youtube-dl

commit 9834872bf63b4e03b66c5e3b8f306556e735d8c5
parent 94a23d2a1ed94af8bb80898194f03c38a5dcdb1d
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Tue, 21 Jan 2014 18:10:14 +0100

[facebook] Add support for embeds

Example URL: http://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html

Diffstat:
M
youtube_dl/extractor/facebook.py
 | 
9
+++++++--
M
youtube_dl/extractor/generic.py
 | 
6
++++++

2 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
@@ -17,7 +17,12 @@ from ..utils import (
 class FacebookIE(InfoExtractor):
     """Information Extractor for Facebook"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+    _VALID_URL = r'''(?x)
+        (?:https?://)?(?:\w+\.)?facebook\.com/
+        (?:[^#?]*\#!/)?
+        (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
+        (?:v|video_id)=(?P<id>[0-9]+)
+        (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
@@ -90,7 +95,7 @@ class FacebookIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group('ID')
+        video_id = mobj.group('id')
 
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -319,6 +319,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Novamov')
 
+        # Look for embedded Facebook player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https://www.facebook.com/video/embed.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Facebook')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None: