#!/usr/bin/perl -w use strict; use HTML::TokeParser::Simple; use Data::Dumper; my $pseudo_html; { local $/; $pseudo_html = ; } print Dumper parse_column_list( $pseudo_html ); sub parse_column_list { my ($str) = @_; my $p = HTML::TokeParser::Simple->new(\$str); my (@cl, $label, %attr); my %attr_default = ( na => 0 ); while(my $t = $p->get_token) { if ( $t->is_start_tag( 'column' ) ) { $label = ''; %attr = (%attr_default, %{$t->return_attr}); } elsif ( $t->is_end_tag( 'column' ) ) { push @cl, { %attr, label => $label }; } else { $label .= $t->return_text; } } return \@cl; } __DATA__ Colum One Header Column Two Header Etcetera