#!/usr/bin/perl

# baygrab.pl v0.3
# Josh Jackson <pturing@firehead.org>


package Baygrab; 

=head1 NAME


   baygrab.pl - A script for downloading images form bayimg.com


=head1 SYNOPSIS

   Baygrab is a script to download all images for a given tag or album from bayimg.com
  It will identify images from the same archive and collect them into a subfolder.

=head1 LICENSE

Copyright (c) 2007 Josh Jackson <pturing@firehead.org>

Permission is hereby granted, free of charge, to any person
obtaining a copy of this software and associated documentation
files (the "Software"), to deal in the Software without
restriction, including without limitation the rights to use,
copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following
conditions:

The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.

=head1 CHANGELOG

 2007.07.21 - 0.3
   code clean up
   add usage information
   download by url
   fix downloading tags and albums with only 1 page of results
   add initial POD info

 2007.06.26 - 0.2
   download either tags or albums
   add cookie to allow downloading 'offensive' images

 2007.06.22 - 0.1
   downloading based on tags only
   sort into album subdirectories
 
=cut


use strict;
use LWP::UserAgent;
use HTTP::Cookies;


my($mode) = 'tag';
my($album, $tag, $filecounter);


sub usage {
 print "usage: \n";
 print "       $0 -album ALBUM\n";
 print "       $0 -url URL_TO_ALBUM_OR_TAG\n";
 print "       $0 [-tag] TAG\n";
 exit;
}


sub init_agent {
  my($ua) = new LWP::UserAgent;
  $ua->agent("Mozilla/4.0 (compatible; IAmTheWalrus 5.5; OpenBDSM)");
  return $ua; 
}


sub request_cookies {
  my $request = shift;
  my $cookie_jar = HTTP::Cookies->new;
  my @rest = ("/", "bayimg.com", undef, 0, 0, 60*60, 0);
  $cookie_jar->set_cookie(undef, 'show_offensive', 'true', @rest);
  $cookie_jar->add_cookie_header($request);
  return $request;
}


sub get_to_file {
  my $url = shift;
  my $file_name = shift;
  my $ua = init_agent();
  my $request = request_cookies(HTTP::Request->new(GET => $url));
  my $res = $ua->request($request);
  open(FH, ">$file_name");
  print FH $res->content;;
  close(FH);
}


sub get_to_string {
  my $url = shift;
  my $ua  = init_agent();
  my $request = request_cookies(HTTP::Request->new(GET => $url));
  my $res = $ua->request($request);
  return $res->as_string;
}
  

sub post_to_string {
  my $posturl = shift;
  my $postvars = shift;
  my $ua = init_agent();
  my $req = request_cookies(HTTP::Request->new(POST => $posturl));
  $req->content_type('application/x-www-form-urlencoded');
  $req->content($postvars);
  my $res = $ua->request($req);
  return $res->as_string;
}


sub fetchtag_page {
  my $tag = shift;
  my $pagenum = shift;
  if ($pagenum == '') { $pagenum = 1; }
  return post_to_string('http://bayimg.com/ajax_tags.php', "page=$pagenum&tag=$tag");
}


sub fetchalbum_page {
  my $album = shift;
  my $pagenum = shift;
  if ($pagenum == '') { $pagenum = 1; }
  return post_to_string('http://bayimg.com/ajax_album.php', "page=$pagenum&id=$album");
}


sub thumbpage_to_imagepages {
  my $x = shift;
  my @url_list = ();
  my @paths = ($x =~ /href\=\"\/.........\"/g);
  foreach(@paths) {
    push(@url_list, substr($_, 7, 9));
  }
  return @url_list;
}


sub before_first {
  my @parts = split(/$_[0]/, $_[1]);
  return $parts[0];
}


sub after_first {
  my @parts = split(/$_[0]/, $_[1]);
  return $parts[1];
}


sub imagepage_imageurl {
  my $x = shift;
  $x =~ /src\=\"(.*)\"\ id\=\"mainImage\"/;
  return $1;
}


sub imagepage_namefromtitle {
  my $x = shift;
  $x =~ /\<title\>bayimg\ -\ image\:\ (.*)\ -\ free\ uncensored\ image\ hosting\<\/title\>/;
  return $1;
}


sub imagepage_namefrominfo {
  my($x) = $_[0];
  $x = after_first('\<div\ id\=\"extra\"\>', $x);
  $x = before_first('\<h2\>Popular\ tags\ on\ the\ site\<\/h2\>', $x);
  $x =~ /\<p\>Image\:\ (.*)\<br\>/;
  #print "info line found as $1\n";
  return $1;
}


sub imagepage_imagename {
  my $x = shift;
  my $id = shift;
  my $fromtitle = imagepage_namefromtitle($x);
  my $frominfo  = imagepage_namefrominfo($x);
  $filecounter += 1;
  my $c = sprintf("%04d", $filecounter);
 
  if (length($fromtitle) == 0) {
    $x = (length($frominfo) == 0) ? $id : $frominfo;
  } else { $x = $fromtitle; }

  if (length($frominfo) != 0 and length($fromtitle) != 0 and $frominfo != $fromtitle) {
    print "title ($fromtitle) differs from info ($frominfo)\n";
  }

  if ($x =~ /\.(rar|zip)$/) {
    mkdir($x);
    return "$x/$c-$id";
  }
  else {
    return "$c-$x";
  }
}


sub saveimage {
  my $page = get_to_string("http://bayimg.com/$_[0]");
  my $image_name = imagepage_imagename($page, $_[0]);
  print "Saving $image_name\n";
  get_to_file(imagepage_imageurl($page), $image_name);
}


sub last_page {
  my $x = shift;
  $x =~ /.*parameters:\ \'page\=([0-9]+)\&.*parameters:\ \'page\=([0-9]+)\&/;
  print "last page is $1\n";
  return ($1 > 1) ? $1 : 1;
}


sub fetchpage_bymode {
  my $x = shift;
  print "will fetch page $x in $mode mode\n";
  my($pagehtml) = '';
  if ($mode =~ /tag/) {
    $pagehtml = fetchtag_page($tag, $x);
  }
  elsif ($mode =~ /album/) {
     $pagehtml = fetchalbum_page($album, $x);
  }
  else {
    print 'error: mode not set\n';
  }
  return $pagehtml;
}



sub bayimg_fetchall {
  my @image_pages;
  my $page = 1;
  my $pagehtml = fetchpage_bymode($page);
  my $lastpage = last_page($pagehtml);
  for ($page = 1; $page <= $lastpage; $page++) {
    print "Page $page\n";
    my($pagehtml) = fetchpage_bymode($page);
    @image_pages = thumbpage_to_imagepages($pagehtml);
    my $count = @image_pages;
    print "$count images to grab\n";
    foreach(@image_pages) {
      saveimage($_);
    }
  }
}



if ($#ARGV == -1 or $ARGV[0] =~ /-help/) {
  usage;
}
elsif ($ARGV[0] =~ /-album/) {
  $mode = 'album';
  $album = $ARGV[1];
}
elsif ($ARGV[0] =~ /-tag/) {
  $tag = $ARGV[1];
}
elsif ($ARGV[0] =~ /-url/) {
  if ($ARGV[1] =~ /bayimg.com\/album\/(.*)/)  { 
    $mode = 'album';
    $album = $1;
  }  
  elsif ($ARGV[1] =~ /bayimg.com\/tag\/(.*)/) { 
    $tag = $1;
  }
  else {
    usage;
  }
}
else {
  $tag = $ARGV[0];
}

if ($mode =~ 'album') {
  print "grabbing album $album\n";
}
else {
  print "grabbing tag $tag\n";
}



bayimg_fetchall();