mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
Code Issues Projects Releases Wiki Activity

[ie/sproutvideo] Fix extractor (#13544)

Browse Source 
Closes #13540
Authored by: bashonly
This commit is contained in:
bashonly 2025-06-25 14:02:37 -05:00 committed by GitHub
parent 8f94b76cbf
commit 5b559d0072
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
yt_dlp/extractor/sproutvideo.py
View File

@ -41,6 +41,7 @@ class SproutVideoIE(InfoExtractor):
'duration': 703, 'duration': 703,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg', 'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
}, },
'skip': 'Account Disabled',
}, { }, {
# http formats 'sd' and 'hd' are available # http formats 'sd' and 'hd' are available
'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90', 'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90',
@ -97,11 +98,21 @@ def _extract_embed_urls(cls, url, webpage):
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage( webpage = self._download_webpage(url, video_id, headers={
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'})) **traverse_obj(smuggled_data, {'Referer': 'referer'}),
# yt-dlp's default Chrome user-agents are too old
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:140.0) Gecko/20100101 Firefox/140.0',
})
data = self._search_json( data = self._search_json(
r'var\s+dat\s*=\s*["\']', webpage, 'data', video_id, contains_pattern=r'[A-Za-z0-9+/=]+', r'var\s+(?:dat|playerInfo)\s*=\s*["\']', webpage, 'player info', video_id,
end_pattern=r'["\'];', transform_source=lambda x: base64.b64decode(x).decode()) contains_pattern=r'[A-Za-z0-9+/=]+', end_pattern=r'["\'];',
transform_source=lambda x: base64.b64decode(x).decode())
# SproutVideo may send player info for 'SMPTE Color Monitor Test' [a791d7b71b12ecc52e]
# e.g. if the user-agent we used with the webpage request is too old
video_uid = data['videoUid']
if video_id != video_uid:
raise ExtractorError(f'{self.IE_NAME} sent the wrong video data ({video_uid})')
formats, subtitles = [], {} formats, subtitles = [], {}
headers = { headers = {