youtube-dl

commit a020a0dc20ced6468ec46214c394f6f360735b1d
parent b04c8f735805ea2671429ac8d683c2887a6b4db8
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Mon, 15 Sep 2014 15:10:24 +0200

[facebook] Fix support for untitled videos (Fixes #3757)

Diffstat:
M
test/test_utils.py
 | 
8
++++++++
M
youtube_dl/extractor/facebook.py
 | 
13
++++++++++---
M
youtube_dl/utils.py
 | 
10
++++++++++

3 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/test/test_utils.py b/test/test_utils.py
@@ -40,6 +40,7 @@ from youtube_dl.utils import (
     parse_iso8601,
     strip_jsonp,
     uppercase_escape,
+    limit_length,
 )
 
 
@@ -286,5 +287,12 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
 
+    def test_limit_length(self):
+        self.assertEqual(limit_length(None, 12), None)
+        self.assertEqual(limit_length('foo', 12), 'foo')
+        self.assertTrue(
+            limit_length('foo bar baz asd', 12).startswith('foo bar'))
+        self.assertTrue('...' in limit_length('foo bar baz asd', 12))
+
 if __name__ == '__main__':
     unittest.main()
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
@@ -12,8 +12,8 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     urlencode_postdata,
-
     ExtractorError,
+    limit_length,
 )
 
 
@@ -38,6 +38,14 @@ class FacebookIE(InfoExtractor):
             'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...',
         }
     }, {
+        'note': 'Video without discernible title',
+        'url': 'https://www.facebook.com/video.php?v=274175099429670',
+        'info_dict': {
+            'id': '274175099429670',
+            'ext': 'mp4',
+            'title': 'Facebook video #274175099429670',
+        }
+    }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
     }]
@@ -131,8 +139,7 @@ class FacebookIE(InfoExtractor):
             video_title = self._html_search_regex(
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
                 webpage, 'alternative title', default=None)
-            if len(video_title) > 80 + 3:
-                video_title = video_title[:80] + '...'
+            video_title = limit_length(video_title, 80)
         if not video_title:
             video_title = 'Facebook video #%s' % video_id
 
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
@@ -1571,3 +1571,13 @@ except AttributeError:
         if ret:
             raise subprocess.CalledProcessError(ret, p.args, output=output)
         return output
+
+
+def limit_length(s, length):
+    """ Add ellipses to overly long strings """
+    if s is None:
+        return None
+    ELLIPSES = '...'
+    if len(s) > length:
+        return s[:length - len(ELLIPSES)] + ELLIPSES
+    return s