Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

[extractor/rtbf] Fix stream extractor (#4671)

Browse Source 
Closes #4656
Authored by: elyse0
This commit is contained in:
Elyse 2022-08-18 15:12:04 -05:00 committed by GitHub
parent f60ef66371
commit 2b3e43e247
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 31 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
yt_dlp/extractor/redbee.py
View File

@ -69,6 +69,10 @@ def _get_formats_and_subtitles(self, asset_id, **kwargs):
fmts, subs = self._extract_m3u8_formats_and_subtitles( fmts, subs = self._extract_m3u8_formats_and_subtitles(
format['mediaLocator'], asset_id, fatal=False) format['mediaLocator'], asset_id, fatal=False)
if format.get('drm'):
for f in fmts:
f['has_drm'] = True
formats.extend(fmts) formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles) self._merge_subtitles(subs, target=subtitles)
@ -269,8 +273,17 @@ def _real_extract(self, url):
embed_page = self._download_webpage( embed_page = self._download_webpage(
'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'), 'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'),
media_id, query={'id': media_id}) media_id, query={'id': media_id})
data = self._parse_json(self._html_search_regex(
r'data-media="([^"]+)"', embed_page, 'media data'), media_id) media_data = self._html_search_regex(r'data-media="([^"]+)"', embed_page, 'media data', fatal=False)
if not media_data:
if re.search(r'<div[^>]+id="js-error-expired"[^>]+class="(?![^"]*hidden)', embed_page):
raise ExtractorError('Livestream has ended.', expected=True)
if re.search(r'<div[^>]+id="js-sso-connect"[^>]+class="(?![^"]*hidden)', embed_page):
self.raise_login_required()
raise ExtractorError('Could not find media data')
data = self._parse_json(media_data, media_id)
error = data.get('error') error = data.get('error')
if error: if error:
@ -280,15 +293,20 @@ def _real_extract(self, url):
if provider in self._PROVIDERS: if provider in self._PROVIDERS:
return self.url_result(data['url'], self._PROVIDERS[provider]) return self.url_result(data['url'], self._PROVIDERS[provider])
title = data['subtitle'] title = traverse_obj(data, 'subtitle', 'title')
is_live = data.get('isLive') is_live = data.get('isLive')
height_re = r'-(\d+)p\.' height_re = r'-(\d+)p\.'
formats = [] formats, subtitles = [], {}
m3u8_url = data.get('urlHlsAes128') or data.get('urlHls') # The old api still returns m3u8 and mpd manifest for livestreams, but these are 'fake'
# since all they contain is a 20s video that is completely unrelated.
# https://github.com/yt-dlp/yt-dlp/issues/4656#issuecomment-1214461092
m3u8_url = None if data.get('isLive') else traverse_obj(data, 'urlHlsAes128', 'urlHls')
if m3u8_url: if m3u8_url:
formats.extend(self._extract_m3u8_formats( fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)) m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x
http_url = data.get('url') http_url = data.get('url')
@ -319,10 +337,12 @@ def _real_extract(self, url):
'height': height, 'height': height,
}) })
mpd_url = data.get('urlDash') mpd_url = None if data.get('isLive') else data.get('urlDash')
if mpd_url and (self.get_param('allow_unplayable_formats') or not data.get('drm')): if mpd_url and (self.get_param('allow_unplayable_formats') or not data.get('drm')):
formats.extend(self._extract_mpd_formats( fmts, subs = self._extract_mpd_formats_and_subtitles(
mpd_url, media_id, mpd_id='dash', fatal=False)) mpd_url, media_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
audio_url = data.get('urlAudio') audio_url = data.get('urlAudio')
if audio_url: if audio_url:
@ -332,7 +352,6 @@ def _real_extract(self, url):
'vcodec': 'none', 'vcodec': 'none',
}) })
subtitles = {}
for track in (data.get('tracks') or {}).values(): for track in (data.get('tracks') or {}).values():
sub_url = track.get('url') sub_url = track.get('url')
if not sub_url: if not sub_url:
@ -342,7 +361,7 @@ def _real_extract(self, url):
}) })
if not formats: if not formats:
fmts, subs = self._get_formats_and_subtitles(url, media_id) fmts, subs = self._get_formats_and_subtitles(url, f'live_{media_id}' if is_live else media_id)
formats.extend(fmts) formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles) self._merge_subtitles(subs, target=subtitles)