#!/usr/bin/perl 

#########################################################
####              CONFIGURATION PARAMETERS      ####
#########################################################
######### The Page you want the script to fetch.
my $return_URL = "http://203.59.39.226/crabbait/index.html";
#my $return_URL = "http://203.59.39.226/cgi-bin/test.pl";
 # The location of the file the html is saved as.
my $file = 'D:/Inetpub/Scripts/fetchtest/images/url.html';
 # The url to the local directory the images are saved in.
my $images_url = 'http://192.168.0.4/cgi-bin/fetchtest/images/';
 # The local server path to the directory the images are saved in.
my $images_path = 'D:/Inetpub/Scripts/fetchtest/images';
 # The local server path to the directory this script is in.
my $cgi_path = 'D:/Inetpub/Scripts/fetchtest';
 # The Local URL of the .html file.
my $html_file = 'http://192.168.0.4/cgi-bin/fetchtest/images/url.html';
#########################################################
use strict;
use warnings;
use diagnostics;
use LWP::Simple;
use HTML::TokeParser;
use URI;
my $query_string = $ENV{"QUERY_STRING"};
my $return_query = "$return_URL?$query_string";

$return_query = "http://$return_query" unless $return_query =~ m{^http://};
my $url = URI->new($return_query);

# Get requested page and save it locally
my $html = get($return_query) || '';

open(OUTPUT_FILE, ">$file") || die "Unable to open $file: $!";
flock(OUTPUT_FILE,2) or die "cannot lock file: $!";
print OUTPUT_FILE $html;
close(OUTPUT_FILE);

# Parse the Web page to identify images
my %imagefiles;                                               
my $parser = HTML::TokeParser->new(\$html);
while (my $img_info = $parser->get_tag('img')) {              
  my $image_name = $img_info->[1]->{'src'};                  
  my $image_url = URI->new($image_name);
  my $image_file = $image_url->abs($url);                   
  $imagefiles{$image_file} = 1;                              
}
  

# Retrieve all the images and save them locally
  foreach my $this_image (keys %imagefiles) {                
  $this_image =~ m{.*/(.*)$};                                 
  my $local_image_name = $1;                                  
  $local_image_name =~ tr/A-Za-z0-9./_/c;                    
  my $local_image_path_name = "$images_path/$local_image_name"; 

  my $image_data = get($this_image) || '';                   
  
    # Get the images after checking if they don't already exist.
    my $local_img = "$images_path/$local_image_name"; 
    unless(-e $local_image_path_name)
     { 
     # Retrieve the page  
     my $image_data = get($this_image) || ''; 
     # Save copy of image locally
   open(OUTPUT_FILE, ">$local_image_path_name") || die "Unable to open $local_image_name: $!";
   binmode(OUTPUT_FILE);
   print OUTPUT_FILE $image_data;
   close(OUTPUT_FILE);
   #print "saved: $local_image_path_name<br>\n";
     }# end of if image exists.
     #print "local img is: $local_img<br>/n";
}

open FILE, "$file"
  or die "Can't open receipt page html file for display $!\n";
  flock(FILE,2) or die "cannot lock file: $!";
  # now make all image paths local and absolute.
  undef $/;    # enable "slurp" mode
  my $line = <FILE>;    # whole file now here
  $line =~ s/\n/ /g;
  
  #Strip out potentially nasty stuff.
  $line =~ s/<embed(.*)?<\/embed>/<!-- removed embed \/\/-->/sig;
  $line =~ s/<applet(.*)?<\/applet>/<!-- removed applet \/\/-->/sig;
                $line =~ s/<object(.*)?<\/object>/<!-- removed object \/\/-->/sig;
 
 $line =~ s/
       (<\s*(?:a|img|area)\b[^>]*(?:href|src)\s*=\s*
       ['"]?)
       ([^'"> ]+)
       (['"]?
       [^>]*>)
       /
       $1.sprintf("%s",URI->new($2)->abs($images_url)).$3
       /segix;
   print "Content-type: text/html\n\n";
  print $line;
close (FILE);

      # This empties the url file after the display is successful
      # Since the final read doesn't alter the actual file, its 
      # important to clear out the file after use so it can't
      # be accessed directly, instead of only via the script.
      open (FILE, ">$file");    
      flock(FILE,2) or die "cannot lock file: $!";
      close (FILE);
exit(0);