Merge remote-tracking branch 'rzhxeo/crunchyroll'

[youtube-dl] / youtube_dl / extractor / facebook.py

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index aa2525f175600e86434a789d2cf58a49c1362ed4..4556079c8ad5edce7a6a3efe29989299d719ed28 100644 (file)
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -1,5 +1,4 @@
 import json
-import netrc
 import re
 import socket
 
@@ -18,7 +17,7 @@ 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'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
     _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'
@@ -28,7 +27,7 @@ class FacebookIE(InfoExtractor):
         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"
         }
     }
@@ -102,10 +101,11 @@ class FacebookIE(InfoExtractor):
         if not m:
             m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
             if m_msg is not None:
-                err_msg = u'The video is not available, Facebook said: "%s"' % m_msg.group(1)
+                raise ExtractorError(
+                    u'The video is not available, Facebook said: "%s"' % m_msg.group(1),
+                    expected=True)
             else:
-                err_msg = u'Cannot parse data'
-            raise ExtractorError(err_msg)
+                raise ExtractorError(u'Cannot parse data')
         data = dict(json.loads(m.group(1)))
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)