lib/whatever-dl/websites/bliptv.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 require 'cgi'
  21
  22 class BliptvMediaFormat
  23   # This is just a convenience class for parsing two parameters out of
  24   # an RSS feed: 'url' and 'blip:role'.
  25   def initialize(line)
  26     @url = nil
  27     @role = nil
  28
  29     url_regex  = /url=\"([^\"]+)\"/
  30     role_regex = /blip:role=\"([^\"]+)\"/
  31     url_matches  = url_regex.match(line)
  32     role_matches = role_regex.match(line)
  33
  34     if not url_matches.nil? and (url_matches.length) > 1
  35       @url = url_matches[1]
  36     end
  37
  38     if not role_matches.nil? and (role_matches.length > 1)
  39       @role = role_matches[1]
  40     end
  41   end
  42
  43   def role
  44     return @role
  45   end
  46
  47   def url
  48     return @url
  49   end
  50 end
  51
  52
  53 class Bliptv < Website
  54
  55   VALID_BLIPTV_URL_REGEX = /^(http:\/\/)?blip\.tv\/.*?(\d+)$/
  56
  57   def self.owns_url?(url)
  58     return url =~ VALID_BLIPTV_URL_REGEX
  59   end
  60
  61
  62   def get_video_url()
  63     video_id = self.parse_video_id()
  64     rss_page_url = "http://blip.tv/rss/flash/#{video_id}"
  65     rss_data = get_page_data(rss_page_url)
  66     video_url = parse_video_url(rss_data)
  67
  68     return video_url
  69   end
  70
  71
  72   protected;
  73
  74   def parse_video_id()
  75     video_id_regex = /(\d+)$/
  76     matches = video_id_regex.match(@url)
  77
  78     if matches.nil? or (matches.length < 2)
  79       raise StandardError.new("Couldn't parse the video id from the URL.")
  80     else
  81       return matches[1]
  82     end
  83   end
  84
  85
  86   def choose_best_format(formats)
  87     # 'formats' is assumed to be an array of BliptvMediaFormat. We
  88     # return the best one (in terms of video quality).
  89     formats.each do |f|
  90       if f.url.nil? or f.role.nil?
  91         formats.delete(f)
  92         next
  93       end
  94
  95       return f if f.role == "Source"
  96     end
  97
  98     if formats.length == 0
  99       raise StandardError.new("No valid formats in the RSS feed.")
 100     else
 101       # Return whatever's left if we don't have a 'Source' video.
 102       return formats[0]
 103     end
 104   end
 105
 106   def parse_video_url(page_data)
 107     # All of the elements containing video URLs begin like this.
 108     media_regex = /^\s*<media:content/
 109
 110     formats = []
 111     # Create an array of BliptvMediaFormat from lines matching
 112     # media_regex.
 113     page_data.lines.each do |line|
 114       if (line =~ media_regex)
 115         bp = BliptvMediaFormat.new(line)
 116         formats << bp
 117       end
 118     end
 119
 120     # And return the URL from the best one.
 121     # choose_best_format will raise an error if need be.
 122     return choose_best_format(formats).url
 123   end
 124
 125 end