RE: [squid-users] User browsing time estimate

Joshua,

We use a product called NetTracker and it is put out by Sane Solutions
(www.sane.com).

While it isn't cheap (around $999 US), it does do the job quite well (it has
a
function for exactly what you're asking) and I thoughroughly recommend it.
The
software is web based and it is multi-platform (Unix, Linux, NT etc).

It can also analyse multiple servers (i.e. ftp, web, proxy etc) so i'd
suggest you
have a look. It does cost money, but sometimes you have to pay for what you
want.

That said, webalizer is a fine product and we previously used it until our
reporting
needs increased.

Regards,

Kieran

-----Original Message-----
From: Robert Collins [mailto:robertc@squid-cache.org]
Sent: Saturday, 12 October 2002 19:19
To: Joshua Penix
Cc: squid-users@squid-cache.org
Subject: Re: [squid-users] User browsing time estimate

On Thu, 2002-10-10 at 11:26, Joshua Penix wrote:
> Much to my dismay, I've got a boss asking for user web-browsing reports
from
> our Squid cache. I used 'sarg' to give him a general idea of the browsing
> patterns, but he wants more specific hours. He wants to know "roughly how
> much time has <blank> spent browsing the internet?"
>
> I attempted to explain that we don't really have enough data to produce
such
> a report - all we know is when someone asked for a webpage, we don't know
> how long that person spend reading it. However, upon further discussion
it
> was decided that we could get a rough estimate by applying a "moving
window"
> analysis to browsing logs. Basically if a user hits pages roughly every
30
> seconds between at 9:05AM and 9:20AM, we could safely assume that he/she
was
> browsing the internet for ~15 minutes that morning.

Yep, thats the only way to assess browser usage.

> If our moving window was 5 minutes, and the user didn't hit any pages
after
> 9:20AM until 11:15AM, we can assume that they stopped browsing at ~9:20,
add
> 15 minutes to their "total time on the internet" report, and then start
> accumulating time all over again based on the 11:15 session.
>
> Surely I could sit down and write a Perl log analyzer which makes these
> assumptions, but I'm hoping someone else already has. I looked at all the
> analyzers linked from squid-cache.org, and didn't really find anything
that
> seems to fit. Anyone have ideas on this?

I've not heard of any, but I'd guess that webalyzer would be a close
match, and relatively easy to extend to do that.

Cheers,
Rob
Received on Sat Oct 12 2002 - 19:47:16 MDT