youtube-dl

commit 1037d53988387db920748861e6af644547be0f20
parent c3ab8f866c37c8773b74fa5d0a57235722fe2c61
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Sun, 23 Jun 2013 13:26:49 +0200

GenericIE: look for Open Graph info

Only if there is a direct link to the file, don't try if it points to a Flash player

Diffstat:
M
youtube_dl/InfoExtractors.py
 | 
7
+++++++

1 file changed, 7 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
@@ -1410,6 +1410,13 @@ class GenericIE(InfoExtractor):
             # Try to find twitter cards info
             mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
         if mobj is None:
+            # We look for Open Graph info:
+            # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
+            m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+            # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
+            if m_video_type is not None:
+                mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
         # It's possible that one of the regexes