diff options
| author | Parmjit Virk <pvirk@mts.net> | 2018-05-26 08:05:54 -0500 |
|---|---|---|
| committer | Sergey M <dstftw@gmail.com> | 2018-05-26 20:05:54 +0700 |
| commit | 986c0b0215b127713825fa1523966ac66e03157b (patch) | |
| tree | 7624c0c0ea0378484962bad5a6b038b9d7cd5861 | |
| parent | 97b01144bd9771f224749ffca10156a1cd7e9c1f (diff) | |
| download | youtube-dl-986c0b0215b127713825fa1523966ac66e03157b.tar.xz | |
[cbc] Fix playlist title extraction (closes #16502)
| -rw-r--r-- | youtube_dl/extractor/cbc.py | 7 |
1 files changed, 5 insertions, 2 deletions
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'<title>([^<]+)</title>', 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'<iframe[^>]+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)) |