use strict;
use warnings;
use HTML::Tree;
use LWP::UserAgent ();
use Data::Dumper;
use open ':std', ':encoding(UTF-8)';
use utf8;
use HTML::TreeBuilder 5 -weak;
use LWP::UserAgent;
use File::Slurp;
use LWP::Simple;


sub test
{
my $url = "https://www.dnes.bg";
my $html = get $url;
print $html;
my $tree = HTML::TreeBuilder->new_from_content($html);


my @aelements = $tree->look_down(_tag => 'a');
	foreach my $aelement(@aelements)
	{
		        if ($aelement->as_text eq "България")
		        {
		                        print $aelement->attr('href');
		                        print "\n";
		        }
		        if ($aelement->as_text eq "Спорт")
		        {
		                        print $aelement->attr('href');
		                        print "\n";
		        }
		        if ($aelement->as_text eq "Бизнес")
		        {
		                        print $aelement->attr('href');
		                        print "\n";
		        }
	}
}


sub GetMainPage
{
my $url = $_[0];
my $ua = LWP::UserAgent->new();
my $html = get $url;
return $html;
}

sub ExtractCategory
{
	my $content = $_[0];
	my $category = $_[1];
	my $tree = HTML::TreeBuilder->new_from_content($content);
	my @elements = $tree->look_down(_tag => 'a');
	foreach my $element(@elements)
	{
                if ($element->as_text eq $category)
                {
                                print $element->attr('href');
                                print "\n";
		return $element->attr('href');
                }
	}
}

sub ExtractCategories
{
	my $html = shift;
	my @cats = @{$_[0]};
	my %urls=();
	my $tmp;
	#print $html;
	foreach my $cat(@cats)
	{
	print $cat;
	$tmp = ExtractCategory($html, $cat);
        $urls{$cat}= $tmp;
	#$returnpairs{$cat} = $tmp;
	}
	#print $urls{"Бизнес"};
	return \%urls;
}

sub ProcessCategory
{
	my $cat = %{$_[0]};
	my $html = GetMainPage($cat);
	my $tree = HTML::TreeBuilder->new_from_content($html);
	my $element = $tree->look_down(_tag => 'div', class => "more");
	print $element->as_text;
}


ProcessCategories
{
   my %cats = %{$_[0]};
   print $cats{'Бизнес'};
   foreach my $key (keys(%cats))
	{
	   ProcessCategory($key);
	}
}

sub main
{
   my $page = 1; # which page do we want to download the news from, can be expanded further so that with a loop we cycle trough any number of desired pages
   my $content = GetMainPage("https://www.dnes.bg/");
   my @categories = ("България", "Бизнес", "Спорт");
   my %catpairs = %{ExtractCategories($content, \@categories)};
   ProcessCategories(%catpairs);
}

main();