From 50317dbbada099eaefdc4bc56fff8109907a827a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 13 Sep 2014 09:01:57 +0200 Subject: [PATCH] [facebook] Fix and caption if title is empty --- youtube_dl/extractor/facebook.py | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index afb34ce51..d675a939d 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -29,13 +29,13 @@ 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': '120708114770723', + 'id': '637842556329505', 'ext': 'mp4', - 'duration': 279, - 'title': 'PEOPLE ARE AWESOME 2013', + 'duration': 38, + 'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...', } }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', @@ -125,7 +125,16 @@ def _real_extract(self, url): raise ExtractorError('Cannot find video URL') video_title = self._html_search_regex( - r'

([^<]*)

', webpage, 'title') + r'

([^<]*)

', webpage, 'title', + fatal=False) + if not video_title: + video_title = self._html_search_regex( + r'(?s)(.*?)', + webpage, 'alternative title', default=None) + if len(video_title) > 80 + 3: + video_title = video_title[:80] + '...' + if not video_title: + video_title = 'Facebook video #%s' % video_id return { 'id': video_id,