websites/infoq.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 'base64'
  21
  22 class Infoq < Website
  23
  24   VALID_INFOQ_URL_REGEX = /^(http:\/\/)?(www\.)?infoq\.com\/(.+)$/
  25
  26   def self.owns_url?(url)
  27     return url =~ VALID_INFOQ_URL_REGEX
  28   end
  29
  30
  31   def get_video_url()
  32     page_data = self.get_page_data(@url)
  33     video_url = self.parse_video_url(page_data)
  34     return video_url
  35   end
  36
  37
  38   protected;
  39
  40   # Get the FLV file URL from the HTML page for this movie.
  41   # It's encoded in base64 -- no big deal.
  42   def parse_video_url(page_data)
  43     # Get the base64 string. It's stored in a javascript
  44     # variable called "jsclassref". This regex should match
  45     # a javascript variable declaration preceded, separated,
  46     # and/or terminated by zero or more whitespace characters.
  47     base64_regex = /^\s*var\s+jsclassref=\'(.*)\';\s*$/
  48     matches = base64_regex.match(page_data)
  49
  50     if (matches.nil? || matches.length < 2)
  51       raise StandardError.new('There were no base64-encoded video URLs found on the page: ');
  52     end
  53
  54     return Base64.decode64(matches[1])
  55   end
  56
  57
  58   # Just make a normal HTTP "get" request.
  59   def get_page_data(url)
  60     uri = URI.parse(url)
  61
  62     response = Net::HTTP.start(uri.host, uri.port) do |http|
  63       http.get(uri.path)
  64     end
  65
  66     return response.body
  67   end
  68
  69 end