#!/usr/bin/perl
use WWW::Mechanize;
use HTML::TokeParser;
use Switch;

my $mech = WWW::Mechanize->new( autocheck => 1 );

#set url
my $url = "http://www.realestate.com.au/cgi-bin/rsearch?a=o&id=106023887";

#$mech->get("http://search.cpan.org");
$mech->get($url);

#pass the stream to tokeparser
my $stream = HTML::TokeParser->new(\$mech->{content});

# go to first p tag
my $tag = $stream->get_tag("p");

# loop through p tags until we find classes
until ($tag->[1]{class} eq "officeFax") 
    {
    
    switch ($tag->[1]{class}) 
        {
		case "propertyID"		
            {
                $propid = $stream->get_trimmed_text("/p");
                
                # now get data straight after this tag
                $tag = $stream->get_tag("h1");
                $address = $stream->get_trimmed_text("/h1");
                $tag = $stream->get_tag("strong");
                    if ($tag->[1]{class} eq "price") 
                        {
                            $price = $stream->get_trimmed_text("/strong");
                        }
                $tag = $stream->get_tag("h2");
                    $header = $stream->get_trimmed_text("/h2");
                $tag = $stream->get_tag("h2");
                    # make sure it's correct part of source
                    if ($tag->[1]{class} eq "propertySummary")
                        {
                            $summary = $stream->get_trimmed_text("/h2");
                        }
                # Due to information not appearing all the time replicate tag and stream for status
                $tag2 = $tag;
                $stream2 = $stream;
                $tag2 = $stream2->get_tag("h3");
                    # Check for under contract/offer etc
                    if ($tag2->[1]{class} eq "highlighted")
                        {
                            $status = $stream2->get_trimmed_text("/h3");
                        }

                # Do the same for auction details
                $tag3 = $tag;
                $stream3 = $stream;
               
=pod
                $tag3 = $stream3->get_tag("span");

                    # Get "Price Authority" - at the moment seems to be only auction
                    if ($tag3->[1]{class} eq "price authority")
                        {
                            $priceauth = $stream3->get_trimmed_text("/span");
                        }
                $tag3 = $stream3->get_tag("span");
                    # Get Auction time
                    if ($tag3->[1]{class} eq "price auction")
                        {
                            $auction = $stream3->get_trimmed_text("/span");
                        }
=cut
                
                # Loop down to description
                $tag = $stream->get_tag("div");
                until ($tag->[1]{class} eq "description") 
                        {
                            $tag = $stream->get_tag("div");                        
                        }
                $description = $stream->get_trimmed_text("/div");
                # Get Agent Name
                $tag = $stream->get_tag("div");
                until ($tag->[1]{id} eq "contactAgentDetails") 
                        {
                            $tag = $stream->get_tag("div");                        
                        }
                $tag = $stream->get_tag("p");
                $agent = $stream->get_trimmed_text("/p");
            }
        case "officePhone"
            {
                $officephone = $stream->get_trimmed_text("/p");
            }
        case "officeFax"
            {
                $officefax  = $stream->get_trimmed_text("/p");
            }
	   }  
    # go to next p tag
    $tag = $stream->get_tag("p");
    }

# Loop down to property summary
until ($tag->[1]{id} eq "propertySummary") 
        {
            $tag = $stream->get_tag("div");                        
        }
        
$tag = $stream->get_tag("dt");
$mycat = $stream->get_trimmed_text("/dt");
# Get property summary details
until ($mycat eq "Close to:")
    {
        switch ($mycat)
            {
                case "Category:"
                    {
                        $tag = $stream->get_tag("dd");
                        $proptype = $stream->get_trimmed_text("/dd");
                    }
                case "Bedrooms:"
                    {
                        $tag = $stream->get_tag("dd");
                        $bed = $stream->get_trimmed_text("/dd");
                    }
                case "Bathrooms:"
                    {
                        $tag = $stream->get_tag("dd");
                        $bath = $stream->get_trimmed_text("/dd");
                    } 
                case "Land:"
                    {
                        $tag = $stream->get_tag("dd");
                        $land = $stream->get_trimmed_text("/dd");
                    } 
                case "Carport:"
                    {
                        $tag = $stream->get_tag("dd");
                        $carnumport = $stream->get_trimmed_text("/dd");
                    }
                case "Garage:"
                    {
                        $tag = $stream->get_tag("dd");
                        $carnumgar = $stream->get_trimmed_text("/dd");
                    }
                case "Municipality:"
                    {
                        $tag = $stream->get_tag("dd");
                        $municipality = $stream->get_trimmed_text("/dd");
                    }
            }
        $tag = $stream->get_tag("dt");
        $mycat = $stream->get_trimmed_text("/dt");
    }
    
print "$propid \n";
print "$status \n";
print $mech->title;    
print "Address: $address \n";
print "Price: $price \n";
print "Type: $proptype \n";
print "Bedrooms: $bed \n";
print "Bathrooms: $bath \n";
if (length($carnumport)>0)
    {
        print "Carport: $carnumport \n";
    }
if (length($carnumgar)>0)
    {
        print "Garage: $carnumgar \n";
    }
print "$header \n";
print "$summary \n";
print "$description \n";
print "Agent Details: \n";
print "$agent \n";
print "$officephone \n";
print "$officefax \n";