fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[redbulltv] fix extraction(closes #15481)

This commit is contained in:
Remita Amine 2018-02-03 15:42:57 +01:00
parent 4989d351b4
commit e2e18694db
1 changed files with 27 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

94
youtube_dl/extractor/redbulltv.py
View File

@ -5,135 +5,93 @@ from .common import InfoExtractor
from ..compat import compat_HTTPError from ..compat import compat_HTTPError
from ..utils import ( from ..utils import (
float_or_none, float_or_none,
int_or_none,
try_get,
# unified_timestamp,
ExtractorError, ExtractorError,
) )
class RedBullTVIE(InfoExtractor): class RedBullTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?redbull\.tv/(?:video|film|live)/(?:AP-\w+/segment/)?(?P<id>AP-\w+)' _VALID_URL = r'https?://(?:www\.)?redbull\.tv/video/(?P<id>AP-\w+)'
_TESTS = [{ _TESTS = [{
# film # film
'url': 'https://www.redbull.tv/video/AP-1Q756YYX51W11/abc-of-wrc', 'url': 'https://www.redbull.tv/video/AP-1Q6XCDTAN1W11',
'md5': 'fb0445b98aa4394e504b413d98031d1f', 'md5': 'fb0445b98aa4394e504b413d98031d1f',
'info_dict': { 'info_dict': {
'id': 'AP-1Q756YYX51W11', 'id': 'AP-1Q6XCDTAN1W11',
'ext': 'mp4', 'ext': 'mp4',
'title': 'ABC of...WRC', 'title': 'ABC of... WRC - ABC of... S1E6',
'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31', 'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
'duration': 1582.04, 'duration': 1582.04,
# 'timestamp': 1488405786,
# 'upload_date': '20170301',
}, },
}, { }, {
# episode # episode
'url': 'https://www.redbull.tv/video/AP-1PMT5JCWH1W11/grime?playlist=shows:shows-playall:web', 'url': 'https://www.redbull.tv/video/AP-1PMHKJFCW1W11',
'info_dict': { 'info_dict': {
'id': 'AP-1PMT5JCWH1W11', 'id': 'AP-1PMHKJFCW1W11',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Grime - Hashtags S2 E4', 'title': 'Grime - Hashtags S2E4',
'description': 'md5:334b741c8c1ce65be057eab6773c1cf5', 'description': 'md5:b5f522b89b72e1e23216e5018810bb25',
'duration': 904.6, 'duration': 904.6,
# 'timestamp': 1487290093,
# 'upload_date': '20170217',
'series': 'Hashtags',
'season_number': 2,
'episode_number': 4,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
# segment
'url': 'https://www.redbull.tv/live/AP-1R5DX49XS1W11/segment/AP-1QSAQJ6V52111/semi-finals',
'info_dict': {
'id': 'AP-1QSAQJ6V52111',
'ext': 'mp4',
'title': 'Semi Finals - Vans Park Series Pro Tour',
'description': 'md5:306a2783cdafa9e65e39aa62f514fd97',
'duration': 11791.991,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.redbull.tv/film/AP-1MSKKF5T92111/in-motion',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
session = self._download_json( session = self._download_json(
'https://api-v2.redbull.tv/session', video_id, 'https://api.redbull.tv/v3/session', video_id,
note='Downloading access token', query={ note='Downloading access token', query={
'build': '4.370.0',
'category': 'personal_computer', 'category': 'personal_computer',
'os_version': '1.0',
'os_family': 'http', 'os_family': 'http',
}) })
if session.get('code') == 'error': if session.get('code') == 'error':
raise ExtractorError('%s said: %s' % ( raise ExtractorError('%s said: %s' % (
self.IE_NAME, session['message'])) self.IE_NAME, session['message']))
auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token']) token = session['token']
try: try:
info = self._download_json( video = self._download_json(
'https://api-v2.redbull.tv/content/%s' % video_id, 'https://api.redbull.tv/v3/products/' + video_id,
video_id, note='Downloading video information', video_id, note='Downloading video information',
headers={'Authorization': auth} headers={'Authorization': token}
) )
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
error_message = self._parse_json( error_message = self._parse_json(
e.cause.read().decode(), video_id)['message'] e.cause.read().decode(), video_id)['error']
raise ExtractorError('%s said: %s' % ( raise ExtractorError('%s said: %s' % (
self.IE_NAME, error_message), expected=True) self.IE_NAME, error_message), expected=True)
raise raise
video = info['video_product'] title = video['title'].strip()
title = info['title'].strip()
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
video['url'], video_id, 'mp4', entry_protocol='m3u8_native', 'https://dms.redbull.tv/v3/%s/%s/playlist.m3u8' % (video_id, token),
m3u8_id='hls') video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats) self._sort_formats(formats)
subtitles = {} subtitles = {}
for _, captions in (try_get( for resource in video.get('resources', []):
video, lambda x: x['attachments']['captions'], if resource.startswith('closed_caption_'):
dict) or {}).items(): splitted_resource = resource.split('_')
if not captions or not isinstance(captions, list): if splitted_resource[2]:
continue subtitles.setdefault('en', []).append({
for caption in captions: 'url': 'https://resources.redbull.tv/%s/%s' % (video_id, resource),
caption_url = caption.get('url') 'ext': splitted_resource[2],
if not caption_url:
continue
ext = caption.get('format')
if ext == 'xml':
ext = 'ttml'
subtitles.setdefault(caption.get('lang') or 'en', []).append({
'url': caption_url,
'ext': ext,
}) })
subheading = info.get('subheading') subheading = video.get('subheading')
if subheading: if subheading:
title += ' - %s' % subheading title += ' - %s' % subheading
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': info.get('long_description') or info.get( 'description': video.get('long_description') or video.get(
'short_description'), 'short_description'),
'duration': float_or_none(video.get('duration'), scale=1000), 'duration': float_or_none(video.get('duration'), scale=1000),
# 'timestamp': unified_timestamp(info.get('published')),
'series': info.get('show_title'),
'season_number': int_or_none(info.get('season_number')),
'episode_number': int_or_none(info.get('episode_number')),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
} }