From 50317dbbada099eaefdc4bc56fff8109907a827a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 13 Sep 2014 09:01:57 +0200 Subject: [facebook] Fix and caption if title is empty --- youtube_dl/extractor/facebook.py | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'youtube_dl/extractor/facebook.py') 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 @@ class FacebookIE(InfoExtractor): 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, -- cgit v1.2.3 From a020a0dc20ced6468ec46214c394f6f360735b1d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 15 Sep 2014 15:10:24 +0200 Subject: [facebook] Fix support for untitled videos (Fixes #3757) --- youtube_dl/extractor/facebook.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'youtube_dl/extractor/facebook.py') diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index d675a939d..60e68d98a 100644 --- 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, ) @@ -37,6 +37,14 @@ class FacebookIE(InfoExtractor): 'duration': 38, '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)(.*?)', 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 -- cgit v1.2.3