#!/usr/bin/perl -w

use strict;

use Data::Dumper;
use HTML::TokeParser;
use URI;

use LWP::UserAgent;
use HTTP::Request;
use HTTP::Headers;
use HTTP::Response;
use HTTP::Cookies;
use HTML::LinkExtor;
use HTTP::Request::Common qw(GET POST);

my $name = "Griffin";

my $WHATWORKS = "http://www.bt.co.uk/directory-enquiries/dq_home.jsp";
$WHATWORKS = URI->new($WHATWORKS);

my $cookie_file = "cookies.txt";

my $cookie_jar = HTTP::Cookies->new(
    file => $cookie_file,
    autosave => 1,
    ignore_discard => 1, # IMPORTANT!!!!!!!!!!!!
);

my $url_search;
my $url_home = "http://www.bt.co.uk/directory-enquiries/dq_home.jsp";

my $ua = new LWP::UserAgent();
$ua->agent( "Mozilla/8.0(${^O};retmaspod)" );
$ua->cookie_jar( $cookie_jar );

###########################################################
## Get Main Search Page - this page contains the engine and session ids

my $req = GET $url_home;
my $res = $ua->request( $req );

open (LOG,">save.html");
my $fileOut = $res->content();
print LOG "$fileOut";

###########################################################
## Get 1st Page of Results
my %FORMOLA;
ParseIt( \$res->{_content} ); # Get Ids

$WHATWORKS->query_form(
  BV_EngineID => $FORMOLA{BV_EngineID},
  BV_SessionID => $FORMOLA{BV_SessionID},
  QRY => "res",
  new_search => "true",
  NAM => $name,
  PCD => "BT",
  limit => "50",
  CallingPage => "Homepage",
  STR => "",
  LOC => "",
  GIV => ""
);

warn Dumper{ $WHATWORKS->query_form};

###########################################################
## Get Sebsequent page for this name search

$url_search = $WHATWORKS;
$req = GET $url_search;

$res = $ua->request($req);
$fileOut = $res->content();
print LOG "$fileOut";

## find how many page in this search by maching Page 1 of *
if(  $res->content() =~ /Page (\d+) of (\d+)/)
{
 print "\nPages: $2";
}

# for each remaining page
for(my $i=1;$i<$2;$i++)
{
  my $startId = $i*50;

  my $WHATWORKS2 = "http://www.bt.co.uk/directory-enquiries/dq_home.jsp?Homepage&start_id=25&lci=0&QRY=res&NAM=Griffin&PCD=BT";  

print "\nhttp://www.bt.co.uk/directory-enquiries/dq_home.jsp?Homepage&start_id=25&lci=0&QRY=res&NAM=Griffin&PCD=BT",

  $WHATWORKS2 = URI->new($WHATWORKS2);
  $url_search = $WHATWORKS2;

  $req = GET $url_search;
  $res = $ua->request($req);

  $fileOut = $res->content();
  print LOG "$fileOut";
}

sub ParseIt {
  my $p  = new HTML::TokeParser( $_[0] );
  while(my $t = $p->get_token() )
  {
    my $ttype = shift @{ $t };
    if($ttype eq "S")    # start tag?
    {
      my($tag, $attr, $attrseq, $rawtxt) = @{ $t };
      if($tag eq 'input' && $attr->{type} eq 'hidden' )
      {
        $FORMOLA{ $attr->{name} } = $attr->{value}
      }
    }
  } 
}