#!/usr/bin/perl
# If required, adjust line above to point to Perl 5.
######################################################################
# fantomas shadowMaker(TM)                                           #
######################################################################
# $vers = "ver. 02.01.01"; # 2006-02-02                              #
######################################################################
# (c) Copyright 2002-2006 by fantomaster.com                         #
# All rights reserved.                                               #
# Copying, modification or distribution requires permission          #
# in writing by copyright holder.                                    #
# fantomas shadowMaker(TM) is the protected trade mark of            #
# fantomaster.com.                                                   # 
# URL: < http://fantomaster.com >                                    #
######################################################################

######################################################################
##########   PLEASE ADJUST THE FOLLOWING VARIABLES!   ################
#                                                                    #
#        "$standard" = denotes the core domain you want to redirect  #
#                      your  "normal" visitors to                    #
#                      (i.e. NO searchbots, etc.)                    #
#    "$keyword_flag" = Set this variable to "1" if you want to       #
#                      include the keyword into $standard            #
#      "LWP::Simple" = Required module for RSS Feed Inclusion        #
#         "XML::RSS" = Required module for RSS Feed Inclusion        #
#        "$rss_flag" = Set this variable to "1" if you want to       #
#                      include an RSS feed                           #
#       "$rss_items" = Define the number of items of the RSS feed    #
#        "$main_dir" = Main directory (DocumentRoot) for your pages  #
#       "$stats_dir" = Directory for log files and admin files       #
#   "$hits_log_file" = Log file listing SD hits                      #
#                      (Default name is: "hits.log")                 #
# " $human_log_file" = Log file listing SD hits from human visitors  #
#                      (Default name is: "human-hits.log")           #
# "$links_list_file" = Links list file name as generated in step 4   #
#                      (Default name is: "links.txt")                #
#     "$selist_file" = Search engine referrer parsing routines       #
#                      (Default name is: "selist.txt")               #
#     "$botbase_dir" = Directory of fantomas spiderSpy(TM) botBase   #
#                      (Default name is: "stats")                    #
#    "$botbase_file" = file containing spider robots list            #
#                      (Default name is: "spiderspy.txt")            #
######################################################################

$standard        = "http://realestate.puravida.com";

#$keyword_flag    = 0;

######################################################################
# RSS Feed Inclusion

#use LWP::Simple;
#use XML::RSS;
$rss_flag        = 1;
$rss_items       = 5;

######################################################################

$main_dir        = "/home/coreb4/public_html/discover-costa-rica-realestate/";
$stats_dir       = "/home/coreb4/public_html/discover-costa-rica-realestate/cgi-bin/stats/";

$hits_log_file   = "hits.log";
$humans_log_file = "human-hits.log";
$links_list_file = "links.txt";
$selist_file     = "selist.txt";

$botbase_dir     = "/home/coreb4/public_html/discover-costa-rica-realestate/cgi-bin/stats/";
$botbase_file    = "spiderspy.txt";

######################################################################
#############   NO EDITING BEYOND THIS LINE!   #######################
######################################################################

$query_string = "$ENV{'QUERY_STRING'}";
$remote_host  = "$ENV{'REMOTE_HOST'}";
$remote_addr  = "$ENV{'REMOTE_ADDR'}";
$user_agent   = "$ENV{'HTTP_USER_AGENT'}";
$referer      = "$ENV{'HTTP_REFERER'}";
$method       = "$ENV{'REQUEST_METHOD'}";

######################################################################

$switch_name = $query_string;
$switch_name =~ s/^\///;
$fantom_name = $switch_name;

######################################################################

&get_date;

&process_register;  

if ($search_engine) { &fantom } else { &standard }

exit;

######################################################################

sub get_date {
    ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst)=localtime(); 
    $mon++;
    $sec  = sprintf ("%02d", $sec);
    $min  = sprintf ("%02d", $min);
    $hour = sprintf ("%02d", $hour);
    $mday = sprintf ("%02d", $mday);
    $mon  = sprintf ("%02d", $mon);
    $year = scalar localtime;
    $year =~ s/.*?(\d{4})/$1/;
    $date = "$year-$mon-$mday, $hour:$min:$sec";
    
    return;
}         

######################################################################

sub process_register {
    open (REGISTER, "$botbase_dir/$botbase_file");
        @register=<REGISTER>;
    close (REGISTER);
    
    $search_engine = ();
    foreach $botbase (@register) {
        next if ($botbase =~ /^[#-]/);
        next if ($botbase =~ /^\s*$/);
        chomp $botbase;
        
        if ( $remote_addr eq $botbase ){ 
            $search_engine = 1;
            last;
        }
    }
    
    return;
}

######################################################################

sub standard {
    if ($keyword_flag) {
        if ($referer) {
            &process_engine_list;
            $keyword = &parse_referer($referer);
        }
    }
    elsif (-f "$stats_dir/$links_list_file" ) {
        if ($referer) {
            &process_engine_list;
            $keyword = &parse_referer($referer);
        }
    }

    if (-f "$stats_dir/$links_list_file" ) {
        open (STANDARD, "$stats_dir/$links_list_file");
            @list=<STANDARD>;
        close (STANDARD);
        
        foreach $line (@list) {
            next if ($line =~ /^[#-]/);
            next if ($line =~ /^\s*$/);
            chomp $line;
            ($field1, $field2) = split (/:::/, $line);
            $links{$field1} = $field2; 
        }
        
        if ( $links{$keyword} ) {
            if ( $links{$keyword} eq '<<STANDARDURL>>' ) {
                &print_location($standard);
            }
            else {
                &print_location($links{$keyword});
            }
        }
        else {
            $switch_name =~ /^(.+?)\-\d{2}/;
            $keyword = $1;
            $keyword =~ s/(\_|\-)/ /g;        
    
            if ( $links{$keyword} ) {
                if ( $links{$keyword} eq '<<STANDARDURL>>' ) {
                    &print_location($standard);
                }
                else {
                    &print_location($links{$keyword});                    
                }
            }
            else {
                &print_location($standard);
            }
        }
    }
    else {
        &print_location($standard);
    }
    
    &log_hits       ("$date -- $remote_host -- $remote_addr -- $switch_name -- $user_agent -- $referer -- $keyword -- $links{$keyword} -- $method\n");
    &log_human_hits ("$date -- $remote_host -- $remote_addr -- $switch_name -- $user_agent -- $referer -- $keyword -- $links{$keyword} -- $method\n");
    
    return;
}

######################################################################

sub fantom {
    @HTML = ();
 
    print "Content-type: text/html\n\n";
 
    if (! -f "$main_dir$fantom_name") { $fantom_name = "index.html" }
 
    open (FANTOM, "$main_dir$fantom_name");
        while (<FANTOM>) {
            $html_string .= $_;
        }
    close (FANTOM);
 
    $html_string =~ s|<\!--\#include virtual=\"(.+?)\"-->|&include_file("$main_dir$1")|egi;
 
    if ($rss_flag) {
        eval {
            $html_string = &include_rss($html_string);
        };
        if ($@) {
            $html_string =~ s|<<RSSFEEDURL:::(.*?)>>||s;
        }
    }

    print $html_string;
 
    &log_hits ("!!$date -- $remote_host -- $remote_addr -- $switch_name -- $user_agent -- $referer -- $method\n");
 
    return;
}                

######################################################################

sub include_file {
    my ($include_file) = @_;
    my $include_string;
    
    open (FILE, "$include_file");
        while (<FILE>) {
            $include_string .= $_;
        }
    close (FILE);
    
    return $include_string;
}

######################################################################

sub log_hits {
    open (HITS, ">>$stats_dir/$hits_log_file");
        print HITS @_;
    close (HITS);
 
    return;
} 

######################################################################

sub log_human_hits {
    open (HITS, ">>$stats_dir/$humans_log_file");
        print HITS @_;
    close (HITS);
 
    return;
} 

######################################################################

sub parse_referer {
    my ($referer) = @_;
    my ($keyword) = ();
 
    foreach $se (@se) {
        foreach $query ( @{ $query{$se} } ) {
            if ($referer =~ m/^http:\/\/($domain{$se})(.*?)($query)(.*?)(\&|$)/i){
               $keyword = $4;
               if (! $keyword) {next}
   
               $keyword =~ s|^cache\:(.+)\+(.*?)\&|$2|;
            }
        }
    }
    return ($keyword);
}

######################################################################

sub process_engine_list {
    open (ENGINES, "$botbase_dir/$selist_file") 
        || die "$botbase_dir/$selist_file: $!";
    
    $i = -1;
    @engines  = ();
    @engine_referer = ();
    @engine_submit  = ();
    
    while (<ENGINES>){
        next if /^\s*$/;
        next if /^\s*#/;
        chomp;
        
        $_ =~ s/^ *(.+?) *$/$1/g;
        
        if (/^\[(.+)\]$/){
            $i++;
            $se = $1;
            $se[$i] = $se;
        }
        if (/domain:\s*(.+)$/){
            $domain = quotemeta $1;
            if ($domain{$se}){
                $domain{$se} = join ("|", $domain{$se}, $domain);
            }
            else {
                $domain{$se} = $domain;
            }
        }
        
        if (/query:\s*(.+)$/){
            $query = quotemeta $1;
            push ( @{ $query{$se} }, $query );
        }
    }
    close (ENGINES);
    
    return;
}

######################################################################

sub decode_keyword {
   my ($keyword) = @_;
   $keyword =~ s/\+/ /g;
   $keyword =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg;
   return $keyword;
}

######################################################################

sub print_location {
    my ($standard) = @_;
    
    if ($keyword_flag) {
        if (! $keyword) {
            $standard =~ s/<<keyword>>//;
        }
        else {
            $standard =~ s/<<keyword>>/$keyword/;
            
            $keyword = &decode_keyword($keyword);
            $keyword =~ s|^\s+||;
            $keyword =~ s|\s+$||;
            $keyword =~ s|\s+| |g;
        }
    }

    print "Location: $standard\n\n";
    
    return;
}

######################################################################

sub include_rss {
    my ($html_string) = @_;
    
    if ($html_string =~ /<<RSSFEEDURL:::(.+?)>>/) {
        $rss_url = $1;
    }
    else {
        return $html_string;
    }
    
    my $rss = XML::RSS->new;

    my $content = get($rss_url);

    $rss->parse($content);

    foreach my $item ( @{$rss->{'items'}} ) {
        $i++;
        if ($rss_items) {
            if ($i > $rss_items) { last }
        }
        $rss_string .= "<p><a href=$item->{'link'}>$item->{'title'}</a><br>$item->{'description'}\n";
    }

    $html_string =~ s|<<RSSFEEDURL:::(.+?)>>|<BR>$rss_string<BR>|s;

    return $html_string;
}

######################################################################