mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-12-06 06:45:00 +01:00
Merge e814d07910 into 36b29bb353
This commit is contained in:
barsnick
GitHub
commit
02deebe03d
2 changed files with 121 additions and 41 deletions
|
|
@ -2287,7 +2287,10 @@ from .uplynk import (
|
|||
UplynkIE,
|
||||
UplynkPreplayIE,
|
||||
)
|
||||
from .urort import UrortIE
|
||||
from .urort import (
|
||||
UrortIE,
|
||||
UrortPlaylistIE,
|
||||
)
|
||||
from .urplay import URPlayIE
|
||||
from .usanetwork import USANetworkIE
|
||||
from .usatoday import USATodayIE
|
||||
|
|
|
|||
|
|
@ -1,60 +1,137 @@
|
|||
import urllib.parse
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
from ..networking import HEADRequest
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
extract_attributes,
|
||||
get_elements_by_class,
|
||||
urlhandle_detect_ext,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class UrortIE(InfoExtractor):
|
||||
_WORKING = False
|
||||
IE_DESC = 'NRK P3 Urørt'
|
||||
_VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/#!/Band/(?P<id>[^/]+)$'
|
||||
class UrortPlaylistIE(InfoExtractor):
|
||||
IE_DESC = 'NRK P3 Urørt Playlist'
|
||||
_VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/(?:artist|playlist)/(?P<id>[^/?#]+)$'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://urort.p3.no/#!/Band/Gerilja',
|
||||
_TESTS = [{
|
||||
'note': 'artist playlist',
|
||||
'url': 'https://urort.p3.no/artist/Gerilja',
|
||||
'md5': '5ed31a924be8a05e47812678a86e127b',
|
||||
'info_dict': {
|
||||
'id': '33124-24',
|
||||
'ext': 'mp3',
|
||||
'title': 'The Bomb',
|
||||
'thumbnail': r're:^https?://.+\.jpg',
|
||||
'uploader': 'Gerilja',
|
||||
'uploader_id': 'Gerilja',
|
||||
'upload_date': '20100323',
|
||||
'id': '1355',
|
||||
'ext': 'm4a',
|
||||
'title': 'Gerilja: Animals (radio edit)',
|
||||
'thumbnail': r're:^https?://.+\.(jpg|png]',
|
||||
},
|
||||
'params': {
|
||||
'matchtitle': '^The Bomb$', # To test, we want just one video
|
||||
'matchtitle': '^Gerilja', # To test, we want just one video
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'note': 'track playlist',
|
||||
'url': 'https://urort.p3.no/playlist/rock',
|
||||
'info_dict': {
|
||||
'id': str,
|
||||
'title': str,
|
||||
},
|
||||
'playlist_count': 100,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
fstr = urllib.parse.quote(f"InternalBandUrl eq '{playlist_id}'")
|
||||
json_url = f'http://urort.p3.no/breeze/urort/TrackDTOViews?$filter={fstr}&$orderby=Released%20desc&$expand=Tags%2CFiles'
|
||||
songs = self._download_json(json_url, playlist_id)
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
playlist_divs = get_elements_by_class('list-track-artist', webpage)
|
||||
if not playlist_divs:
|
||||
playlist_divs = get_elements_by_class('list-track-container', webpage)
|
||||
track_containers = []
|
||||
if playlist_divs:
|
||||
track_containers = get_elements_by_class('track-container', playlist_divs[0])
|
||||
if not track_containers:
|
||||
return {}
|
||||
entries = []
|
||||
for s in songs:
|
||||
formats = [{
|
||||
'tbr': f.get('Quality'),
|
||||
'ext': f['FileType'],
|
||||
'format_id': '{}-{}'.format(f['FileType'], f.get('Quality', '')),
|
||||
'url': 'http://p3urort.blob.core.windows.net/tracks/{}'.format(f['FileRef']),
|
||||
'quality': 3 if f['FileType'] == 'mp3' else 2,
|
||||
} for f in s['Files']]
|
||||
e = {
|
||||
'id': '%d-%s' % (s['BandId'], s['$id']),
|
||||
'title': s['Title'],
|
||||
'uploader_id': playlist_id,
|
||||
'uploader': s.get('BandName', playlist_id),
|
||||
'thumbnail': 'http://urort.p3.no/cloud/images/{}'.format(s['Image']),
|
||||
'upload_date': unified_strdate(s.get('Released')),
|
||||
'formats': formats,
|
||||
}
|
||||
entries.append(e)
|
||||
for track_container in track_containers:
|
||||
info_divs = get_elements_by_class('info', track_container)
|
||||
title_divs = get_elements_by_class('title', info_divs[0])
|
||||
entries.extend([self.url_result(
|
||||
urljoin(url, x)) for x in re.findall(r'<a[^>]+href="([^"]+)"', title_divs[0])])
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': playlist_id,
|
||||
'title': playlist_id,
|
||||
'entries': entries,
|
||||
'title': self._og_search_title(webpage).replace(' | NRK P3 Urørt', ''),
|
||||
}
|
||||
|
||||
|
||||
class UrortIE(InfoExtractor):
|
||||
IE_DESC = 'NRK P3 Urørt'
|
||||
_VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/track/[^/]+/(?P<id>[^/&?#$]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'note': 'MP4 AAC and default empty PNG thunbnail',
|
||||
'url': 'https://urort.p3.no/track/Gerilja/the-bomb',
|
||||
'md5': '9eee22c88598e285a3b4fa06ac387f79',
|
||||
'info_dict': {
|
||||
'id': '1356',
|
||||
'display_id': 'the-bomb',
|
||||
'ext': 'm4a',
|
||||
'title': 'Gerilja: The Bomb',
|
||||
'thumbnail': r're:^https?://.+\.(jpg|png)',
|
||||
},
|
||||
}, {
|
||||
'note': 'MP3 and custom thunbnail',
|
||||
'url': 'https://urort.p3.no/track/lokal-politikk/svarteper-1',
|
||||
'md5': 'b9cc2b97820016a89b1140f11cf78fac',
|
||||
'info_dict': {
|
||||
'id': '191567',
|
||||
'display_id': 'svarteper-1',
|
||||
'ext': 'mp3',
|
||||
'title': 'Lokal Politikk : Svarteper',
|
||||
'thumbnail': r're:^https?://',
|
||||
},
|
||||
}, {
|
||||
'note': 'WAV and custom thunbnail',
|
||||
'url': 'https://urort.p3.no/track/girl-group/shut-your-mouth-sometimes',
|
||||
'md5': '625873985ccdbbc37d05078d8927a522',
|
||||
'info_dict': {
|
||||
'id': '224148',
|
||||
'display_id': 'shut-your-mouth-sometimes',
|
||||
'ext': 'wav',
|
||||
'title': 'Girl Group: Shut Your Mouth (Sometimes) ',
|
||||
'thumbnail': r're:^https?://',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
title_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, title_id)
|
||||
track_info_divs = get_elements_by_class('track-info-page track', webpage)
|
||||
cover_divs = get_elements_by_class('cover-page', track_info_divs[0])
|
||||
if cover_divs:
|
||||
thumbnail = self._search_regex(
|
||||
r'<img[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1', cover_divs[0], 'thumbnail',
|
||||
default=None, group='value') or self._html_search_meta(
|
||||
['og:image', 'twitter:image'], webpage, 'thumbnail', default=None)
|
||||
|
||||
track_info_div = self._search_regex(r'(<div[^>]+\bclass="[^"]*track-info["\s][^>]*>)',
|
||||
track_info_divs[0], 'media URL', default=None)
|
||||
video_url = extract_attributes(track_info_div)['data-trackurl']
|
||||
video_id = extract_attributes(track_info_div).get('data-trackid') or title_id
|
||||
|
||||
# usually no media type known or extension found
|
||||
ext = determine_ext(video_url)
|
||||
if ext == 'unknown_video':
|
||||
urlh = self._request_webpage(
|
||||
HEADRequest(video_url), video_id, fatal=False, note='Checking media type')
|
||||
if urlh and urlh.status == 200:
|
||||
ext = urlhandle_detect_ext(urlh)
|
||||
|
||||
return {
|
||||
'display_id': title_id,
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': ext,
|
||||
'title': self._og_search_title(webpage).replace(' | NRK P3 Urørt', ''),
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue