src/websites/vimeo.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 video XML file, which is in turn
  22 # needed because it contains the junk we need to construct
  23 # the video URL.
  24 require 'net/http'
  25 require 'uri'
  26
  27
  28 class Vimeo < Website
  29
  30   VALID_VIMEO_URL_REGEX = /^(http:\/\/)?(www\.)?vimeo\.com\/(moogaloop\.swf\?clip_id=)?(\d+)/
  31
  32   def self.owns_url?(url)
  33     return url =~ VALID_VIMEO_URL_REGEX
  34   end
  35
  36
  37   def get_video_url()
  38     # First, figure out the video id from the URL.
  39     # Then, use the video id to construct the video details URL.
  40     # Get the video details page, and parse the resulting XML for
  41     # the junk we need to construct the video URL. Note that the file
  42     # URL given in the XML is *not* valid.
  43     video_id = self.parse_video_id()
  44     details_url = "http://www.vimeo.com/moogaloop/load/clip:#{video_id}/local"
  45     details_data = get_page_data(details_url)
  46
  47
  48     request_signature = parse_request_signature(details_data)
  49     request_signature_expires = parse_request_signature_expires(details_data)
  50     quality = parse_quality(details_data)
  51
  52     # Being slightly explicit about what we're doing here...
  53     video_url = "http://www.vimeo.com/moogaloop/play/clip:#{video_id}/#{request_signature}/#{request_signature_expires}/?q=#{quality}"
  54
  55     return video_url
  56   end
  57
  58
  59   def get_video_filename()
  60     # The default behavior is no good here, use the video
  61     # id with an extension tacked onto it.
  62     return (self.parse_video_id() + '.flv')
  63   end
  64
  65
  66   protected;
  67
  68   def parse_video_id()
  69     video_id = nil
  70
  71     # First, try to get the video id from the end of the URL.
  72     video_id_regex = /\/(\d+)$/
  73     matches = video_id_regex.match(@url)
  74
  75     if matches.nil?
  76       # If that didn't work, the URL must be of the clip_id= form.
  77       video_id_regex = /clip_id\=(\d+)/
  78       matches = video_id_regex.match(@url)
  79       video_id = matches[1] if not (matches.nil? || matches.length < 1)
  80     else
  81       video_id = matches[1] if not (matches.nil? || matches.length < 1)
  82     end
  83
  84     return video_id
  85   end
  86
  87
  88   def parse_request_signature(page_data)
  89     # It's XML.
  90     rs_regex = /<request_signature>(.*?)<\/request_signature>/
  91     matches = rs_regex.match(page_data)
  92     request_signature = matches[1] if not (matches.nil? || matches.length < 1)
  93
  94     return request_signature
  95   end
  96
  97
  98   def parse_request_signature_expires(page_data)
  99     rse_regex = /<request_signature_expires>(.*?)<\/request_signature_expires>/
 100     matches = rse_regex.match(page_data)
 101     request_signature_expires = matches[1] if not (matches.nil? || matches.length < 1)
 102
 103     return request_signature_expires
 104   end
 105
 106
 107   def parse_quality(page_data)
 108     quality_regex = /<isHD>([01])<\isHD>/
 109     matches = quality_regex.match(page_data)
 110     is_hd = matches[1] if not (matches.nil? || matches.length < 1)
 111
 112     if is_hd == '1' then
 113        # High-definition
 114       return "hd"
 115     else
 116       # Standard-definition
 117       return "sd"
 118     end
 119   end
 120
 121
 122   def get_page_data(url)
 123     uri = URI.parse(url)
 124
 125     response = Net::HTTP.start(uri.host, uri.port) do |http|
 126       http.get(uri.path)
 127     end
 128
 129     return response.body
 130   end
 131
 132 end