diff options
author | Sergey M․ <dstftw@gmail.com> | 2016-02-11 22:02:37 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2016-02-11 22:02:37 +0600 |
commit | 6b3fbd3425180a00d99e91e6f2b9b5896c567ea4 (patch) | |
tree | 74e0adf223471e81e5c938787971bcd578ea7e1d | |
parent | a7ab46375b81dfab6b46535796f3f63296c7bb2c (diff) |
[pbs] Fix multi part videos extraction
-rw-r--r-- | youtube_dl/extractor/pbs.py | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index c159c0071..cca012953 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -366,10 +366,14 @@ class PBSIE(InfoExtractor): webpage, 'upload date', default=None)) # tabbed frontline videos - tabbed_videos = re.findall( - r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage) - if tabbed_videos: - return tabbed_videos, presumptive_id, upload_date + MULTI_PART_REGEXES = ( + r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', + r'<a[^>]+href=["\']#video-\d+["\'][^>]+data-coveid=["\'](\d+)', + ) + for p in MULTI_PART_REGEXES: + tabbed_videos = re.findall(p, webpage) + if tabbed_videos: + return tabbed_videos, presumptive_id, upload_date MEDIA_ID_REGEXES = [ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed |