# strip html tags
$text     =~ s/<[^>]*>//g;

# strip special chars
$text     =~ s/&[^;]*;//g;

# shove resulting words into an array
my @words = $text =~ /(\w+\'*\w+)/g;

##</code><code>##

#!/usr/bin/perl

use strict;
use warnings;

my $html = '';
while (<STDIN>) {
        $html .= $_;
}

my $begin = 0;
my $end = 0;
my @excerpts = ();
for (my $i=0;$i<length($html);$i++) {
        if (substr($html,$i,1) eq '>') {
                $begin = $i + 1;
        }

        if ($begin && substr($html,$i,1) eq '<') {
                $end = $i;
        }

        if ($begin && $end) {
                push @excerpts, { begin => $begin, end => $end };
                $begin = 0;
                $end = 0;
        }
}

# last snippet
if ($begin && !$end) {
        push @excerpts, { begin => $begin, end => length($html) };
}
foreach my $excerpt (@excerpts) {
        my $begin       = $excerpt->{begin} || 0;
        my $end         = $excerpt->{end} || 0;
        my $length      = $end - $begin;

        my $word_string = substr($html,$begin,$length);

        ...still working on search and replaces for $word_string...
}