diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-07-16 04:30:48 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-07-16 04:30:48 +0700 |
| commit | 089b97cfee8553886d33cd52b7ede178cebd7034 (patch) | |
| tree | d8de7d83ac50bac1bbdbd9f47a549d91ccaa157d | |
| parent | decf86044d17a8ec04e43a4805a0092622d976ae (diff) | |
[nexx] Improve JS embed extraction
| -rw-r--r-- | youtube_dl/extractor/nexx.py | 18 |
1 files changed, 11 insertions, 7 deletions
diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py index 60b42cb7d..12450d4c5 100644 --- a/youtube_dl/extractor/nexx.py +++ b/youtube_dl/extractor/nexx.py @@ -72,13 +72,17 @@ class NexxIE(InfoExtractor): entries = [] # JavaScript Integration - for domain_id, video_id in re.findall( - r'''(?isx) - <script\b[^>]+\bsrc=["\']https?://require\.nexx(?:\.cloud|cdn\.com)/(\d+).+? - onPLAYReady.+? - _play\.init\s*\(.+?\s*,\s*(\d+)\s*,\s*.+?\) - ''', webpage): - entries.append('https://api.nexx.cloud/v3/%s/videos/byid/%s' % (domain_id, video_id)) + mobj = re.search( + r'<script\b[^>]+\bsrc=["\']https?://require\.nexx(?:\.cloud|cdn\.com)/(?P<id>\d+)', + webpage) + if mobj: + domain_id = mobj.group('id') + for video_id in re.findall( + r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)', + webpage): + entries.append( + 'https://api.nexx.cloud/v3/%s/videos/byid/%s' + % (domain_id, video_id)) # TODO: support more embed formats |