use strict;
use warnings;

use LWP::Simple;
use HTML::Strip;

my $url = "http://www.expressen.se/ekonomi/1.1805368/reinfeldt-forsvarar-nya-sjukregler";
my $html = get($url);

defined $html or die "Can't fetch HTML from: ",$url;

my $hs = HTML::Strip->new();

my $clean_text = $hs->parse( $html );
$hs->eof;

#sentences spread across multiple lines
$clean_text =~ s/(\n)/ /g;
$clean_text =~ s/(\r)/ /g;

#compact double white space into dots
$clean_text =~ s/(\s){2,}/./g;

#compact dots into single dots
$clean_text =~ s/(\.){2,}/\./g;

#split sentances on dots
my @sentences = split(/\./, $clean_text);

my @realSentences = ();

#ignore sentences with single words
foreach my $sentence (@sentences)
{
  if(($sentence =~ tr/ //)>1)
  {
  	push @realSentences, $sentence;
  }
}

foreach (@realSentences) 
{
  print "$_\n";
}