diff options
| author | coletdjnz <coletdjnz@protonmail.com> | 2022-10-04 08:37:48 +1300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-10-03 19:37:48 +0000 |
| commit | d3a3d7f0cc27ca78aeb807b27c7ebee88ff3161e (patch) | |
| tree | 22e9aded6d3f0ace3c9f8a5db41e4f016343a1ad /yt_dlp/extractor/jwplatform.py | |
| parent | 8671f995cc5296f1bc9f68afc886353b5a9e40aa (diff) | |
| download | hypervideo-pre-d3a3d7f0cc27ca78aeb807b27c7ebee88ff3161e.tar.lz hypervideo-pre-d3a3d7f0cc27ca78aeb807b27c7ebee88ff3161e.tar.xz hypervideo-pre-d3a3d7f0cc27ca78aeb807b27c7ebee88ff3161e.zip | |
[extractor/JWPlatform] Fix extractor (#5112)
Fix bitrate and filesize extraction and support embeds with unquoted urls.
Related: #5106
Authored by: coletdjnz
Diffstat (limited to 'yt_dlp/extractor/jwplatform.py')
| -rw-r--r-- | yt_dlp/extractor/jwplatform.py | 31 |
1 files changed, 30 insertions, 1 deletions
diff --git a/yt_dlp/extractor/jwplatform.py b/yt_dlp/extractor/jwplatform.py index d6b8420a8..c94968943 100644 --- a/yt_dlp/extractor/jwplatform.py +++ b/yt_dlp/extractor/jwplatform.py @@ -22,13 +22,42 @@ class JWPlatformIE(InfoExtractor): 'only_matching': True, }] + _WEBPAGE_TESTS = [{ + # JWPlatform iframe + 'url': 'https://www.covermagazine.co.uk/feature/2465255/business-protection-involved', + 'info_dict': { + 'id': 'AG26UQXM', + 'ext': 'mp4', + 'upload_date': '20160719', + 'timestamp': 1468923808, + 'title': '2016_05_18 Cover L&G Business Protection V1 FINAL.mp4', + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/AG26UQXM/poster.jpg?width=720', + 'description': '', + 'duration': 294.0, + }, + }, { + # Player url not surrounded by quotes + 'url': 'https://www.deutsche-kinemathek.de/en/online/streaming/darling-berlin', + 'info_dict': { + 'id': 'R10NQdhY', + 'title': 'Playgirl', + 'ext': 'mp4', + 'upload_date': '20220624', + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/R10NQdhY/poster.jpg?width=720', + 'timestamp': 1656064800, + 'description': 'BRD 1966, Will Tremper', + 'duration': 5146.0, + }, + 'params': {'allowed_extractors': ['generic', 'jwplatform']}, + }] + @classmethod def _extract_embed_urls(cls, url, webpage): for tag, key in ((r'(?:script|iframe)', 'src'), ('input', 'value')): # <input value=URL> is used by hyland.com # if we find <iframe>, dont look for <input> ret = re.findall( - r'<%s[^>]+?%s=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})' % (tag, key), + r'<%s[^>]+?%s=["\']?((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})' % (tag, key), webpage) if ret: return ret |