websites/veoh.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 # Needed to download the page, which is in turn
  22 # needed because it contains the video (redirect) URL.
  23 require 'net/http'
  24 require 'uri'
  25
  26
  27 class Veoh < Website
  28
  29   VALID_VEOH_URL_REGEX = /^(http:\/\/)?(www\.)?veoh\.com\/videos\/([[:alnum:]]+)$/
  30
  31   def self.owns_url?(url)
  32     return url =~ VALID_VEOH_URL_REGEX
  33   end
  34
  35
  36   def get_video_url()
  37     # First, figure out the video id from the URL.
  38     # Then, use the video id to construct the video details URL.
  39     # Get the video details page, and parse the redirect
  40     # URL from it. Now, I guess we *could* retrieve the video
  41     # id from the redirect, but for now we're going to rely
  42     # on our HTTP library to follow the redirect for us and
  43     # save us a step.
  44     video_id = self.parse_video_id()
  45     details_url = "http://www.veoh.com/rest/video/#{video_id}/details"
  46     details_data = get_page_data(details_url)
  47     redirect_url = parse_redirect_url(details_data)
  48
  49     # We trust our HTTP library to do the right thing here.
  50     return redirect_url
  51   end
  52
  53
  54   def get_video_filename()
  55     return (self.parse_video_id() + '.flv')
  56   end
  57
  58   protected;
  59
  60   def parse_video_id()
  61     video_id_regex = /[[:alnum:]]+$/
  62     matches = video_id_regex.match(@url)
  63     video_id = matches[0] if not matches.nil?
  64
  65     return video_id
  66   end
  67
  68
  69   # The main video page has the "video" URL buried
  70   # in some javascript parameters.
  71   def parse_redirect_url(page_data)
  72     redirect_url_regex = /fullPreviewHashPath=\"(.*?)\"/
  73     matches = redirect_url_regex.match(page_data)
  74     redirect_url = matches[1] if not (matches.nil? || matches.length < 1)
  75
  76     return redirect_url
  77   end
  78
  79
  80   def get_page_data(url)
  81     uri = URI.parse(url)
  82
  83     response = Net::HTTP.start(uri.host, uri.port) do |http|
  84       http.get(uri.path)
  85     end
  86
  87     return response.body
  88   end
  89
  90 end