BEGIN { $ENV{LC_ALL} = $ENV{LANG} = 'sv_SE.UTF-8' }
use strict;
use warnings;
use utf8;
use open ':std', ':locale';
use LWP::UserAgent qw( get );
use HTML::Strip qw( );
use HTML::Entities qw( decode_entities );
use Text::Sentence qw( split_sentences );
my $userAgent = LWP::UserAgent->new();
#$userAgent->agent('Mozilla/5.0');
my $url = "http://www.expressen.se";
my $response = $userAgent->get($url);
die "Can't get $url: ", $response->status_line
unless $response->is_success;
my $hs = HTML::Strip->new( decode_entities => 0 );
my $parsedContent = $hs->parse( $response->content );
utf8::decode( my $decodedParsedContent = $parsedContent );
$decodedParsedContent =~ s/(\s)+/ /g; # remove double whitespace
decode_entities(my $decodedParsedContentWithDecodeEntities = $decodedParsedContent);
my @sentences = split_sentences( $decodedParsedContentWithDecodeEntities );
foreach my $sentence (@sentences)
{
#$sentence =~ s/^\s+//; # remove leading whitespace
#$sentence =~ s/\s+$//; # remove trailing
decode_entities(my $sentenceDecodeEntities = $sentence);
while ($sentenceDecodeEntities =~ /(\w+)/g)
{
print "$1 : ".$sentenceDecodeEntities."\n";
}
}
####
gor : BLOGG Europe Turnéblogg Mic i vĺr replokal "The Dungeon" BLOGG Lotta Gröning Krönikör Demokratifiasko...
##
##
gor : BLOGG Europe Turnéblogg Mic i vĺr replokal "The Dungeon" BLOGG Lotta Gröning Krönikör Demokratifiasko...