#!/usr/bin/perl
use strict;
use warnings;
use HTML::TokeParser;
my $p = HTML::TokeParser->new( *DATA ) or die;
my @html_blocks = ( '' );
while ( my $token = $p->get_token ) {
my @t = @{ $token };
my $type = $t[0];
my $type_tag = "$t[0] $t[1]";
my $text_pos = ($type eq 'S' ) ? 4
: ($type eq 'E' ) ? 2
: ($type eq 'T' ) ? 1
: ($type eq 'C' ) ? 1
: ($type eq 'D' ) ? 1
: ($type eq 'PI') ? 2
: die "Can't happen"
;
my $text = $t[$text_pos];
push @html_blocks, '' if $html_blocks[-1] and $type_tag eq 'S p';
$html_blocks[-1] .= $text;
push @html_blocks, '' if $html_blocks[-1] and $type_tag eq 'E p';
}
pop @html_blocks while $html_blocks[-1] eq '';
use Data::Dumper; $Data::Dumper::Useqq = 1;
print Dumper \@html_blocks;
__END__
HTML::TokeParser
NAME
HTML::TokeParser - Alternative HTML::Parser interface
use HTML::TokeParser;
--snip--
The HTML::TokeParser is an --snip--