// download all .torrent links on the btjunkie frontpage
//
// more fun with mechanize @
// http://tramchase.com/scrape-myspace-youtube-torrents-for-fun-and-profit

agent = WWW::Mechanize.new
agent.get("http://btjunkie.org/")
links = agent.page.search('.tor_details tr a')
hrefs = links.map { |m| m['href'] }.select { |u| u =~ /\.torrent$/ } # just links ending in .torrent
FileUtils.mkdir_p('btjunkie-torrents') # keep it neat
hrefs.each { |torrent|
  filename = "btjunkie-torrents/#{torrent[0].split('/')[-2]}"
  puts "Saving #{torrent} as #{filename}"
  agent.get(torrent).save_as(filename)
}

// fetch all img's from a myspace profile's .friendSpace div
// more @ http://tramchase.com/scrape-myspace-youtube-torrents-for-fun-and-profit

agent = WWW::Mechanize.new
agent.get("http://myspace.com/graffitiresearchlab")
links = agent.page.search('.friendSpace img') # found w/ firebug
FileUtils.mkdir_p 'myspace-images' # make the images dir
links.each_with_index { |link, index| 
  url = link['src']
  puts "Saving thumbnail #{url}"
  agent.get(url).save_as("myspace-images/top_friend#{index}_#{File.basename url}")
}

// fun with mechanize
// more @ http://tramchase.com/scrape-myspace-youtube-torrents-for-fun-and-profit

agent = WWW::Mechanize.new
url = "http://gdata.youtube.com/feeds/api/standardfeeds/most_viewed" # all time
page = agent.get(url)
# parse again w/ Hpcricot for some XML convenience
doc = Hpricot.parse(page.body)
# pp (doc/:entry) # like "search"; cool division overload
images = (doc/'media:thumbnail') # use strings instead of symbols for namespaces
FileUtils.mkdir_p 'youtube-images' # make the images dir
urls = images.map { |i| i[:url] }
urls.each_with_index do |file,index|
  puts "Saving image #{file}"
  agent.get(file).save_as("youtube-images/vid#{index}_#{File.basename file}")
end

function get_remote_file_size($url, $readable = true){
   $parsed = parse_url($url);
   $host = $parsed["host"];
   $fp = @fsockopen($host, 80, $errno, $errstr, 20);
   if(!$fp) return false;
   else {
       @fputs($fp, "HEAD $url HTTP/1.1\r\n");
       @fputs($fp, "HOST: $host\r\n");
       @fputs($fp, "Connection: close\r\n\r\n");
       $headers = "";
       while(!@feof($fp))$headers .= @fgets ($fp, 128);
   }
   @fclose ($fp);
   $return = false;
   $arr_headers = explode("\n", $headers);
   foreach($arr_headers as $header) {
                        // follow redirect
                        $s = 'Location: ';
                        if(substr(strtolower ($header), 0, strlen($s)) == strtolower($s)) {
                                $url = trim(substr($header, strlen($s)));
                                return get_remote_file_size($url, $readable);
                        }
                        
                        // parse for content length
       $s = "Content-Length: ";
       if(substr(strtolower ($header), 0, strlen($s)) == strtolower($s)) {
           $return = trim(substr($header, strlen($s)));
           break;
       }
   }
   if($return && $readable) {
                        $size = round($return / 1024, 2);
                        $sz = "KB"; // Size In KB
                        if ($size > 1024) {
                                $size = round($size / 1024, 2);
                                $sz = "MB"; // Size in MB
                        }
                        $return = "$size $sz";
   }
   return $return;
}