From dbb18861148beed6630ebf895cd3f9e8165f75df Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Jun 2019 03:06:41 +0700 Subject: [PATCH] [ted] Improve playlist extraction (closes #21032) --- youtube_dl/extractor/ted.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 17dc41a394..9b60cc4626 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -157,16 +157,19 @@ def _playlist_videos_info(self, url, name): 'Downloading playlist webpage') playlist_entries = [] - for entry in re.findall(r'(?s)<[^>]+data-ga-context="playlist"[^>]*>', webpage): + for entry in re.findall(r'(?s)<[^>]+data-ga-context=["\']playlist["\'][^>]*>', webpage): attrs = extract_attributes(entry) entry_url = compat_urlparse.urljoin(url, attrs['href']) playlist_entries.append(self.url_result(entry_url, self.ie_key())) - final_url = self._og_search_url(webpage) + final_url = self._og_search_url(webpage, fatal=False) + playlist_id = ( + re.match(self._VALID_URL, final_url).group('playlist_id') + if final_url else None) + return self.playlist_result( - playlist_entries, - playlist_id=re.match(self._VALID_URL, final_url, re.VERBOSE).group('playlist_id'), - playlist_title=self._og_search_title(webpage), + playlist_entries, playlist_id=playlist_id, + playlist_title=self._og_search_title(webpage, fatal=False), playlist_description=self._og_search_description(webpage)) def _talk_info(self, url, video_name):