# # Copyright Michael Orlitzky # # http://michael.orlitzky.com/ # # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # http://www.fsf.org/licensing/licenses/gpl.html # require 'src/website' class Howcast < Website VALID_HOWCAST_URL_REGEX = /^(http:\/\/)?(www\.)?howcast\.com\/videos\/(\d+)-(.+)$/ def self.owns_url?(url) return url =~ VALID_HOWCAST_URL_REGEX end def get_video_url() video_id = parse_video_id() xml_url = "http://www.howcast.com/videos/#{video_id}.xml" xml_data = self.get_page_data(xml_url) filepath = parse_file_path_from_xml(xml_data) return "http://www.howcast.com#{filepath}" end protected; def parse_video_id() # This regex just pulls out the video id id_regex = /\/(\d+)-/ matches = id_regex.match(@url) if matches.nil? 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.') end return matches[1] end def parse_file_path_from_xml(data) file_path_regex = /(.*?)<\/filename>/ matches = file_path_regex.match(data) if matches.nil? raise StandardError.new("Couldn't parse the tag from the XML file.") end return matches[1] end end