debian/control: Massive update of supported sites.

[youtubedl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 3b210710e3695ec3aa940b335d9868a281d7740a..8f9154c0e6864d04ef6c4e0f441ef4a68e6d30d2 100644 (file)
--- 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"""
 
 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'
     _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'


@@ -27,7 +32,7 @@ class FacebookIE(InfoExtractor):
         u'file': u'120708114770723.mp4',
         u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
         u'info_dict': {
         u'file': u'120708114770723.mp4',
         u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
         u'info_dict': {

-            u"duration": 279, 
+            u"duration": 279,

             u"title": u"PEOPLE ARE AWESOME 2013"
         }
     }
             u"title": u"PEOPLE ARE AWESOME 2013"
         }
     }


@@ -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)
         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)
 
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)