in reply to easy HTML::TokeParser help request

With HTML::TokeParser::Simple

(assumes all links within class="full")

#!/usr/bin/perl use strict; use warnings; use HTML::TokeParser::Simple; my $html = do {local $/; <DATA>}; my $p = HTML::TokeParser::Simple->new(\$html) or die "can't parse: $!"; my ($in_full, @href); while (my $t = $p->get_token){ next if $t->is_start_tag('div') and $t->get_attr('class') and $t->get_attr('class') eq 'content'; $in_full++, next if $t->is_start_tag('div') and $t->get_attr('class') eq 'full'; $in_full = 0, next if $t->is_start_tag('div') and $t->get_attr('class') ne 'full'; next unless $in_full; push @href, $t->get_attr('href') if $t->is_start_tag('a'); } print "$_\n" for @href; __DATA__ <!-- some other divs and so here --> <div class="full"> <div class="content"> <ul class="topics"> <-- I want extract these links div class "full" only --> <li><a href="foobar">foobar</a></li> <li><a href="foobr2">fobar2</a></li> <li><a href="fobar3">foobr3</a></li> </ul> </div> </div> <div class="otherclass"> <div class="content"> <ul class="topics"> <-- I DO NOT WANT these links --> <li><a href="fbaor">fbaor</a></li> <li><a href="fabar2">fabar2</a></li> <li><a href="fbar3">fbar3</a></li> </ul> </div> </div> <!-- some other divs and so here --> <div class="full"> <div class="content"> <ul class="topics"> <-- I want extract these links div class "full" only --> <li><a href="foobar4">foobar4</a></li> <li><a href="foobr5">fobar5</a></li> <li><a href="fobar6">foobr6</a></li> </ul> </div> </div> <div class="otherclass"> <div class="content"> <ul class="topics"> <-- I DO NOT WANT these links --> <li><a href="fbaor">fbaor</a></li> <li><a href="fabar2">fabar2</a></li> <li><a href="fbar3">fbar3</a></li> </ul> </div> </div> <!-- some other divs and so here -->