#!/usr/bin/perl
# tom365crawl2.pl
# http://www.cs.utk.edu/cs594ipm/perl/crawltut.html
# http://perldoc.perl.org/Encode.html
# http://juerd.nl/site.plp/perluniadvice
# http://www.perlmonks.org/?node_id=620068

use warnings;
use strict;

use File::stat;
use Tie::File;

use LWP::Simple;
use LWP::UserAgent;
use HTTP::Request;
use HTTP::Response;
use HTML::LinkExtor; # Allows you to extract the links off of an HTML page.
#use File::Slurp;

use Encode;

my $site1 = "http://www.tom365.com/"; # Full url like http://www.tom365.com/movie_2004/html/????.html
my $delim1a = "\<div class=\"movie\"\>\<img src=\"";
my $delim1b = "\" class=\"mp\" \/\>";
my $folder1 = "movie_2004/html/";
my $url1;
my $start1 = 1000;
my $end1 = 1000;
my $contents1;
my $image1;

my $browser1 = LWP::UserAgent->new();
$browser1->timeout(10);
my $request1;
my $response1;

my $count;
for ($count=$start1; $count<=$end1; $count++) {
  $url1 = $site1 . $folder1 . $count . ".html";
  printf "Downloading %s\n", $url1;

  # Method 1
  #$contents1 = get($url1);

  # Method 2
  $request1 = HTTP::Request->new(GET => $url1);
  $response1 = $browser1->request($request1);
  if ($response1->is_error()) {
    printf "%s\n", $response1->status_line;
  }
  $contents1 = $response1->decoded_content();

  #open(NEWFILE1, "> Debug.txt");
  #(print NEWFILE1 $contents1)    or die "Can't write to Debug.txt: $!";
  #close(NEWFILE1);

  #print $contents1;

  if ($contents1 =~ /\<div class=\"movie\"\>\<img src=\"(.*)\" class=\"mp\" \/\>/m) {
    $image1 = "$1";
    printf "Downloading %s\n", $image1;
    `wget -q -O $count.jpg $image1`;

    #if ($image1 =~ /\/([^\/]*)$/m) {
    #  printf "Renaming %s to $count.jpg\n", $1;
    #} else {
    #  printf "Could not rename %s to $count.jpg\n", $image1;
    #}
  } else {
    #open(NEWFILE1, "> $count.txt");
    #(print NEWFILE1 "Download failed.\n")    or die "Can't write to $image1: $!";
    #close(NEWFILE1);
  }
}