 
	) sdk_log lateral view flat_analizer(ops) tmp_k as event_name, event_json;
"

$hive -e "$sql"

（2）增加脚本执行权限

[rootu@hadoop1 bin]# chmod 777 dwd_base_log.sh

（3）脚本使用

[rootu@hadoop1 bin]# dwd_base_log.sh 2019-02-11

（4）查询导入结果

hive (gmall)> 
select * from dwd_base_event_log where dt='2019-02-11' limit 2;

脚本执行时间
企业开发中一般在每日凌晨30分~1点

2、DWD层事件表获取

用户行为数据仓库 第 4 节 DWD层数据解析脚本

3、商品点击表解析

用户行为数据仓库 第 4 节 DWD层数据解析脚本
（1）建表语句

hive (gmall)> 
drop table if exists dwd_display_log;
CREATE EXTERNAL TABLE dwd_display_log(
`mid_id` string,
`user_id` string,
`version_code` string,
`version_name` string,
`lang` string,
`source` string,
`os` string,
`area` string,
`model` string,
`brand` string,
`sdk_version` string,
`gmail` string,
`height_width` string,
`app_time` string,
`network` string,
`lng` string,
`lat` string,
`action` string,
`goodsid` string,
`place` string,
`extend1` string,
`category` string,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_display_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_display_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.action') action,
get_json_object(event_json,'$.kv.goodsid') goodsid,
get_json_object(event_json,'$.kv.place') place,
get_json_object(event_json,'$.kv.extend1') extend1,
get_json_object(event_json,'$.kv.category') category,
server_time
from dwd_base_event_log 
where dt='2019-02-10' and event_name='display';

（3）测试

hive (gmall)> select * from dwd_display_log limit 2;

3、商品详情页表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_newsdetail_log;
CREATE EXTERNAL TABLE dwd_newsdetail_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string, 
`app_time` string,  
`network` string, 
`lng` string, 
`lat` string, 
`entry` string,
`action` string,
`goodsid` string,
`showtype` string,
`news_staytime` string,
`loading_time` string,
`type1` string,
`category` string,
`server_time` string)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_newsdetail_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_newsdetail_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.entry') entry,
get_json_object(event_json,'$.kv.action') action,
get_json_object(event_json,'$.kv.goodsid') goodsid,
get_json_object(event_json,'$.kv.showtype') showtype,
get_json_object(event_json,'$.kv.news_staytime') news_staytime,
get_json_object(event_json,'$.kv.loading_time') loading_time,
get_json_object(event_json,'$.kv.type1') type1,
get_json_object(event_json,'$.kv.category') category,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='newsdetail';

（3）测试

hive (gmall)> select * from dwd_newsdetail_log limit 2;

4、商品列表页表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_loading_log;
CREATE EXTERNAL TABLE dwd_loading_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string,
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`action` string,
`loading_time` string,
`loading_way` string,
`extend1` string,
`extend2` string,
`type` string,
`type1` string,
`server_time` string)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_loading_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_loading_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.action') action,
get_json_object(event_json,'$.kv.loading_time') loading_time,
get_json_object(event_json,'$.kv.loading_way') loading_way,
get_json_object(event_json,'$.kv.extend1') extend1,
get_json_object(event_json,'$.kv.extend2') extend2,
get_json_object(event_json,'$.kv.type') type,
get_json_object(event_json,'$.kv.type1') type1,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='loading';

（3）测试

hive (gmall)> select * from dwd_loading_log limit 2;

5、广告表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_ad_log;
CREATE EXTERNAL TABLE dwd_ad_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`entry` string,
`action` string,
`content` string,
`detail` string,
`ad_source` string,
`behavior` string,
`newstype` string,
`show_style` string,
`server_time` string)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_ad_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_ad_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.entry') entry,
get_json_object(event_json,'$.kv.action') action,
get_json_object(event_json,'$.kv.content') content,
get_json_object(event_json,'$.kv.detail') detail,
get_json_object(event_json,'$.kv.source') ad_source,
get_json_object(event_json,'$.kv.behavior') behavior,
get_json_object(event_json,'$.kv.newstype') newstype,
get_json_object(event_json,'$.kv.show_style') show_style,
server_time
from dwd_base_event_log 
where dt='2019-02-10' and event_name='ad';

（3）测试

hive (gmall)> select * from dwd_ad_log limit 2;

6、消息通知表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_notification_log;
CREATE EXTERNAL TABLE dwd_notification_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string,
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`action` string,
`noti_type` string,
`ap_time` string,
`content` string,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_notification_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_notification_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.action') action,
get_json_object(event_json,'$.kv.noti_type') noti_type,
get_json_object(event_json,'$.kv.ap_time') ap_time,
get_json_object(event_json,'$.kv.content') content,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='notification';

（3）测试

hive (gmall)> select * from dwd_notification_log limit 2;**

7、用户前台活跃表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_active_foreground_log;
CREATE EXTERNAL TABLE dwd_active_foreground_log(
`mid_id` string,
`user_id` string,
`version_code` string,
`version_name` string,
`lang` string,
`source` string,
`os` string,
`area` string,
`model` string,
`brand` string,
`sdk_version` string,
`gmail` string,
`height_width` string,
`app_time` string,
`network` string,
`lng` string,
`lat` string,
`push_id` string,
`access` string,
`server_time` string)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_foreground_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_active_foreground_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.push_id') push_id,
get_json_object(event_json,'$.kv.access') access,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='active_foreground';

（3）测试

hive (gmall)> select * from dwd_active_foreground_log limit 2;

8、用户后台活跃表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_active_background_log;
CREATE EXTERNAL TABLE dwd_active_background_log(
`mid_id` string,
`user_id` string,
`version_code` string,
`version_name` string,
`lang` string,
`source` string,
`os` string,
`area` string,
`model` string,
`brand` string,
`sdk_version` string,
`gmail` string,
 `height_width` string,
`app_time` string,
`network` string,
`lng` string,
`lat` string,
`active_source` string,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_background_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_active_background_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.active_source') active_source,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='active_background';

（3）测试

hive (gmall)> select * from dwd_active_background_log limit 2;

9、 评论表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_comment_log;
CREATE EXTERNAL TABLE dwd_comment_log(
`mid_id` string,
`user_id` string,
`version_code` string,
`version_name` string,
`lang` string,
`source` string,
`os` string,
`area` string,
`model` string,
`brand` string,
`sdk_version` string,
`gmail` string,
`height_width` string,
`app_time` string,
`network` string,
`lng` string,
`lat` string,
`comment_id` int,
`userid` int,
`p_comment_id` int, 
`content` string,
`addtime` string,
`other_id` int,
`praise_count` int,
`reply_count` int,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_comment_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_comment_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.comment_id') comment_id,
get_json_object(event_json,'$.kv.userid') userid,
get_json_object(event_json,'$.kv.p_comment_id') p_comment_id,
get_json_object(event_json,'$.kv.content') content,
get_json_object(event_json,'$.kv.addtime') addtime,
get_json_object(event_json,'$.kv.other_id') other_id,
get_json_object(event_json,'$.kv.praise_count') praise_count,
get_json_object(event_json,'$.kv.reply_count') reply_count,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='comment';

（3）测试

hive (gmall)> select * from dwd_comment_log limit 2;

10、 收藏表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_favorites_log;
CREATE EXTERNAL TABLE dwd_favorites_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`id` int, 
`course_id` int, 
`userid` int,
`add_time` string,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_favorites_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_favorites_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.id') id,
get_json_object(event_json,'$.kv.course_id') course_id,
get_json_object(event_json,'$.kv.userid') userid,
get_json_object(event_json,'$.kv.add_time') add_time,
server_time
from dwd_base_event_log 
where dt='2019-02-10' and event_name='favorites';

（3）测试

hive (gmall)> select * from dwd_favorites_log limit 2;

11、点赞表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_praise_log;
CREATE EXTERNAL TABLE dwd_praise_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`id` string, 
`userid` string, 
`target_id` string,
`type` string,
`add_time` string,
`server_time` string
)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_praise_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_praise_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.id') id,
get_json_object(event_json,'$.kv.userid') userid,
get_json_object(event_json,'$.kv.target_id') target_id,
get_json_object(event_json,'$.kv.type') type,
get_json_object(event_json,'$.kv.add_time') add_time,
server_time
from dwd_base_event_log
where dt='2019-02-10' and event_name='praise';

（3）测试

hive (gmall)> select * from dwd_praise_log limit 2;

12、 错误日志表

（1）建表语句

hive (gmall)> 
drop table if exists dwd_error_log;
CREATE EXTERNAL TABLE dwd_error_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`errorBrief` string, 
`errorDetail` string, 
`server_time` string)
PARTITIONED BY (dt string)
location '/warehouse/gmall/dwd/dwd_error_log/';

（2）导入数据

hive (gmall)> 
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table dwd_error_log
PARTITION (dt='2019-02-10')
select 
mid_id,
user_id,
version_code,
version_name,
lang,
source,
os,
area,
model,
brand,
sdk_version,
gmail,
height_width,
app_time,
network,
lng,
lat,
get_json_object(event_json,'$.kv.errorBrief') errorBrief,
get_json_object(event_json,'$.kv.errorDetail') errorDetail,
server_time
from dwd_base_event_log 
where dt='2019-02-10' and event_name='error';

（3）测试

hive (gmall)> select * from dwd_error_log limit 2;

13、 DWD层事件表加载数据脚本

（1）在hadoop1。的/home/MrZhou/bin目录下创建脚本

[root@hadoop1 bin]# vim dwd_event_log.sh

//在脚本中编写如下内容
#!/bin/bash

# 定义变量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
	do_date=$1
else 
	do_date=`date -d "-1 day" +%F`  
fi 

sql="
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table "$APP".dwd_display_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.goodsid') goodsid,
	get_json_object(event_json,'$.kv.place') place,
	get_json_object(event_json,'$.kv.extend1') extend1,
	get_json_object(event_json,'$.kv.category') category,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='display';


insert overwrite table "$APP".dwd_newsdetail_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.entry') entry,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.goodsid') goodsid,
	get_json_object(event_json,'$.kv.showtype') showtype,
	get_json_object(event_json,'$.kv.news_staytime') news_staytime,
	get_json_object(event_json,'$.kv.loading_time') loading_time,
	get_json_object(event_json,'$.kv.type1') type1,
	get_json_object(event_json,'$.kv.category') category,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='newsdetail';


insert overwrite table "$APP".dwd_loading_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.loading_time') loading_time,
	get_json_object(event_json,'$.kv.loading_way') loading_way,
	get_json_object(event_json,'$.kv.extend1') extend1,
	get_json_object(event_json,'$.kv.extend2') extend2,
	get_json_object(event_json,'$.kv.type') type,
	get_json_object(event_json,'$.kv.type1') type1,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='loading';


insert overwrite table "$APP".dwd_ad_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.entry') entry,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.content') content,
	get_json_object(event_json,'$.kv.detail') detail,
	get_json_object(event_json,'$.kv.source') ad_source,
	get_json_object(event_json,'$.kv.behavior') behavior,
	get_json_object(event_json,'$.kv.newstype') newstype,
	get_json_object(event_json,'$.kv.show_style') show_style,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='ad';


insert overwrite table "$APP".dwd_notification_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.noti_type') noti_type,
	get_json_object(event_json,'$.kv.ap_time') ap_time,
	get_json_object(event_json,'$.kv.content') content,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='notification';


insert overwrite table "$APP".dwd_active_foreground_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
get_json_object(event_json,'$.kv.push_id') push_id,
get_json_object(event_json,'$.kv.access') access,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='active_foreground';


insert overwrite table "$APP".dwd_active_background_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.active_source') active_source,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='active_background';


insert overwrite table "$APP".dwd_comment_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.comment_id') comment_id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.p_comment_id') p_comment_id,
	get_json_object(event_json,'$.kv.content') content,
	get_json_object(event_json,'$.kv.addtime') addtime,
	get_json_object(event_json,'$.kv.other_id') other_id,
	get_json_object(event_json,'$.kv.praise_count') praise_count,
	get_json_object(event_json,'$.kv.reply_count') reply_count,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='comment';


insert overwrite table "$APP".dwd_favorites_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.id') id,
	get_json_object(event_json,'$.kv.course_id') course_id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.add_time') add_time,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='favorites';


insert overwrite table "$APP".dwd_praise_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.id') id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.target_id') target_id,
	get_json_object(event_json,'$.kv.type') type,
	get_json_object(event_json,'$.kv.add_time') add_time,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='praise';


insert overwrite table "$APP".dwd_error_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.errorBrief') errorBrief,
	get_json_object(event_json,'$.kv.errorDetail') errorDetail,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='error';
"

$hive -e "$sql"

(2)增加脚本执行权限

[root@hadoop1 bin]# chmod 777 dwd_event_log.sh

(3) 脚本使用

[root@hadoop1 bin]# dwd_event_log.sh 2019-02-11

(4) 查询导入结果

hive (gmall)> 
select * from dwd_comment_log where dt='2019-02-11' limit 2;

(5) 脚本执行时间
企业开发中一般在每日凌晨30分~1点

相关标签： 电商数仓

上一篇： 手动安装composer

下一篇： 剑指OFFER 面试题15（二进制）：二进制中1的个数 （JAVA）

推荐阅读