#!/usr/bin/perl

use strict;
use LWP::UserAgent;
use HTTP::Request;

use Encode;  # you need this module

binmode STDOUT, ":utf8";

my $ua = LWP::UserAgent->new;

my $url = "some_url_that_works_for_you";
my $req = HTTP::Request->new( GET => $url );

my $res = $ua->request( $req );
$txt = decode( 'utf-8', $res->content );  # decode "external" utf8 to "internal"

my @accented = ( $txt =~ /(\w*?[^[:ascii:]]\w*)/g );
if ( @accented ) {
    printf( "found %d words with non-ascii characters.\n", scalar @accented );

    my @alphanumerics = grep /^\w+$/, @accented;
    printf( "of those, %d words match ^\\w+\$:\n ", scalar @alphanumerics );
    print join( "\n ", @alphanumerics ),"\n";

    my @diacritic_marks = grep /\p{NonspacingMark}/, @accented;
    printf( "and %d used separate diacritic marks:\n ", scalar @diacritic_marks );
    print join( "\n ", @diacritic_marks ), "\n";
}