From: Parmjit Virk Date: Sat, 26 May 2018 13:05:54 +0000 (-0500) Subject: [cbc] Fix playlist title extraction (closes #16502) X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=commitdiff_plain;ds=inline;h=986c0b0215b127713825fa1523966ac66e03157b;p=youtube-dl.git [cbc] Fix playlist title extraction (closes #16502) --- diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 54b4b9be9..ce8e3d346 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -20,6 +20,7 @@ from ..utils import ( parse_duration, parse_iso8601, parse_age_limit, + strip_or_none, int_or_none, ExtractorError, ) @@ -129,6 +130,9 @@ class CBCIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) + title = self._og_search_title(webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', default=None) or self._html_search_regex( + r'([^<]+)', webpage, 'title', fatal=False) entries = [ self._extract_player_init(player_init, display_id) for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)] @@ -136,8 +140,7 @@ class CBCIE(InfoExtractor): self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r']+src="[^"]+?mediaId=(\d+)"', webpage)]) return self.playlist_result( - entries, display_id, - self._og_search_title(webpage, fatal=False), + entries, display_id, strip_or_none(title), self._og_search_description(webpage))