[generic] Add comment for unescaping webpage contents

[youtube-dl.git] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 7666cf2078177db0682aae81b01b4253362efdfd..300485c7f81b2ee6cba9f03823592d31b2fc6f9a 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -134,6 +134,17 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # funnyordie embed
+        {
+            'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
+            'md5': '7cf780be104d40fea7bae52eed4a470e',
+            'info_dict': {
+                'id': '18e820ec3f',
+                'ext': 'mp4',
+                'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
+                'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
+            }
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -280,6 +291,11 @@ class GenericIE(InfoExtractor):
         except compat_xml_parse_error:
             pass
 
+        # Sometimes embedded video player is hidden behind percent encoding
+        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+        # Unescaping the whole page allows to handle those cases in a generic way
+        webpage = compat_urllib_parse.unquote(webpage)
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
@@ -432,6 +448,14 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
 
+        # Look for funnyordie embed
+        matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
+        if matches:
+            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
+                     for eurl in matches]
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None: