[cbc] Fix playlist title extraction (closes #16502)

This commit is contained in:
Parmjit Virk 2018-05-26 08:05:54 -05:00 committed by Sergey M
parent 97b01144bd
commit 986c0b0215

View file

@ -20,6 +20,7 @@ from ..utils import (
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
parse_age_limit, parse_age_limit,
strip_or_none,
int_or_none, int_or_none,
ExtractorError, ExtractorError,
) )
@ -129,6 +130,9 @@ class CBCIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) 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'<title>([^<]+)</title>', webpage, 'title', fatal=False)
entries = [ entries = [
self._extract_player_init(player_init, display_id) self._extract_player_init(player_init, display_id)
for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)] 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) self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
return self.playlist_result( return self.playlist_result(
entries, display_id, entries, display_id, strip_or_none(title),
self._og_search_title(webpage, fatal=False),
self._og_search_description(webpage)) self._og_search_description(webpage))