Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-11 14:18:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

[roosterteeth] Use common code for subtitle extraction

Browse Source
This commit is contained in:
Felix S 2021-04-15 10:18:13 +02:00
parent a00d781b73
commit 015c10aeec
1 changed files with 2 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
yt_dlp/extractor/roosterteeth.py
View File

@ -103,7 +103,7 @@ def _real_extract(self, url):
api_episode_url + '/videos', display_id, api_episode_url + '/videos', display_id,
'Downloading video JSON metadata')['data'][0] 'Downloading video JSON metadata')['data'][0]
m3u8_url = video_data['attributes']['url'] m3u8_url = video_data['attributes']['url']
subtitle_m3u8_url = video_data['links']['download'] # XXX: additional URL at video_data['links']['download']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if self._parse_json(e.cause.read().decode(), display_id).get('access') is False: if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
@ -111,7 +111,7 @@ def _real_extract(self, url):
'%s is only available for FIRST members' % display_id) '%s is only available for FIRST members' % display_id)
raise raise
formats = self._extract_m3u8_formats( formats, subtitles = self._extract_m3u8_formats_and_subtitles(
m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls') m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats) self._sort_formats(formats)
@ -134,33 +134,6 @@ def _real_extract(self, url):
'url': img_url, 'url': img_url,
}) })
subtitles = {}
res = self._download_webpage_handle(
subtitle_m3u8_url, display_id,
'Downloading m3u8 information',
'Failed to download m3u8 information',
fatal=True, data=None, headers={}, query={})
if res is not False:
subtitle_m3u8_doc, _ = res
for line in subtitle_m3u8_doc.split('\n'):
if 'EXT-X-MEDIA:TYPE=SUBTITLES' in line:
parts = line.split(',')
for part in parts:
if 'LANGUAGE' in part:
lang = part[part.index('=') + 2:-1]
elif 'URI' in part:
uri = part[part.index('=') + 2:-1]
res = self._download_webpage_handle(
uri, display_id,
'Downloading m3u8 information',
'Failed to download m3u8 information',
fatal=True, data=None, headers={}, query={})
doc, _ = res
for l in doc.split('\n'):
if not l.startswith('#'):
subtitles[lang] = [{'url': uri[:-uri[::-1].index('/')] + l}]
break
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,