use strict; use warnings; sub url_segments { local($_) = @_; my $segments = { url => $_ }; return unless m{ \A (?: ([a-z]{3,6}) : (?://)? )? # proto ( [:a-z0-9@._-]+ ) # domain (?: ( .*? / ) # location ( ( [^/]*? ) # filename_only ( (?: \. \w*[a-z]\w* )* ) # ext ) (?: ( \? .* ) )? # query )? \Z }x; $segments->{proto} = $1 if $1; $segments->{domain} = $2 if $2; $segments->{location} = $3 if $3; $segments->{filename} = $4 if $4; $segments->{filename_only} = $5 if $5; $segments->{ext} = $6 if $6; $segments->{query} = $7 if $7; $segments } use YAML; print Dump( { map { $_ => url_segments $_ } qw( http://foo.com/downloads/pkg-5.6.tar.gz http://bar.com/list/file-5.6-win32.zip example.org/subd/golf.txt http://digg.com/page4 http://digg.com/page4?format=printable http://www.cnn.com/2008/US/07/17/beck.che.guevara/index.html https://tomwtriker:imzadi@coldmail.net/goethe.3.5.tar mailto:tomwtriker@coldmail.net ) } )