src/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
  21 class Bliptv < Website
  22
  23   VALID_BLIPTV_URL_REGEX = /^(http:\/\/)?([[:alnum:]\-]+\.)?blip\.tv\/file\/(\d+)(.*)?$/
  24   VALID_BLIPTV_REDIR_URL_REGEX = /^(http:\/\/)?([[:alnum:]\-]+\.)?blip\.tv\/play\/[[:alnum:]]+$/
  25
  26   def self.owns_url?(url)
  27     return (url =~ VALID_BLIPTV_URL_REGEX ||
  28             url =~ VALID_BLIPTV_REDIR_URL_REGEX)
  29   end
  30
  31
  32   def get_video_url()
  33     page_data = ''
  34
  35     if (@url =~ VALID_BLIPTV_URL_REGEX)
  36       page_data = self.get_page_data(@url)
  37     else
  38       # It's a redirect. Figure out the RSS page URL from the redirect.
  39       redir_url = get_redirect_url
  40       rss_page_url = parse_rss_url(redir_url)
  41       rss_data = get_page_data(rss_page_url)
  42
  43       # The "real" page URL is embedded in the RSS feed. Once we get the
  44       # real URL, we can proceed as if we were given that URL in the first
  45       # place.
  46       real_page_url = parse_page_url(rss_data)
  47       page_data = self.get_page_data(real_page_url)
  48     end
  49
  50     filepath = parse_video_url(page_data)
  51
  52     return filepath
  53   end
  54
  55
  56   protected;
  57
  58   def parse_page_url(data)
  59     # A simplified VALID_BLIPTV_URL_REGEX.
  60     page_url_regex = /http:\/\/blip\.tv\/file\/\d+/
  61     matches = page_url_regex.match(data)
  62
  63     if matches.nil?
  64       raise StandardError.new("Couldn't parse the real page URL from the RSS page.")
  65     end
  66
  67     return matches[0]
  68   end
  69
  70   def parse_rss_url(url)
  71     rss_id_regex = /\/flash\/(\d+)/
  72     matches = rss_id_regex.match(url)
  73
  74     if matches.nil? or (matches.length < 2)
  75       raise StandardError.new("Couldn't parse the video ID from the redirect URL: #{url}")
  76     end
  77
  78     return "http://blip.tv/rss/flash/#{matches[1]}"
  79   end
  80
  81   def get_redirect_url
  82     uri = URI.parse(@url)
  83
  84     response = Net::HTTP.start(uri.host, uri.port) do |http|
  85       http.get(uri.request_uri, {})
  86     end
  87
  88     return response['location']
  89   end
  90
  91
  92   def parse_video_url(page_data)
  93     # First, try to find the MOV video. The source videos are usually
  94     # encoded with MOV.
  95     video_url_regex = /"Quicktime \(\.mov\)", "attribute" : "(.*?\.mov)/i
  96     matches = video_url_regex.match(page_data)
  97
  98     if not matches.nil? and (matches.length > 1)
  99       return matches[1]
 100     end
 101
 102     # I've seen some free software videos encoded as OGG/Vorbis, too.
 103     video_url_regex = /"Ogg Theora\/Vorbis \(\.og[gv]\)", "attribute" : "(.*?\.og[gv])/i
 104     matches = video_url_regex.match(page_data)
 105
 106     if not matches.nil? and (matches.length > 1)
 107       return matches[1]
 108     end
 109
 110     # If that didn't work, try the WMV format, which is occasionally
 111     # used for the source as well.
 112     video_url_regex = /"Windows Media \(\.wmv\)", "attribute" : "(.*?\.wmv)/i
 113     matches = video_url_regex.match(page_data)
 114
 115     if not matches.nil? and (matches.length > 1)
 116       return matches[1]
 117     end
 118
 119
 120     # If neither of the source formats are present, just grab the
 121     # video URL from the Flash variable and be done with it.
 122     video_url_regex = /setPrimaryMediaUrl\("(.*?\.(flv|mov|wmv|mp4|og[gv]))/i
 123     matches = video_url_regex.match(page_data)
 124
 125     if matches.nil? or (matches.length < 2)
 126       raise StandardError.new("Couldn't parse any of the video format URLs.")
 127     end
 128
 129     return matches[1]
 130   end
 131
 132 end