src/websites/generic.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
  19 require 'src/website'
  20
  21 class Generic < Website
  22
  23   VALID_GENERIC_URL_REGEX = /^(http:\/\/)?(www\.)?(.+)$/
  24
  25   def self.owns_url?(url)
  26     return url =~ VALID_GENERIC_URL_REGEX
  27   end
  28
  29
  30   def get_video_url()
  31     page_data = self.get_page_data(@url)
  32     video_url = self.parse_video_url(page_data)
  33
  34     return video_url
  35   end
  36
  37
  38   protected;
  39
  40   def base_url
  41     # Return the website portion of the URL, e.g.
  42     # http://www.example.com/
  43     base_regex = /(http:\/\/.+?\/)/
  44     matches = base_regex.match(@url)
  45
  46     # It's assumed that this will work, since @url is valid.
  47     return matches[1]
  48   end
  49
  50   def parse_video_url(page_data)
  51     full_video_url_regex = /(http:\/\/.+?\.(flv|mp4))/i
  52     matches = full_video_url_regex.match(page_data)
  53
  54     if not (matches.nil? || matches.length < 2)
  55       return matches[1]
  56     end
  57
  58     partial_video_url_regex = /([^\=\"\']+\.(flv|mp4))/i
  59     matches = partial_video_url_regex.match(page_data)
  60
  61     if not (matches.nil? || matches.length < 2)
  62       return base_url + matches[1]
  63     end
  64
  65     return nil
  66   end
  67
  68
  69 end