SolarFM/plugins/youtube_download/yt_dlp/extractor/digitalconcerthall.py

151 lines
6.3 KiB
Python
Raw Normal View History

from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_resolution,
traverse_obj,
try_get,
urlencode_postdata,
)
class DigitalConcertHallIE(InfoExtractor):
IE_DESC = 'DigitalConcertHall extractor'
2023-08-14 01:13:21 +00:00
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)'
_OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
_ACCESS_TOKEN = None
_NETRC_MACHINE = 'digitalconcerthall'
_TESTS = [{
'note': 'Playlist with only one video',
'url': 'https://www.digitalconcerthall.com/en/concert/53201',
'info_dict': {
'id': '53201-1',
'ext': 'mp4',
'composer': 'Kurt Weill',
'title': '[Magic Night]',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
'upload_date': '20210624',
'timestamp': 1624548600,
'duration': 2798,
'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler',
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'Concert with several works and an interview',
'url': 'https://www.digitalconcerthall.com/en/concert/53785',
'info_dict': {
'id': '53785',
'album_artist': 'Berliner Philharmoniker / Kirill Petrenko',
'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
},
'params': {'skip_download': 'm3u8'},
'playlist_count': 3,
2023-08-14 01:13:21 +00:00
}, {
'url': 'https://www.digitalconcerthall.com/en/film/388',
'info_dict': {
'id': '388',
'ext': 'mp4',
'title': 'The Berliner Philharmoniker and Frank Peter Zimmermann',
'description': 'md5:cfe25a7044fa4be13743e5089b5b5eb2',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
'upload_date': '20220714',
'timestamp': 1657785600,
'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff',
},
'params': {'skip_download': 'm3u8'},
}]
2023-02-21 01:18:45 +00:00
def _perform_login(self, username, password):
token_response = self._download_json(
self._OAUTH_URL,
None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({
'affiliate': 'none',
'grant_type': 'device',
'device_vendor': 'unknown',
'app_id': 'dch.webapp',
'app_version': '1.0.0',
'client_secret': '2ySLN+2Fwb',
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
self._ACCESS_TOKEN = token_response['access_token']
try:
self._download_json(
self._OAUTH_URL,
None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({
'grant_type': 'password',
'username': username,
'password': password,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': 'https://www.digitalconcerthall.com',
'Authorization': f'Bearer {self._ACCESS_TOKEN}'
})
except ExtractorError:
self.raise_login_required(msg='Login info incorrect')
def _real_initialize(self):
2023-02-21 01:18:45 +00:00
if not self._ACCESS_TOKEN:
self.raise_login_required(method='password')
2023-08-14 01:13:21 +00:00
def _entries(self, items, language, type_, **kwargs):
for item in items:
video_id = item['id']
stream_info = self._download_json(
self._proto_relative_url(item['_links']['streams']['href']), video_id, headers={
'Accept': 'application/json',
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
'Accept-Language': language
})
m3u8_url = traverse_obj(
2023-02-21 01:18:45 +00:00
stream_info, ('channel', lambda k, _: k.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False)
yield {
'id': video_id,
'title': item.get('title'),
'composer': item.get('name_composer'),
'url': m3u8_url,
'formats': formats,
'duration': item.get('duration_total'),
'timestamp': traverse_obj(item, ('date', 'published')),
'description': item.get('short_description') or stream_info.get('short_description'),
**kwargs,
'chapters': [{
'start_time': chapter.get('time'),
'end_time': try_get(chapter, lambda x: x['time'] + x['duration']),
'title': chapter.get('text'),
2023-08-14 01:13:21 +00:00
} for chapter in item['cuepoints']] if item.get('cuepoints') and type_ == 'concert' else None,
}
def _real_extract(self, url):
2023-08-14 01:13:21 +00:00
language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id')
if not language:
language = 'en'
thumbnail_url = self._html_search_regex(
r'(https?://images\.digitalconcerthall\.com/cms/thumbnails/.*\.jpg)',
self._download_webpage(url, video_id), 'thumbnail')
thumbnails = [{
'url': thumbnail_url,
**parse_resolution(thumbnail_url)
}]
vid_info = self._download_json(
2023-08-14 01:13:21 +00:00
f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={
'Accept': 'application/json',
'Accept-Language': language
})
album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '')
2023-08-14 01:13:21 +00:00
videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
return {
'_type': 'playlist',
'id': video_id,
'title': vid_info.get('title'),
2023-08-14 01:13:21 +00:00
'entries': self._entries(videos, language, thumbnails=thumbnails, album_artist=album_artist, type_=type_),
'thumbnails': thumbnails,
'album_artist': album_artist,
}