src/websites/redtube.rb

   1 #
   2 # Copyright Michael Orlitzky
   3 #
   4 # http://michael.orlitzky.com/
   5 #
   6 # This program is free software: you can redistribute it and/or modify
   7 # it under the terms of the GNU General Public License as published by
   8 # the Free Software Foundation, either version 3 of the License, or
   9 # (at your option) any later version.
  10 #
  11 # This program is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14 # GNU General Public License for more details.
  15 #
  16 # http://www.fsf.org/licensing/licenses/gpl.html
  17
  18 require 'src/website'
  19 require 'cgi'
  20
  21
  22 class Redtube < Website
  23
  24   VALID_REDTUBE_URL_REGEX = /^(http:\/\/)?(www\.)?redtube\.com\/(\d+)$/
  25
  26   def self.owns_url?(url)
  27     return url =~ VALID_REDTUBE_URL_REGEX
  28   end
  29
  30
  31   def get_video_url()
  32     page_data = self.get_page_data(@url)
  33     begin
  34       # We prefer to parse the HTML5 version because it can come in a
  35       # nicer container format.
  36       return parse_html5_src(page_data)
  37     rescue StandardError
  38       return self.parse_hashlink(page_data)
  39     end
  40   end
  41
  42
  43   protected;
  44
  45   def parse_video_id()
  46     return /\d+/.match(@url)[0]
  47   end
  48
  49
  50   def parse_html5_src(page_data)
  51     html5_src_regex = /\"<source src='([^']+?)'/
  52
  53     matches = html5_src_regex.match(page_data)
  54
  55     if matches.nil? or matches.length < 2
  56       raise StandardError.new("Could not parse the HTML5 source src.")
  57     else
  58       return matches[1]
  59     end
  60
  61   end
  62
  63
  64   def parse_hashlink(page_data)
  65     hashlink_regex = /hashlink=([^&]+)&/
  66
  67     matches = hashlink_regex.match(page_data)
  68
  69     if matches.nil? or matches.length < 2
  70       raise StandardError.new("Could not parse the 'hashlink' Flash variable.")
  71     end
  72
  73     # The hashlink variable /is/ the video URL, but it's encoded.
  74     return CGI::unescape(matches[1])
  75   end
  76
  77 end