"Learning" about pages

This is just a random thought htat popped into my head, so induldge me.

Most of my customers go to the same web pages day in and day out, some of
those web pages use server-side detection for clients and Squid always
attempts to cache it, so the user must hit reload to view the updated web
page. This happens all the time, the best way to fix it is to have the
adminstrator add expires tags and what not, but let's face it... not
everyone is going to do that.

One of those web pages is yahoo, it seems to show a different web page if
you are using a text browser versus a graphical browser. I could go in and
disable caching, however in time I'm going to have more hosts than I know
what to do with.

The idea I had was to keep a history log of web pages. Lets take
http://www.prevue.com/ which contains tv listings inside somewhere... almost
every time someone goes to www.prevue.com, the page is different, however
because of lack of Expires tags, the page never changes (even when you hit
reload, silly frames). Squid would remember that www.prevue.com has changed
every time we've reloaded and would automatically disable caching for it.

The logic would look something like:

Connect to www.prevue.com if not cached
Connect to www.prevue.com if page set expires and is outdated
Connect to www.prevue.com if last xxx fetches resulted in a new page

Just an idea,

Jordan

--
Jordan Mendelson     : http://jordy.wserv.com
Web Services, Inc.   : http://www.wserv.com