[facebook] Add support for embeds
authorPhilipp Hagemeister <phihag@phihag.de>
Tue, 21 Jan 2014 17:10:14 +0000 (18:10 +0100)
committerPhilipp Hagemeister <phihag@phihag.de>
Tue, 21 Jan 2014 17:10:17 +0000 (18:10 +0100)
Example URL: http://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html

youtube_dl/extractor/facebook.py
youtube_dl/extractor/generic.py

index 4556079c8ad5edce7a6a3efe29989299d719ed28..8f9154c0e6864d04ef6c4e0f441ef4a68e6d30d2 100644 (file)
@@ -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)
index 3e96cb15fb79e2be42a2417535689b8daadd7cc8..91536075d018aaa3b6d3777ec899dacd5bc4d5a7 100644 (file)
@@ -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: