From b703ebeeafed3e890270633788c7340d174cde86 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 13 Nov 2015 19:09:42 +0100 Subject: [PATCH] [twitter] Don't fail if the description doesn't contain an URL (fixes #7489) --- youtube_dl/extractor/twitter.py | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 0db7a4440..2bd5946ac 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -147,6 +147,17 @@ class TwitterIE(InfoExtractor): 'uploader': 'Gifs', 'uploader_id': 'giphz', }, + }, { + 'url': 'https://twitter.com/starwars/status/665052190608723968', + 'md5': '39b7199856dee6cd4432e72c74bc69d4', + 'info_dict': { + 'id': '665052190608723968', + 'ext': 'mp4', + 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.', + 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."', + 'uploader_id': 'starwars', + 'uploader': 'Star Wars', + }, }] def _real_extract(self, url): @@ -158,17 +169,16 @@ def _real_extract(self, url): username = remove_end(self._og_search_title(webpage), ' on Twitter') - title = self._og_search_description(webpage).strip('').replace('\n', ' ') + title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”') # strip 'https -_t.co_BJYgOjSeGA' junk from filenames - mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title) - title, short_url = mobj.groups() + title = re.sub(r'\s+(https?://[^ ]+)', '', title) info = { 'uploader_id': user_id, 'uploader': username, 'webpage_url': url, - 'description': '%s on Twitter: "%s %s"' % (username, title, short_url), + 'description': '%s on Twitter: "%s"' % (username, description), 'title': username + ' - ' + title, }