#!/usr/bin/perl use warnings; use strict; use LWP::Simple; use HTML::TokeParser::Simple; my $page=get('http://www.page.you.want.com/some/path'); my $p = HTML::TokeParser::Simple->new( \$page ); while ( my $token = $p->get_token ) { # This prints all text in an HTML doc (i.e., it strips the HTML) next unless $token->is_text; print $token->as_is; }