src/website.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 # Needed for the default implementation of get_page_data.
  20 require 'net/http'
  21
  22 # Necessary in a lot of subclasses; plus, we need it
  23 # to parse the server name out of our URL.
  24 require 'uri'
  25
  26 # Needed to download.. things.
  27 require 'net/http'
  28
  29 # This class keeps track of all its subclasses
  30 # We use this to loop through every "website" in an
  31 # attempt to determine to which site a URL belongs.
  32 class Website
  33
  34   protected;
  35
  36   @url = nil
  37
  38
  39   def self.inherited(subclass)
  40     if superclass.respond_to? :inherited
  41       superclass.inherited(subclass)
  42     end
  43
  44     # Every time we're subclassed, add the new
  45     # subclass to our list of subclasses.
  46     @subclasses ||= []
  47     @subclasses << subclass
  48   end
  49
  50
  51   def server
  52     # Get the HTTP server portion of our URI
  53     uri = URI.parse(@url)
  54     return uri.host
  55   end
  56
  57
  58
  59   def get_page_data(url)
  60     # A naive implementation that just grabs the
  61     # data from a page.
  62     uri = URI.parse(url)
  63
  64     response = Net::HTTP.start(uri.host, uri.port) do |http|
  65       http.get(uri.request_uri)
  66     end
  67
  68     return response.body
  69   end
  70
  71
  72
  73   public;
  74
  75   def initialize(url)
  76     @url = url
  77   end
  78
  79
  80   def self.create(url)
  81     # Factory method returning an instance of
  82     # the appropriate subclass.
  83
  84     # Check the URL against each website's class.
  85     # The class will know whether or not the URL
  86     # "belongs" to its website.
  87     @subclasses.each do |w|
  88       if w.owns_url?(url)
  89         return w.new(url)
  90       end
  91     end
  92
  93     # If nothing matched, we don't return an instance
  94     # of anything.
  95     return nil
  96   end
  97
  98
  99   # Abstract definition. Each subclass of Website
 100   # should support it on its own.
 101   def self.owns_url?(url)
 102     raise NotImplementedError
 103   end
 104
 105
 106   # Same here. Abstract.
 107   def get_video_url()
 108     raise NotImplementedError
 109   end
 110
 111
 112   # The website class should be responsible for determining the
 113   # video's filename. By default, we can take the last component
 114   # of the video URL, but in some cases, subclasses will want
 115   # to override this behavior.
 116   def get_video_filename()
 117     # Use whatever comes after the final front slash.
 118     file_and_params = get_video_url().split('/').pop()
 119
 120     # Unless it contains URL parameters. We don't want those.
 121     return file_and_params unless file_and_params.include?('?')
 122
 123     # There must be some parameters. Strip them off.
 124     param_start_idx = file_and_params.index('?')
 125     return file_and_params[0...(param_start_idx)]
 126   end
 127
 128 end