use strict;
use HTML::TokeParser::Simple;

my @letters = qw(A B C D E F G H I J K L M N O P Q R S T U V W X Y Z);
my $savePath = "C:/temp/quotes.txt";
open (OUT, ">>$savePath");

foreach my $letter (@letters) {
    my $baseUrl = "http://www.quotationspage.com/quotes/$letter.html";
    my $parent_parser = HTML::TokeParser::Simple->new( url => $baseUrl );
    my $parent_pr;
    while ( my $parent_token = $parent_parser->get_token ) {
        if (   $parent_token->is_tag('div')
            && $parent_token->get_attr('class') eq 'authorrow' )
        {
            $parent_pr = 1;
            next;
        }
        if ( $parent_pr && $parent_token->is_tag('a') ) {
            my $authorUrl =
              "http://www.quotationspage.com" . $parent_token->get_attr('href');
            my $author = $parent_token->get_attr('href');
            $author =~ /\/quotes\/(.*?)\//;
            $author = $1;
            $author =~ s/_/ /g;
            my $child_parser =
              HTML::TokeParser::Simple->new( url => $authorUrl );
            my $child_pr;
            my $quote;
            while ( my $child_token = $child_parser->get_token ) {
                if (   $child_token->is_tag('dt')
                    && $child_token->get_attr('class') eq 'quote' )
                {
                    $child_pr = 1;
                    next;
                }
                if ( $child_pr && $child_token->is_text ) {
                    $quote .= $child_token->as_is;
                    next;
                }
                else {
                    if ( $child_token->is_end_tag('dt') ) {
                        $child_pr = 0;
                        print "$quote|| $author\n\n";
                        print OUT "$quote|| $author\n";
                        $quote = undef;
                        next;
                    }
                }
            }

        }
        else {
            if ( $parent_token->is_end_tag('div') ) {
                $parent_pr = 0;
            }
        }
    }
}