第2节 网站点击流项目(下)：4、受访分析

标签：mozilla   long   having   int   top   ever   source   log   stat   

2． 受访分析（从页面的角度分析）

select * from ods_click_pageviews limit 2;
+---------------------------------------+----------------------------------+----------------------------------+---------------------------------+------------------------------+---------------------------------+------------------------------------+----------------------------------------------------+----------------------------------------------------+--------------------------------------+-----------------------------+------------------------------+--+
| ods_click_pageviews.session | ods_click_pageviews.remote_addr | ods_click_pageviews.remote_user | ods_click_pageviews.time_local | ods_click_pageviews.request | ods_click_pageviews.visit_step | ods_click_pageviews.page_staylong | ods_click_pageviews.http_referer | ods_click_pageviews.http_user_agent | ods_click_pageviews.body_bytes_sent | ods_click_pageviews.status | ods_click_pageviews.datestr |
+---------------------------------------+----------------------------------+----------------------------------+---------------------------------+------------------------------+---------------------------------+------------------------------------+----------------------------------------------------+----------------------------------------------------+--------------------------------------+-----------------------------+------------------------------+--+
| 9ff03c4c-25f4-43fc-b3e0-08ea88b38fcc | 1.80.249.223 | - | 2013-09-18 07:57:33 | /hadoop-hive-intro/ | 1 | 60 | "http://www.google.com.hk/url?sa=t&rct=j&q=hive%E7%9A%84%E5%AE%89%E8%A3%85&source=web&cd=2&ved=0CC4QFjAB&url=%68%74%74%70%3a%2f%2f%62%6c%6f%67%2e%66%65%6e%73%2e%6d%65%2f%68%61%64%6f%6f%70%2d%68%69%76%65%2d%69%6e%74%72%6f%2f&ei=5lw5Uo-2NpGZiQfCwoG4BA&usg=AFQjCNF8EFxPuCMrm7CvqVgzcBUzrJZStQ&bvm=bv.52164340,d.aGc&cad=rjt" | "Mozilla/5.0(WindowsNT5.2;rv:23.0)Gecko/20100101Firefox/23.0" | 14764 | 200 | 20130918 |
| ba46b150-ca63-47d1-9cdd-e278df01f5d3 | 101.226.167.201 | - | 2013-09-18 09:30:36 | /hadoop-mahout-roadmap/ | 1 | 60 | "http://blog.fens.me/hadoop-mahout-roadmap/" | "Mozilla/4.0(compatible;MSIE8.0;WindowsNT6.1;Trident/4.0;SLCC2;.NETCLR2.0.50727;.NETCLR3.5.30729;.NETCLR3.0.30729;MediaCenterPC6.0;MDDR;.NET4.0C;.NET4.0E;.NETCLR1.1.4322;TabletPC2.0);360Spider" | 10335 | 200 | 20130918 |
+---------------------------------------+----------------------------------+----------------------------------+---------------------------------+------------------------------+---------------------------------+------------------------------------+----------------------------------------------------+----------------------------------------------------+--------------------------------------+-----------------------------+------------------------------+--+

--各页面访问统计
各页面PV：各个页面被访问了多少次

select request as request,count(1) as request_counts from
ods_weblog_detail group by request having request is not null order by request_counts desc limit 20;

-----------------------------------------------
--热门页面统计
统计20130918这个分区里面的受访页面的top10

drop table dw_hotpages_everyday;
create table dw_hotpages_everyday(day string,url string,pvs string);

insert into table dw_hotpages_everyday
select ‘20130918‘,a.request,a.request_counts from
(
select request as request,count(request) as request_counts
from ods_weblog_detail
where datestr=‘20130918‘
group by request
having request is not null
) a
order by a.request_counts desc limit 10;

统计每日最热门页面的top10
select a.month,a.day,a.request ,concat(a.month,a.day),a.total_request
from (
select month,day, request,count(1) as total_request
from ods_weblog_detail
where datestr = ‘20130918‘
group by request ,month ,day
having request is not null
order by total_request desc limit 10
) a;

第2节 网站点击流项目(下)：4、受访分析

标签：mozilla   long   having   int   top   ever   source   log   stat   

原文地址：https://www.cnblogs.com/mediocreWorld/p/11107376.html