X-Git-Url: http://gitweb.michael.orlitzky.com/?a=blobdiff_plain;f=src%2Fwebsite.rb;h=2f03e6cb4c383fa63093553a60317925bee51183;hb=11aa7c3e702f4ea466152b706f60e154e60e188e;hp=5e064799cd3ede567d732e1f3e2f5c8f72aaf51a;hpb=174589cd65cf32d4a54b9298953228f6094c7128;p=dead%2Fwhatever-dl.git

diff --git a/src/website.rb b/src/website.rb
index 5e06479..2f03e6c 100644
--- a/src/website.rb
+++ b/src/website.rb
@@ -16,10 +16,16 @@
 # http://www.fsf.org/licensing/licenses/gpl.html
 #
 
+# Needed for the default implementation of get_page_data.
+require 'net/http'
+
 # Necessary in a lot of subclasses; plus, we need it
 # to parse the server name out of our URL.
 require 'uri'
 
+# Needed to download.. things.
+require 'net/http'
+
 # This class keeps track of all its subclasses
 # We use this to loop through every "website" in an
 # attempt to determine to which site a URL belongs.
@@ -50,13 +56,13 @@ class Website
 
 
   
-  def get_page_data(url)
+  def get_page_data(url, headers = {})
     # A naive implementation that just grabs the
     # data from a page.
     uri = URI.parse(url)
 
     response = Net::HTTP.start(uri.host, uri.port) do |http|
-      http.get(uri.request_uri)
+      http.get(uri.request_uri, headers)
     end
 
     return response.body
@@ -108,8 +114,15 @@ class Website
   # of the video URL, but in some cases, subclasses will want
   # to override this behavior.
   def get_video_filename()
-    # Use whatever comes after the final front slash.    
-    return get_video_url().split('/').pop()
+    # Use whatever comes after the final front slash.
+    file_and_params = get_video_url().split('/').pop()
+
+    # Unless it contains URL parameters. We don't want those.
+    return file_and_params unless file_and_params.include?('?')
+    
+    # There must be some parameters. Strip them off.
+    param_start_idx = file_and_params.index('?')
+    return file_and_params[0...(param_start_idx)]
   end
   
 end