#!/usr/bin/perl use strict; use HTML::TokeParser; my $sample_HTML = < blah. Just some random whatever. It might have some real HTML like a table or CSS styling or even some

IMPORTANT

words. Maybe even a form EOD my $p = HTML::TokeParser->new( \$sample_HTML ); my $in_cdata = 0; while ( my $token = $p->get_token ) { my ( $tkn_type, $tkn_content, @rest ) = @$token; if ( $tkn_type =~ /[SE]/ ) { $tkn_content = pop @rest; # last array element is full tag string } print $tkn_content if ( $in_cdata and $tkn_content !~ /cdata/ ); if ( $tkn_content =~ /cdata/i ) { $in_cdata += ( $tkn_type eq 'S' ) ? 1 : -1; } }