src/websites/yikers.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
  22 class Yikers < Website
  23
  24   VALID_YIKERS_URL_REGEX = /^(http:\/\/)?(www\.)?yikers\.com\/([[:alnum:]_]+)\.html$/
  25
  26   def self.owns_url?(url)
  27     return url =~ VALID_YIKERS_URL_REGEX
  28   end
  29
  30
  31   def get_video_url()
  32     # First we download the page. Each page contains a flash parameter
  33     # called 'xml' which contains the relative path to the video's XML file.
  34     # We download their XML file (passing it the video id as a side effect),
  35     # and that contains the URL of the video file we want.
  36     page_data = get_page_data(@url)
  37     xml_path = self.parse_xml_path(page_data)
  38
  39     # The XML path parameter doesn't contain a host name.
  40     xml_url = "http://#{self.server}#{xml_path}"
  41     xml_data = get_page_data(xml_url)
  42
  43     video_url = parse_video_url(xml_data)
  44
  45     return video_url
  46   end
  47
  48
  49   def get_video_filename()
  50     # Default to whatever comes after the final frontslash
  51     # in the main URL.
  52     filename = @url.split('/').pop()
  53
  54     # These page URLs are actually descriptive, so we can use
  55     # the file name of the HTML page as our video file name.
  56     filename_regex = /\/([[:alnum:]_]+)\.html$/
  57     matches = filename_regex.match(@url)
  58
  59     # Overwrite the default if our regex worked.
  60     filename = matches[1] if not (matches.nil? || matches.length < 1)
  61
  62     return (filename + '.flv')
  63   end
  64
  65   protected;
  66
  67   def parse_video_url(data)
  68     video_url_regex = /http:\/\/(cdn\.)?yikers\.com\/([[:alnum:]_\/]+)\.flv/
  69     matches = video_url_regex.match(data)
  70     video_url = matches[0] if not matches.nil?
  71
  72     return video_url
  73   end
  74
  75
  76   def parse_xml_path(data)
  77     xml_path_regex = /addVariable\(\'xml\', \'(.*?)\'\)/
  78     matches = xml_path_regex.match(data)
  79     xml_path = matches[1] if not (matches.nil? || matches.length < 2)
  80
  81     return xml_path
  82   end
  83
  84 end