X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffacebook.py;h=10480356324d2b1d3558e570b02646990321bb27;hb=e311b6389a7582eef6f3f8ca4b41edd4efd6cd55;hp=afb34ce511f1bf2f526a03acc9083df2eba2a77c;hpb=7d4d5f25edb607371bb53c3b9bd8ed805c6fb0f6;p=youtube-dl

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index afb34ce51..104803563 100644
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -5,15 +5,17 @@ import re
 import socket
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     urlencode_postdata,
-
     ExtractorError,
+    limit_length,
 )
 
 
@@ -29,13 +31,21 @@ class FacebookIE(InfoExtractor):
     _NETRC_MACHINE = 'facebook'
     IE_NAME = 'facebook'
     _TESTS = [{
-        'url': 'https://www.facebook.com/photo.php?v=120708114770723',
-        'md5': '48975a41ccc4b7a581abd68651c1a5a8',
+        'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
+        'md5': '6a40d33c0eccbb1af76cf0485a052659',
+        'info_dict': {
+            'id': '637842556329505',
+            'ext': 'mp4',
+            'duration': 38,
+            'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
+        }
+    }, {
+        'note': 'Video without discernible title',
+        'url': 'https://www.facebook.com/video.php?v=274175099429670',
         'info_dict': {
-            'id': '120708114770723',
+            'id': '274175099429670',
             'ext': 'mp4',
-            'duration': 279,
-            'title': 'PEOPLE ARE AWESOME 2013',
+            'title': 'Facebook video #274175099429670',
         }
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
@@ -125,7 +135,15 @@ class FacebookIE(InfoExtractor):
             raise ExtractorError('Cannot find video URL')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
+            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title',
+            fatal=False)
+        if not video_title:
+            video_title = self._html_search_regex(
+                r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
+                webpage, 'alternative title', default=None)
+            video_title = limit_length(video_title, 80)
+        if not video_title:
+            video_title = 'Facebook video #%s' % video_id
 
         return {
             'id': video_id,