[ie/digitalconcerthall] Rework extractor (#10152)

Authored by: tippfehlr, seproDev

Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com>
This commit is contained in:
tippfehlr 2024-06-30 22:48:54 +02:00 committed by GitHub
parent 61714f4695
commit 2a4f2e82db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -1,16 +1,16 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
parse_resolution,
traverse_obj,
try_get, try_get,
url_or_none,
urlencode_postdata, urlencode_postdata,
) )
from ..utils.traversal import traverse_obj
class DigitalConcertHallIE(InfoExtractor): class DigitalConcertHallIE(InfoExtractor):
IE_DESC = 'DigitalConcertHall extractor' IE_DESC = 'DigitalConcertHall extractor'
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
_OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token' _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
_ACCESS_TOKEN = None _ACCESS_TOKEN = None
_NETRC_MACHINE = 'digitalconcerthall' _NETRC_MACHINE = 'digitalconcerthall'
@ -26,7 +26,8 @@ class DigitalConcertHallIE(InfoExtractor):
'upload_date': '20210624', 'upload_date': '20210624',
'timestamp': 1624548600, 'timestamp': 1624548600,
'duration': 2798, 'duration': 2798,
'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler', 'album_artists': ['Members of the Berliner Philharmoniker', 'Simon Rössler'],
'composers': ['Kurt Weill'],
}, },
'params': {'skip_download': 'm3u8'}, 'params': {'skip_download': 'm3u8'},
}, { }, {
@ -34,8 +35,9 @@ class DigitalConcertHallIE(InfoExtractor):
'url': 'https://www.digitalconcerthall.com/en/concert/53785', 'url': 'https://www.digitalconcerthall.com/en/concert/53785',
'info_dict': { 'info_dict': {
'id': '53785', 'id': '53785',
'album_artist': 'Berliner Philharmoniker / Kirill Petrenko', 'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich', 'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
}, },
'params': {'skip_download': 'm3u8'}, 'params': {'skip_download': 'm3u8'},
'playlist_count': 3, 'playlist_count': 3,
@ -49,9 +51,20 @@ class DigitalConcertHallIE(InfoExtractor):
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$', 'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
'upload_date': '20220714', 'upload_date': '20220714',
'timestamp': 1657785600, 'timestamp': 1657785600,
'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff', 'album_artists': ['Frank Peter Zimmermann', 'Benedikt von Bernstorff', 'Jakob von Bernstorff'],
}, },
'params': {'skip_download': 'm3u8'}, 'params': {'skip_download': 'm3u8'},
}, {
'note': 'Concert with several works and an interview',
'url': 'https://www.digitalconcerthall.com/en/work/53785-1',
'info_dict': {
'id': '53785',
'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
'playlist_count': 1,
}] }]
def _perform_login(self, username, password): def _perform_login(self, username, password):
@ -97,15 +110,14 @@ def _entries(self, items, language, type_, **kwargs):
'Accept-Language': language, 'Accept-Language': language,
}) })
m3u8_url = traverse_obj( formats = []
stream_info, ('channel', lambda k, _: k.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False) for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False) formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False))
yield { yield {
'id': video_id, 'id': video_id,
'title': item.get('title'), 'title': item.get('title'),
'composer': item.get('name_composer'), 'composer': item.get('name_composer'),
'url': m3u8_url,
'formats': formats, 'formats': formats,
'duration': item.get('duration_total'), 'duration': item.get('duration_total'),
'timestamp': traverse_obj(item, ('date', 'published')), 'timestamp': traverse_obj(item, ('date', 'published')),
@ -119,31 +131,32 @@ def _entries(self, items, language, type_, **kwargs):
} }
def _real_extract(self, url): def _real_extract(self, url):
language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id') language, type_, video_id, part = self._match_valid_url(url).group('language', 'type', 'id', 'part')
if not language: if not language:
language = 'en' language = 'en'
thumbnail_url = self._html_search_regex( api_type = 'concert' if type_ == 'work' else type_
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( vid_info = self._download_json(
f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={ f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
'Accept': 'application/json', 'Accept': 'application/json',
'Accept-Language': language, 'Accept-Language': language,
}) })
album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '') album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...)) videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
if type_ == 'work':
videos = [videos[int(part) - 1]]
thumbnail = traverse_obj(vid_info, (
'image', ..., {self._proto_relative_url}, {url_or_none},
{lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': video_id, 'id': video_id,
'title': vid_info.get('title'), 'title': vid_info.get('title'),
'entries': self._entries(videos, language, thumbnails=thumbnails, album_artist=album_artist, type_=type_), 'entries': self._entries(
'thumbnails': thumbnails, videos, language, type_, thumbnail=thumbnail, album_artists=album_artists),
'album_artist': album_artist, 'thumbnail': thumbnail,
'album_artists': album_artists,
} }