From eea2fafcf506336e37ca514f72757acf8ee004af Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 16 May 2018 18:34:25 +0100 Subject: [PATCH] [pbs] fix embed data extraction(fixes #16474) --- youtube_dl/extractor/pbs.py | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index f11d5da52..a28ee17ca 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -505,7 +505,7 @@ class PBSIE(InfoExtractor): if player: video_info = self._parse_json( self._search_regex( - r'(?s)PBS\.videoData\s*=\s*({.+?});\n', + [r'(?s)PBS\.videoData\s*=\s*({.+?});\n', r'window\.videoBridge\s*=\s*({.+?});'], player, '%s video data' % page, default='{}'), display_id, transform_source=js_to_json, fatal=False) if video_info: @@ -513,10 +513,14 @@ class PBSIE(InfoExtractor): if not info: info = video_info if not chapters: - for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player): - chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False) - if not chapter: - continue + raw_chapters = video_info.get('chapters') or [] + if not raw_chapters: + for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player): + chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False) + if not chapter: + continue + raw_chapters.append(chapter) + for chapter in raw_chapters: start_time = float_or_none(chapter.get('start_time'), 1000) duration = float_or_none(chapter.get('duration'), 1000) if start_time is None or duration is None: