From 0e854c89d9fc6e26c7177b5ffd642dd136ce6892 Mon Sep 17 00:00:00 2001 From: Michael Orlitzky Date: Mon, 24 Jan 2011 19:45:58 -0500 Subject: [PATCH] Add support for xvideos.com. --- src/websites/xvideos.rb | 75 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 src/websites/xvideos.rb diff --git a/src/websites/xvideos.rb b/src/websites/xvideos.rb new file mode 100644 index 0000000..d0ad433 --- /dev/null +++ b/src/websites/xvideos.rb @@ -0,0 +1,75 @@ +# +# 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' +require 'cgi' + +class Xvideos < Website + + VALID_XVIDEOS_URL_REGEX = /^(http:\/\/)?(www.)?xvideos\.com\/video[0-9]+\/[a-z0-9_\-]+$/i + + def self.owns_url?(url) + return url =~ VALID_XVIDEOS_URL_REGEX + end + + + def get_video_url() + page_data = get_page_data(@url) + filepath = parse_video_url(page_data) + + return CGI::unescape(filepath) + end + + + def get_video_filename() + # Override the default since a nice human-readable name is right + # at the end of @url. + file_and_params = @url.split('/').pop() + + filename = file_and_params + # Unless it contains URL parameters. We don't want those. + if file_and_params.include?('?') + # There must be some parameters. Strip them off. + param_start_idx = file_and_params.index('?') + filename = file_and_params[0...(param_start_idx)] + end + + # Use the Website method to get the real extension of the file + # (the file /name/ we get back will be useless, but we can ignore + # it). + extension = super().split('.').pop() + filename += '.' + extension + + return filename + end + + + protected; + + def parse_video_url(page_data) + video_url_regex = /flv_url=([^&]+)&/i + matches = video_url_regex.match(page_data) + + if matches.nil? or (matches.length < 2) + raise StandardError.new("Couldn't parse the 'flv_url' parameter.") + else + return matches[1] + end + end + +end -- 2.44.2