From 5a116e13020813f9f1d952504455043986c28b9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Thu, 2 Feb 2017 22:45:18 +0700
Subject: [PATCH] [facebook] Fix title extraction (closes #11941)
---
youtube_dl/extractor/facebook.py | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 47bcc0dbc..b325c8200 100644
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -73,7 +73,7 @@ class FacebookIE(InfoExtractor):
'info_dict': {
'id': '274175099429670',
'ext': 'mp4',
- 'title': 'Facebook video #274175099429670',
+ 'title': 'Asif Nawab Butt posted a video to his Timeline.',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
@@ -318,10 +318,16 @@ 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)
- video_title = limit_length(video_title, 80)
if not video_title:
+ video_title = self._html_search_meta(
+ 'description', webpage, 'title')
+ if video_title:
+ video_title = limit_length(video_title, 80)
+ else:
video_title = 'Facebook video #%s' % video_id
- uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+ uploader = clean_html(get_element_by_id(
+ 'fbPhotoPageAuthorName', webpage)) or self._search_regex(
+ r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader', fatal=False)
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))