mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-25 00:31:26 +01:00
Compare commits
10 Commits
8610c7c5ad
...
615c0c24c2
Author | SHA1 | Date | |
---|---|---|---|
|
615c0c24c2 | ||
|
eb15fd5a32 | ||
|
7cecd299e4 | ||
|
48416c3718 | ||
|
2fd16fdc6e | ||
|
245ca4e515 | ||
|
0f49100783 | ||
|
05b4719f6c | ||
|
52f73ffc61 | ||
|
83dedc8369 |
|
@ -626,6 +626,11 @@ from .europeantour import EuropeanTourIE
|
||||||
from .eurosport import EurosportIE
|
from .eurosport import EurosportIE
|
||||||
from .euscreen import EUScreenIE
|
from .euscreen import EUScreenIE
|
||||||
from .expressen import ExpressenIE
|
from .expressen import ExpressenIE
|
||||||
|
from .extrememusic import (
|
||||||
|
ExtremeMusicAIE,
|
||||||
|
ExtremeMusicIE,
|
||||||
|
ExtremeMusicPIE,
|
||||||
|
)
|
||||||
from .eyedotv import EyedoTVIE
|
from .eyedotv import EyedoTVIE
|
||||||
from .facebook import (
|
from .facebook import (
|
||||||
FacebookAdsIE,
|
FacebookAdsIE,
|
||||||
|
@ -946,6 +951,10 @@ from .kaltura import KalturaIE
|
||||||
from .kankanews import KankaNewsIE
|
from .kankanews import KankaNewsIE
|
||||||
from .karaoketv import KaraoketvIE
|
from .karaoketv import KaraoketvIE
|
||||||
from .kelbyone import KelbyOneIE
|
from .kelbyone import KelbyOneIE
|
||||||
|
from .kenh14 import (
|
||||||
|
Kenh14PlaylistIE,
|
||||||
|
Kenh14VideoIE,
|
||||||
|
)
|
||||||
from .khanacademy import (
|
from .khanacademy import (
|
||||||
KhanAcademyIE,
|
KhanAcademyIE,
|
||||||
KhanAcademyUnitIE,
|
KhanAcademyUnitIE,
|
||||||
|
|
|
@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
|
||||||
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
|
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
|
||||||
}
|
}
|
||||||
|
|
||||||
def _extract_from_webpage(self, video_id, tld):
|
def _extract_from_html(self, video_id, tld):
|
||||||
webpage = self._download_webpage(
|
webpage = self._download_webpage(
|
||||||
f'https://chaturbate.{tld}/{video_id}/', video_id,
|
f'https://chaturbate.{tld}/{video_id}/', video_id,
|
||||||
headers=self.geo_verification_headers(), impersonate=True)
|
headers=self.geo_verification_headers(), impersonate=True)
|
||||||
|
@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id, tld = self._match_valid_url(url).group('id', 'tld')
|
video_id, tld = self._match_valid_url(url).group('id', 'tld')
|
||||||
return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
|
return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)
|
||||||
|
|
358
yt_dlp/extractor/extrememusic.py
Normal file
358
yt_dlp/extractor/extrememusic.py
Normal file
|
@ -0,0 +1,358 @@
|
||||||
|
import itertools
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
determine_ext,
|
||||||
|
int_or_none,
|
||||||
|
join_nonempty,
|
||||||
|
merge_dicts,
|
||||||
|
str_or_none,
|
||||||
|
traverse_obj,
|
||||||
|
unified_strdate,
|
||||||
|
url_or_none,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class ExtremeMusicBaseIE(InfoExtractor):
|
||||||
|
_API_URL = 'https://snapi.extrememusic.com'
|
||||||
|
_REQUEST_HEADERS = None
|
||||||
|
_REQUIRE_VERSION = []
|
||||||
|
|
||||||
|
def _initialize(self, url, video_id, country=None):
|
||||||
|
self._REQUIRE_VERSION = (self._configuration_arg('ver', ie_key='extrememusic')
|
||||||
|
or self._configuration_arg('version', ie_key='extrememusic'))
|
||||||
|
# This site serves different versions of the same playlist id due to geo-restriction
|
||||||
|
# use user's own country code if no code (geo_bypass_country or pre-defined country code) is provided
|
||||||
|
if not country:
|
||||||
|
country = self._download_webpage('https://ipapi.co/country_code', video_id)
|
||||||
|
self.to_screen(f'Set country code to {country}')
|
||||||
|
env = self._download_json('https://www.extrememusic.com/env', video_id)
|
||||||
|
self._REQUEST_HEADERS = {
|
||||||
|
'Accept': 'application/json',
|
||||||
|
'Origin': 'https://www.extrememusic.com',
|
||||||
|
'Referer': url,
|
||||||
|
'Sec-Fetch-Mode': 'cors',
|
||||||
|
'X-API-Auth': env['token'],
|
||||||
|
'X-Site-Id': 4,
|
||||||
|
'X-Viewer-Country': country.upper(),
|
||||||
|
}
|
||||||
|
|
||||||
|
def _get_album_data(self, album_id, video_id, fatal=True):
|
||||||
|
album = self._download_json(f'{self._API_URL}/albums/{album_id}', video_id, fatal=fatal,
|
||||||
|
note='Downloading album data', errnote='Unable to download album data',
|
||||||
|
headers=self._REQUEST_HEADERS) or {}
|
||||||
|
if video_id == album_id:
|
||||||
|
bio = self._download_json(f'{self._API_URL}/albums/{album_id}/bio', video_id, fatal=False,
|
||||||
|
note='Downloading album data', errnote='Unable to download album data',
|
||||||
|
headers=self._REQUEST_HEADERS) or {}
|
||||||
|
return merge_dicts(album, bio)
|
||||||
|
else:
|
||||||
|
return album
|
||||||
|
|
||||||
|
def _extract_track(self, album_data, track_id=None, version_id=None):
|
||||||
|
if 'tracks' in album_data and 'track_sounds' in album_data:
|
||||||
|
if not track_id and version_id:
|
||||||
|
track_id = traverse_obj(album_data['track_sounds'],
|
||||||
|
(lambda _, v: v['id'] == int(version_id), 'track_id', {int}), get_all=False)
|
||||||
|
if track := traverse_obj(album_data['tracks'],
|
||||||
|
(lambda _, v: v['id'] == int(track_id), {dict}), get_all=False):
|
||||||
|
info = {**traverse_obj(track, {
|
||||||
|
'track': ('title', {str}),
|
||||||
|
'track_number': ('sort_order', {lambda v: v + 1}, {int}),
|
||||||
|
'track_id': ('track_no', {str}),
|
||||||
|
'description': ('description', {lambda v: str_or_none(v) or None}),
|
||||||
|
'artists': ('artists', {lambda v: v or traverse_obj(album_data, ('album', 'artist'))},
|
||||||
|
{lambda v: (v if isinstance(v, list) else [v]) if v else None}),
|
||||||
|
'composers': ('composers', ..., 'name'),
|
||||||
|
'genres': (('genre', 'subgenre'), ..., 'label'),
|
||||||
|
'tag': ('keywords', ..., 'label'),
|
||||||
|
'album': ('album_title', {lambda v: str_or_none(v) or None}),
|
||||||
|
}), **traverse_obj(album_data, {
|
||||||
|
'album_artists': ('album', 'artist', {lambda v: [v] if v else None}),
|
||||||
|
'upload_date': ('album', 'created', {unified_strdate}),
|
||||||
|
})}
|
||||||
|
entries, thumbnails = [], []
|
||||||
|
for image in traverse_obj(track, ('images', 'default')):
|
||||||
|
thumbnails.append(traverse_obj(image, {
|
||||||
|
'url': ('url', {url_or_none}),
|
||||||
|
'width': ('width', {int_or_none}),
|
||||||
|
'height': ('height', {int_or_none}),
|
||||||
|
}))
|
||||||
|
if not self._REQUIRE_VERSION:
|
||||||
|
version_id = version_id or traverse_obj(track, 'default_track_sound_id', ('track_sound_ids', 0))
|
||||||
|
for sound_id in [version_id] if version_id else track['track_sound_ids']:
|
||||||
|
if sound := traverse_obj(album_data['track_sounds'],
|
||||||
|
(lambda _, v: v['id'] == int(sound_id) and v['track_id'] == int(track_id),
|
||||||
|
{dict}), get_all=False):
|
||||||
|
if (version_id
|
||||||
|
or 'all' in self._REQUIRE_VERSION
|
||||||
|
or any(x in sound['version_type'].lower() for x in self._REQUIRE_VERSION)):
|
||||||
|
formats = []
|
||||||
|
for audio_url in traverse_obj(sound, ('assets', 'audio', ('preview_url',
|
||||||
|
'preview_url_hls'))):
|
||||||
|
if determine_ext(audio_url) == 'm3u8':
|
||||||
|
m3u8_url = re.sub(r'\.m3u8\?.*', '/HLS/128_v4.m3u8', audio_url)
|
||||||
|
for f in self._extract_m3u8_formats(m3u8_url, sound_id, 'm4a', fatal=False):
|
||||||
|
formats.append({
|
||||||
|
**f,
|
||||||
|
'vcodec': 'none',
|
||||||
|
'perference': -2,
|
||||||
|
})
|
||||||
|
else:
|
||||||
|
formats.append({
|
||||||
|
'url': audio_url,
|
||||||
|
'vcodec': 'none',
|
||||||
|
})
|
||||||
|
entries.append({
|
||||||
|
'id': str(sound_id),
|
||||||
|
'title': join_nonempty('title', 'version_type', from_dict=sound, delim=' - '),
|
||||||
|
'alt_title': sound['version_type'],
|
||||||
|
**info,
|
||||||
|
'thumbnails': thumbnails,
|
||||||
|
'duration': sound.get('duration'),
|
||||||
|
'formats': formats,
|
||||||
|
'webpage_url': f"https://www.extrememusic.com/albums/{track['album_id']}?item={track_id}&ver={sound_id}",
|
||||||
|
})
|
||||||
|
|
||||||
|
if len(entries) > 1:
|
||||||
|
return {
|
||||||
|
'id': track_id,
|
||||||
|
**info,
|
||||||
|
'entries': entries,
|
||||||
|
'_type': 'playlist',
|
||||||
|
}
|
||||||
|
elif len(entries) == 1:
|
||||||
|
return entries[0]
|
||||||
|
else:
|
||||||
|
self.raise_no_formats('Track data not found', video_id=track_id)
|
||||||
|
return []
|
||||||
|
|
||||||
|
|
||||||
|
class ExtremeMusicIE(ExtremeMusicBaseIE):
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?extrememusic\.com/albums/(?P<album>\d+)\?(.*item=(?P<id>\d+))?(.*ver=(?P<ver>\d+))?'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.extrememusic.com/albums/15875?item=263381&ver=1265009&sharedTrack=dHJ1ZQ==',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1265009',
|
||||||
|
'ext': 'mp3',
|
||||||
|
'title': 'FOLLOW - Instrumental',
|
||||||
|
'alt_title': 'Instrumental',
|
||||||
|
'track': 'FOLLOW',
|
||||||
|
'track_number': 5,
|
||||||
|
'track_id': 'HPE316_05',
|
||||||
|
'artists': ['PRAERS'],
|
||||||
|
'composers': ['Joseph Andrew Banfi', 'Thomas Louis James White'],
|
||||||
|
'genres': ['POP', 'DREAM', 'INDIE'],
|
||||||
|
'tag': 'count:7',
|
||||||
|
'album': 'AVALON',
|
||||||
|
'album_artists': ['PRAERS'],
|
||||||
|
'upload_date': '20240729',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/album/600/HPE316.jpg',
|
||||||
|
'duration': 246,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.extrememusic.com/albums/15823?ver=1262087',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1262087',
|
||||||
|
'ext': 'mp3',
|
||||||
|
'title': 'MAGICAL HIGHWAY - VOCALS',
|
||||||
|
'alt_title': 'VOCALS',
|
||||||
|
'track': 'MAGICAL HIGHWAY',
|
||||||
|
'track_number': 2,
|
||||||
|
'track_id': 'ASM0002_02',
|
||||||
|
'description': 'Full version - a fun, happy and upbeat pop track with a medium - fast tempo - electronic, bouncy, bright',
|
||||||
|
'composers': ['ENB'],
|
||||||
|
'genres': ['POP', 'ELECTRO', 'JPOP'],
|
||||||
|
'tag': 'count:8',
|
||||||
|
'album': 'TOKYO POPPIN\'',
|
||||||
|
'upload_date': '20240709',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/album/600/ASM0002.jpg',
|
||||||
|
'duration': 265,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.extrememusic.com/albums/15064?item=254704',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1178851',
|
||||||
|
'ext': 'mp3',
|
||||||
|
'title': 'SWEET TOOTH - Full Version',
|
||||||
|
'alt_title': 'Full Version',
|
||||||
|
'track': 'SWEET TOOTH',
|
||||||
|
'track_number': 2,
|
||||||
|
'track_id': 'HPE263_02',
|
||||||
|
'artists': ['PILOT PAISLEY-ROSE'],
|
||||||
|
'composers': ['PILOT PAISLEY ROSE SARACENO', 'SAMUEL JAMES BRANDT'],
|
||||||
|
'genres': ['POP', 'ELECTRO', 'ROCK'],
|
||||||
|
'tag': 'count:7',
|
||||||
|
'album': 'ADDICTED',
|
||||||
|
'album_artists': ['PILOT PAISLEY-ROSE'],
|
||||||
|
'upload_date': '20230629',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/album/600/HPE263.jpg',
|
||||||
|
'duration': 161,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.extrememusic.com/albums/1315?item=24795',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '61003',
|
||||||
|
'ext': 'mp3',
|
||||||
|
'title': 'JOY TO THE WORLD (INST) - Instrumental',
|
||||||
|
'alt_title': 'Instrumental',
|
||||||
|
'track': 'JOY TO THE WORLD (INST)',
|
||||||
|
'track_number': 6,
|
||||||
|
'track_id': 'XEL016_06',
|
||||||
|
'composers': ['TRADITIONAL'],
|
||||||
|
'genres': ['HOLIDAY', 'CHRISTMAS'],
|
||||||
|
'tag': 'count:5',
|
||||||
|
'album': 'CHRISTMAS SPARKLE',
|
||||||
|
'upload_date': '20041001',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/album/600/XEL016.jpg',
|
||||||
|
'duration': 132,
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
album_id, track_id, version_id = self._match_valid_url(url).group('album', 'id', 'ver')
|
||||||
|
self._initialize(url, version_id or track_id, self.get_param('geo_bypass_country') or 'DE')
|
||||||
|
album_data = self._get_album_data(album_id, version_id or track_id)
|
||||||
|
if result := self._extract_track(album_data, track_id, version_id):
|
||||||
|
return result
|
||||||
|
else:
|
||||||
|
self.raise_no_formats('No formats were found')
|
||||||
|
|
||||||
|
|
||||||
|
class ExtremeMusicAIE(ExtremeMusicBaseIE):
|
||||||
|
IE_NAME = 'ExtremeMusic:album'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?extrememusic\.com/albums/(?P<id>\d+)(?!.*(item|ver)=)'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.extrememusic.com/albums/6778',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '6778',
|
||||||
|
'album': 'Ethereal Voices',
|
||||||
|
},
|
||||||
|
'playlist_count': 11,
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.extrememusic.com/albums/15835',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '15835',
|
||||||
|
'album': 'BIGGEST BANG',
|
||||||
|
'description': 'Minus Aura, a minimalist duo who create deep drama and emotion to put you under their spell.',
|
||||||
|
'artists': ['MINUS AURA'],
|
||||||
|
'genres': ['ELECTRONICA', 'POP', 'SYNTH'],
|
||||||
|
'tag': ['ELECTRONIC', 'STRUGGLE'],
|
||||||
|
},
|
||||||
|
'playlist_count': 4,
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
album_id = self._match_id(url)
|
||||||
|
self._initialize(url, album_id, self.get_param('geo_bypass_country') or 'DE')
|
||||||
|
album_data = self._get_album_data(album_id, album_id)
|
||||||
|
|
||||||
|
entries = []
|
||||||
|
for track_id in traverse_obj(album_data, ('tracks', ..., 'id')):
|
||||||
|
if track := self._extract_track(album_data, track_id=track_id):
|
||||||
|
if track.get('entries'):
|
||||||
|
entries.extend(track['entries'])
|
||||||
|
else:
|
||||||
|
entries.append(track)
|
||||||
|
|
||||||
|
if entries:
|
||||||
|
subgenres = traverse_obj(album_data, ('album', 'subgenres', {str_or_none}))
|
||||||
|
return merge_dicts(traverse_obj(album_data.get('album'), {
|
||||||
|
'id': ('id', {lambda v: str(v)}),
|
||||||
|
'album': ('title', {str_or_none}),
|
||||||
|
'description': ('description', {lambda v: str_or_none(v) or None}),
|
||||||
|
'artists': ('artist', {lambda v: [v] if v else None}),
|
||||||
|
'genres': ('genres', {str_or_none}, {lambda v: join_nonempty(v, subgenres, delim=', ')},
|
||||||
|
{lambda v: v.split(', ') if v else None}),
|
||||||
|
'tag': ('keywords', {lambda v: v.split(', ') if v else None}),
|
||||||
|
}), {
|
||||||
|
'description': traverse_obj(album_data, ('bio', 'description', {lambda v: str_or_none(v) or None})),
|
||||||
|
'entries': entries,
|
||||||
|
'_type': 'playlist',
|
||||||
|
})
|
||||||
|
else:
|
||||||
|
self.raise_no_formats('No formats were found')
|
||||||
|
|
||||||
|
|
||||||
|
class ExtremeMusicPIE(ExtremeMusicBaseIE):
|
||||||
|
IE_NAME = 'ExtremeMusic:playlist'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?extrememusic\.com/playlists/(?P<id>[^?]+)'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.extrememusic.com/playlists/Kf3fAppAKK2UpAUUp7KK1pBDBMrC62c_Kf8UKAAppUUKppK2UAp92K7Appp8xMx',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'Kf3fAppAKK2UpAUUp7KK1pBDBMrC62c_Kf8UKAAppUUKppK2UAp92K7Appp8xMx',
|
||||||
|
'title': 'NICE',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/featureditem/square/thumbnail_PLAYLIST_Nice-square-(formerly ChristmasTraditional).jpg',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 29,
|
||||||
|
'expected_warnings': ['This playlist has geo-restricted items. Try using --xff to specify a different country code, e.g. DE'],
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.extrememusic.com/playlists/fUKKU5KAfK61pAAKp4U4KpKUxsRk2ki_fU117KpUUAAUKAUfpA6UAfAKK8Ul5ji',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'fUKKU5KAfK61pAAKp4U4KpKUxsRk2ki_fU117KpUUAAUKAUfpA6UAfAKK8Ul5ji',
|
||||||
|
'title': 'NEO CLASSICAL',
|
||||||
|
'thumbnail': 'https://d2oet5a29f64lj.cloudfront.net/img-data/w/2480/featureditem/square/NeoClassical.jpg',
|
||||||
|
},
|
||||||
|
'playlist_mincount': 50,
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
playlist_id = self._match_id(url)
|
||||||
|
self._initialize(url, playlist_id, self.get_param('geo_bypass_country'))
|
||||||
|
|
||||||
|
def playlist_query(playlist_id, offset, limit):
|
||||||
|
# playlist api: https://snapi.extrememusic.com/playlists?id={playlist_id}&range={offset}%2C{limit}'
|
||||||
|
return self._download_json(
|
||||||
|
'https://snapi.extrememusic.com/playlists', playlist_id,
|
||||||
|
note=f'Downloading item {offset + 1}-{offset + limit}', query={
|
||||||
|
'id': playlist_id,
|
||||||
|
'range': f'{offset},{limit}',
|
||||||
|
}, headers=self._REQUEST_HEADERS)
|
||||||
|
|
||||||
|
thumbnails, entries = [], []
|
||||||
|
album_data, track_done, limit = {}, [], 50
|
||||||
|
for i in itertools.count():
|
||||||
|
playlist = playlist_query(playlist_id, i * limit, limit)
|
||||||
|
if len(playlist['playlist_items']) == 0:
|
||||||
|
break
|
||||||
|
else:
|
||||||
|
track_ids = traverse_obj(playlist, ('playlist_items', ..., 'track_id'))
|
||||||
|
for track_id in list(dict.fromkeys(track_ids)):
|
||||||
|
if track_id not in track_done:
|
||||||
|
album_id = traverse_obj(playlist,
|
||||||
|
('tracks', lambda _, v: v['id'] == track_id, 'album_id', {int}), get_all=False)
|
||||||
|
if album_id not in album_data:
|
||||||
|
album_data[album_id] = self._get_album_data(album_id, track_id, fatal=False)
|
||||||
|
playlist['album'] = traverse_obj(album_data, (album_id, 'album', {dict}))
|
||||||
|
if track := self._extract_track(playlist, track_id=track_id):
|
||||||
|
if track.get('entries'):
|
||||||
|
entries.extend(track['entries'])
|
||||||
|
else:
|
||||||
|
entries.append(track)
|
||||||
|
track_done.append(track_id)
|
||||||
|
if len(track_done) >= playlist['playlist']['playlist_items_count']:
|
||||||
|
break
|
||||||
|
|
||||||
|
if entries:
|
||||||
|
if len(track_done) < playlist['playlist']['playlist_items_count']:
|
||||||
|
self.report_warning('This playlist has geo-restricted items. Try using --xff to specify a different country code, e.g. DE')
|
||||||
|
|
||||||
|
for image in traverse_obj(playlist['playlist'], ('images', 'square')):
|
||||||
|
thumbnails.append(traverse_obj(image, {
|
||||||
|
'url': ('url', {url_or_none}),
|
||||||
|
'width': ('width', {int_or_none}),
|
||||||
|
'height': ('height', {int_or_none}),
|
||||||
|
}))
|
||||||
|
|
||||||
|
return {k: v for k, v in {
|
||||||
|
'id': playlist['playlist']['id'],
|
||||||
|
'title': playlist['playlist']['title'],
|
||||||
|
'thumbnail': traverse_obj(thumbnails, (0, 'url', {url_or_none})),
|
||||||
|
'thumbnails': thumbnails,
|
||||||
|
'uploader': playlist['playlist']['owner_name'],
|
||||||
|
'entries': entries,
|
||||||
|
'_type': 'playlist',
|
||||||
|
}.items() if v}
|
||||||
|
else:
|
||||||
|
self.raise_no_formats('No formats were found')
|
160
yt_dlp/extractor/kenh14.py
Normal file
160
yt_dlp/extractor/kenh14.py
Normal file
|
@ -0,0 +1,160 @@
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
clean_html,
|
||||||
|
extract_attributes,
|
||||||
|
get_element_by_class,
|
||||||
|
get_element_html_by_attribute,
|
||||||
|
get_elements_html_by_class,
|
||||||
|
int_or_none,
|
||||||
|
parse_duration,
|
||||||
|
parse_iso8601,
|
||||||
|
remove_start,
|
||||||
|
strip_or_none,
|
||||||
|
unescapeHTML,
|
||||||
|
update_url,
|
||||||
|
url_or_none,
|
||||||
|
)
|
||||||
|
from ..utils.traversal import traverse_obj
|
||||||
|
|
||||||
|
|
||||||
|
class Kenh14VideoIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
|
||||||
|
'md5': '1ed67f9c3a1e74acf15db69590cf6210',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '316173',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
||||||
|
'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
|
||||||
|
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
|
||||||
|
'tags': [],
|
||||||
|
'uploader': 'Unbox Therapy',
|
||||||
|
'upload_date': '20220517',
|
||||||
|
'view_count': int,
|
||||||
|
'duration': 722.86,
|
||||||
|
'timestamp': 1652764468,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/video-316174.chn',
|
||||||
|
'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '316174',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
|
||||||
|
'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
|
||||||
|
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
|
||||||
|
'tags': [],
|
||||||
|
'upload_date': '20220517',
|
||||||
|
'view_count': int,
|
||||||
|
'duration': 70.04,
|
||||||
|
'timestamp': 1652766021,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/0-344740.chn',
|
||||||
|
'md5': 'b843495d5e728142c8870c09b46df2a9',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '344740',
|
||||||
|
'ext': 'mov',
|
||||||
|
'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
|
||||||
|
'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
|
||||||
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
|
||||||
|
'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
|
||||||
|
'uploader': 'Quang Vũ',
|
||||||
|
'upload_date': '20241024',
|
||||||
|
'view_count': int,
|
||||||
|
'duration': 198.88,
|
||||||
|
'timestamp': 1729741590,
|
||||||
|
},
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
|
attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
|
||||||
|
direct_url = attrs['data-vid']
|
||||||
|
|
||||||
|
metadata = self._download_json(
|
||||||
|
'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
|
||||||
|
remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
|
||||||
|
|
||||||
|
formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
|
||||||
|
subtitles = {}
|
||||||
|
video_data = self._download_json(
|
||||||
|
f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
|
||||||
|
if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
|
||||||
|
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||||
|
hls_url, video_id, m3u8_id='hls', fatal=False)
|
||||||
|
formats.extend(fmts)
|
||||||
|
self._merge_subtitles(subs, target=subtitles)
|
||||||
|
if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
|
||||||
|
fmts, subs = self._extract_mpd_formats_and_subtitles(
|
||||||
|
dash_url, video_id, mpd_id='dash', fatal=False)
|
||||||
|
formats.extend(fmts)
|
||||||
|
self._merge_subtitles(subs, target=subtitles)
|
||||||
|
|
||||||
|
return {
|
||||||
|
**traverse_obj(metadata, {
|
||||||
|
'duration': ('duration', {parse_duration}),
|
||||||
|
'uploader': ('author', {strip_or_none}),
|
||||||
|
'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
|
||||||
|
'view_count': ('views', {int_or_none}),
|
||||||
|
}),
|
||||||
|
'id': video_id,
|
||||||
|
'title': (
|
||||||
|
traverse_obj(metadata, ('title', {strip_or_none}))
|
||||||
|
or clean_html(self._og_search_title(webpage))
|
||||||
|
or clean_html(get_element_by_class('vdbw-title', webpage))),
|
||||||
|
'formats': formats,
|
||||||
|
'subtitles': subtitles,
|
||||||
|
'description': (
|
||||||
|
clean_html(self._og_search_description(webpage))
|
||||||
|
or clean_html(get_element_by_class('vdbw-sapo', webpage))),
|
||||||
|
'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
|
||||||
|
'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
|
||||||
|
{lambda x: x.split(';')}, ..., filter)),
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
class Kenh14PlaylistIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '71',
|
||||||
|
'title': 'Trần Tình (Naked love) mùa 2',
|
||||||
|
'description': 'md5:e9522339304956dea931722dd72eddb2',
|
||||||
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
|
||||||
|
},
|
||||||
|
'playlist_count': 9,
|
||||||
|
}, {
|
||||||
|
'url': 'https://video.kenh14.vn/playlist/0-72.chn',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '72',
|
||||||
|
'title': 'Lau Lại Đầu Từ',
|
||||||
|
'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
|
||||||
|
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
|
||||||
|
},
|
||||||
|
'playlist_count': 6,
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
playlist_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, playlist_id)
|
||||||
|
|
||||||
|
category_detail = get_element_by_class('category-detail', webpage) or ''
|
||||||
|
embed_info = traverse_obj(
|
||||||
|
self._yield_json_ld(webpage, playlist_id),
|
||||||
|
(lambda _, v: v['name'] and v['alternateName'], any)) or {}
|
||||||
|
|
||||||
|
return self.playlist_from_matches(
|
||||||
|
get_elements_html_by_class('video-item', webpage), playlist_id,
|
||||||
|
(clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
|
||||||
|
getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
|
||||||
|
ie=Kenh14VideoIE, playlist_description=(
|
||||||
|
clean_html(get_element_by_class('description', category_detail))
|
||||||
|
or unescapeHTML(embed_info.get('alternateName'))),
|
||||||
|
thumbnail=traverse_obj(
|
||||||
|
self._og_search_thumbnail(webpage),
|
||||||
|
({url_or_none}, {update_url(query=None)})))
|
Loading…
Reference in New Issue
Block a user