Add a generic parser that will hopefully supplant some site-specific subclasses.

[dead/whatever-dl.git] / src / websites / generic.rb

diff --git a/src/websites/generic.rb b/src/websites/generic.rb
new file mode 100644 (file)
index 0000000..88fa515
--- /dev/null
+++ b/src/websites/generic.rb
@@ -0,0 +1,69 @@
+#
+# 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 Generic < Website
+
+  VALID_GENERIC_URL_REGEX = /^(http:\/\/)?(www\.)?(.+)$/
+
+  def self.owns_url?(url)
+    return url =~ VALID_GENERIC_URL_REGEX
+  end
+
+
+  def get_video_url()
+    page_data = self.get_page_data(@url)
+    video_url = self.parse_video_url(page_data)
+
+    return video_url
+  end
+
+
+  protected;
+
+  def base_url
+    # Return the website portion of the URL, e.g.
+    # http://www.example.com/
+    base_regex = /(http:\/\/.+?\/)/
+    matches = base_regex.match(@url)
+
+    # It's assumed that this will work, since @url is valid.
+    return matches[1]
+  end
+
+  def parse_video_url(page_data)
+    full_video_url_regex = /(http:\/\/.+?\.(flv|mp4))/i
+    matches = full_video_url_regex.match(page_data)
+
+    if not (matches.nil? || matches.length < 2)
+      return matches[1]
+    end
+
+    partial_video_url_regex = /([^\=\"\']+\.(flv|mp4))/i
+    matches = partial_video_url_regex.match(page_data)
+
+    if not (matches.nil? || matches.length < 2)
+      return base_url + matches[1]
+    end
+
+    return nil
+  end
+
+
+end