lib/whatever-dl/websites/howcast.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 Howcast < Website
  22
  23   VALID_HOWCAST_URL_REGEX = /^(http:\/\/)?(www\.)?howcast\.com\/videos\/(\d+)-(.+)$/
  24
  25   def self.owns_url?(url)
  26     return url =~ VALID_HOWCAST_URL_REGEX
  27   end
  28
  29
  30   def get_video_url()
  31     video_id = parse_video_id()
  32     xml_url = "http://www.howcast.com/videos/#{video_id}.xml"
  33     xml_data = self.get_page_data(xml_url)
  34     filepath = parse_file_path_from_xml(xml_data)
  35
  36     return "http://www.howcast.com#{filepath}"
  37   end
  38
  39   protected;
  40
  41   def parse_video_id()
  42     # This regex just pulls out the video id
  43     id_regex = /\/(\d+)-/
  44     matches = id_regex.match(@url)
  45
  46     if matches.nil?
  47       raise StandardError.new('The URL is a valid Howcast URL, but does not match on the digit portion of the regex. Since the digit portion is a subset of the "valid" regex, this should never occur.')
  48     end
  49
  50     return matches[1]
  51   end
  52
  53
  54   def parse_file_path_from_xml(data)
  55     file_path_regex = /<filename>(.*?)<\/filename>/
  56     matches = file_path_regex.match(data)
  57
  58     if matches.nil?
  59       raise StandardError.new("Couldn't parse the <filename> tag from the XML file.")
  60     end
  61
  62     return matches[1]
  63   end
  64
  65 end