mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into pr/live-sections
commit
59dcadefdb
@ -1,8 +1,5 @@
|
||||
blank_issues_enabled: false
|
||||
contact_links:
|
||||
- name: Get help from the community on Discord
|
||||
- name: Get help on Discord
|
||||
url: https://discord.gg/H5MNcFW63r
|
||||
about: Join the yt-dlp Discord for community-powered support!
|
||||
- name: Matrix Bridge to the Discord server
|
||||
url: https://matrix.to/#/#yt-dlp:matrix.org
|
||||
about: For those who do not want to use Discord
|
||||
about: Join the yt-dlp Discord server for support and discussion
|
||||
|
@ -0,0 +1,10 @@
|
||||
from yt_dlp.extractor.common import InfoExtractor
|
||||
|
||||
|
||||
class NormalPluginIE(InfoExtractor):
|
||||
_VALID_URL = 'normal'
|
||||
REPLACED = True
|
||||
|
||||
|
||||
class _IgnoreUnderscorePluginIE(InfoExtractor):
|
||||
pass
|
@ -0,0 +1,5 @@
|
||||
from yt_dlp.postprocessor.common import PostProcessor
|
||||
|
||||
|
||||
class NormalPluginPP(PostProcessor):
|
||||
REPLACED = True
|
@ -0,0 +1,5 @@
|
||||
from yt_dlp.extractor.generic import GenericIE
|
||||
|
||||
|
||||
class OverrideGenericIE(GenericIE, plugin_name='override'):
|
||||
TEST_FIELD = 'override'
|
@ -0,0 +1,5 @@
|
||||
from yt_dlp.extractor.generic import GenericIE
|
||||
|
||||
|
||||
class _UnderscoreOverrideGenericIE(GenericIE, plugin_name='underscore-override'):
|
||||
SECONDARY_TEST_FIELD = 'underscore-override'
|
@ -0,0 +1,50 @@
|
||||
import hashlib
|
||||
import random
|
||||
import threading
|
||||
|
||||
from .common import FileDownloader
|
||||
from . import HlsFD
|
||||
from ..networking import Request
|
||||
from ..networking.exceptions import network_exceptions
|
||||
|
||||
|
||||
class BunnyCdnFD(FileDownloader):
|
||||
"""
|
||||
Downloads from BunnyCDN with required pings
|
||||
Note, this is not a part of public API, and will be removed without notice.
|
||||
DO NOT USE
|
||||
"""
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
self.to_screen(f'[{self.FD_NAME}] Downloading from BunnyCDN')
|
||||
|
||||
fd = HlsFD(self.ydl, self.params)
|
||||
|
||||
stop_event = threading.Event()
|
||||
ping_thread = threading.Thread(target=self.ping_thread, args=(stop_event,), kwargs=info_dict['_bunnycdn_ping_data'])
|
||||
ping_thread.start()
|
||||
|
||||
try:
|
||||
return fd.real_download(filename, info_dict)
|
||||
finally:
|
||||
stop_event.set()
|
||||
|
||||
def ping_thread(self, stop_event, url, headers, secret, context_id):
|
||||
# Site sends ping every 4 seconds, but this throttles the download. Pinging every 2 seconds seems to work.
|
||||
ping_interval = 2
|
||||
# Hard coded resolution as it doesn't seem to matter
|
||||
res = 1080
|
||||
paused = 'false'
|
||||
current_time = 0
|
||||
|
||||
while not stop_event.wait(ping_interval):
|
||||
current_time += ping_interval
|
||||
|
||||
time = current_time + round(random.random(), 6)
|
||||
md5_hash = hashlib.md5(f'{secret}_{context_id}_{time}_{paused}_{res}'.encode()).hexdigest()
|
||||
ping_url = f'{url}?hash={md5_hash}&time={time}&paused={paused}&resolution={res}'
|
||||
|
||||
try:
|
||||
self.ydl.urlopen(Request(ping_url, headers=headers)).read()
|
||||
except network_exceptions as e:
|
||||
self.to_screen(f'[{self.FD_NAME}] Ping failed: {e}')
|
@ -0,0 +1,178 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import HEADRequest
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
parse_qs,
|
||||
smuggle_url,
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
urlhandle_detect_ext,
|
||||
)
|
||||
from ..utils.traversal import find_element, traverse_obj
|
||||
|
||||
|
||||
class BunnyCdnIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:iframe\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
|
||||
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL}[^\'"]*)[\'"]']
|
||||
_TESTS = [{
|
||||
'url': 'https://iframe.mediadelivery.net/embed/113933/e73edec1-e381-4c8b-ae73-717a140e0924',
|
||||
'info_dict': {
|
||||
'id': 'e73edec1-e381-4c8b-ae73-717a140e0924',
|
||||
'ext': 'mp4',
|
||||
'title': 'mistress morgana (3).mp4',
|
||||
'description': '',
|
||||
'timestamp': 1693251673,
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/e73edec1-e381-4c8b-ae73-717a140e0924/thumbnail\.jpg',
|
||||
'duration': 7.0,
|
||||
'upload_date': '20230828',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
'url': 'https://iframe.mediadelivery.net/play/136145/32e34c4b-0d72-437c-9abb-05e67657da34',
|
||||
'info_dict': {
|
||||
'id': '32e34c4b-0d72-437c-9abb-05e67657da34',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1691145748,
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
|
||||
'duration': 106.0,
|
||||
'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
|
||||
'upload_date': '20230804',
|
||||
'title': 'Sanela ist Teil der #arbeitsmarktkraft',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
# Stream requires activation and pings
|
||||
'url': 'https://iframe.mediadelivery.net/embed/200867/2e8545ec-509d-4571-b855-4cf0235ccd75',
|
||||
'info_dict': {
|
||||
'id': '2e8545ec-509d-4571-b855-4cf0235ccd75',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1708497752,
|
||||
'title': 'netflix part 1',
|
||||
'duration': 3959.0,
|
||||
'description': '',
|
||||
'upload_date': '20240221',
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# Stream requires Referer
|
||||
'url': 'https://conword.io/',
|
||||
'info_dict': {
|
||||
'id': '3a5d863e-9cd6-447e-b6ef-e289af50b349',
|
||||
'ext': 'mp4',
|
||||
'title': 'Conword bei der Stadt Köln und Stadt Dortmund',
|
||||
'description': '',
|
||||
'upload_date': '20231031',
|
||||
'duration': 31.0,
|
||||
'thumbnail': 'https://video.watchuh.com/3a5d863e-9cd6-447e-b6ef-e289af50b349/thumbnail.jpg',
|
||||
'timestamp': 1698783879,
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
# URL requires token and expires
|
||||
'url': 'https://www.stockphotos.com/video/moscow-subway-the-train-is-arriving-at-the-park-kultury-station-10017830',
|
||||
'info_dict': {
|
||||
'id': '0b02fa20-4e8c-4140-8f87-f64d820a3386',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/0b02fa20-4e8c-4140-8f87-f64d820a3386/thumbnail\.jpg',
|
||||
'title': 'Moscow subway. The train is arriving at the Park Kultury station.',
|
||||
'upload_date': '20240531',
|
||||
'duration': 18.0,
|
||||
'timestamp': 1717152269,
|
||||
'description': '',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
for embed_url in super()._extract_embed_urls(url, webpage):
|
||||
yield smuggle_url(embed_url, {'Referer': url})
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
|
||||
webpage = self._download_webpage(
|
||||
f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
|
||||
headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
|
||||
query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
|
||||
|
||||
if html_title := self._html_extract_title(webpage, default=None) == '403':
|
||||
raise ExtractorError(
|
||||
'This video is inaccessible. Setting a Referer header '
|
||||
'might be required to access the video', expected=True)
|
||||
elif html_title == '404':
|
||||
raise ExtractorError('This video does not exist', expected=True)
|
||||
|
||||
headers = {'Referer': url}
|
||||
|
||||
info = traverse_obj(self._parse_html5_media_entries(url, webpage, video_id, _headers=headers), 0) or {}
|
||||
formats = info.get('formats') or []
|
||||
subtitles = info.get('subtitles') or {}
|
||||
|
||||
original_url = self._search_regex(
|
||||
r'(?:var|const|let)\s+originalUrl\s*=\s*["\']([^"\']+)["\']', webpage, 'original url', default=None)
|
||||
if url_or_none(original_url):
|
||||
urlh = self._request_webpage(
|
||||
HEADRequest(original_url), video_id=video_id, note='Checking original',
|
||||
headers=headers, fatal=False, expected_status=(403, 404))
|
||||
if urlh and urlh.status == 200:
|
||||
formats.append({
|
||||
'url': original_url,
|
||||
'format_id': 'source',
|
||||
'quality': 1,
|
||||
'http_headers': headers,
|
||||
'ext': urlhandle_detect_ext(urlh, default='mp4'),
|
||||
'filesize': int_or_none(urlh.get_header('Content-Length')),
|
||||
})
|
||||
|
||||
# MediaCage Streams require activation and pings
|
||||
src_url = self._search_regex(
|
||||
r'\.setAttribute\([\'"]src[\'"],\s*[\'"]([^\'"]+)[\'"]\)', webpage, 'src url', default=None)
|
||||
activation_url = self._search_regex(
|
||||
r'loadUrl\([\'"]([^\'"]+/activate)[\'"]', webpage, 'activation url', default=None)
|
||||
ping_url = self._search_regex(
|
||||
r'loadUrl\([\'"]([^\'"]+/ping)[\'"]', webpage, 'ping url', default=None)
|
||||
secret = traverse_obj(parse_qs(src_url), ('secret', 0))
|
||||
context_id = traverse_obj(parse_qs(src_url), ('contextId', 0))
|
||||
ping_data = {}
|
||||
if src_url and activation_url and ping_url and secret and context_id:
|
||||
self._download_webpage(
|
||||
activation_url, video_id, headers=headers, note='Downloading activation data')
|
||||
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
src_url, video_id, 'mp4', headers=headers, m3u8_id='hls', fatal=False)
|
||||
for fmt in fmts:
|
||||
fmt.update({
|
||||
'protocol': 'bunnycdn',
|
||||
'http_headers': headers,
|
||||
})
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
ping_data = {
|
||||
'_bunnycdn_ping_data': {
|
||||
'url': ping_url,
|
||||
'headers': headers,
|
||||
'secret': secret,
|
||||
'context_id': context_id,
|
||||
},
|
||||
}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(webpage, ({find_element(id='main-video', html=True)}, {extract_attributes}, {
|
||||
'title': ('data-plyr-config', {json.loads}, 'title', {str}),
|
||||
'thumbnail': ('data-poster', {url_or_none}),
|
||||
})),
|
||||
**ping_data,
|
||||
**self._search_json_ld(webpage, video_id, fatal=False),
|
||||
}
|
@ -0,0 +1,84 @@
|
||||
import json
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
jwt_decode_hs256,
|
||||
parse_iso8601,
|
||||
url_or_none,
|
||||
variadic,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class CanalsurmasIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?canalsurmas\.es/videos/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.canalsurmas.es/videos/44006-el-gran-queo-1-lora-del-rio-sevilla-20072014',
|
||||
'md5': '861f86fdc1221175e15523047d0087ef',
|
||||
'info_dict': {
|
||||
'id': '44006',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lora del Río (Sevilla)',
|
||||
'description': 'md5:3d9ee40a9b1b26ed8259e6b71ed27b8b',
|
||||
'thumbnail': 'https://cdn2.rtva.interactvty.com/content_cards/00f3e8f67b0a4f3b90a4a14618a48b0d.jpg',
|
||||
'timestamp': 1648123182,
|
||||
'upload_date': '20220324',
|
||||
},
|
||||
}]
|
||||
_API_BASE = 'https://api-rtva.interactvty.com'
|
||||
_access_token = None
|
||||
|
||||
@staticmethod
|
||||
def _is_jwt_expired(token):
|
||||
return jwt_decode_hs256(token)['exp'] - time.time() < 300
|
||||
|
||||
def _call_api(self, endpoint, video_id, fields=None):
|
||||
if not self._access_token or self._is_jwt_expired(self._access_token):
|
||||
self._access_token = self._download_json(
|
||||
f'{self._API_BASE}/jwt/token/', None,
|
||||
'Downloading access token', 'Failed to download access token',
|
||||
headers={'Content-Type': 'application/json'},
|
||||
data=json.dumps({
|
||||
'username': 'canalsur_demo',
|
||||
'password': 'dsUBXUcI',
|
||||
}).encode())['access']
|
||||
|
||||
return self._download_json(
|
||||
f'{self._API_BASE}/api/2.0/contents/{endpoint}/{video_id}/', video_id,
|
||||
f'Downloading {endpoint} API JSON', f'Failed to download {endpoint} API JSON',
|
||||
headers={'Authorization': f'jwtok {self._access_token}'},
|
||||
query={'optional_fields': ','.join(variadic(fields))} if fields else None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_info = self._call_api('content', video_id, fields=[
|
||||
'description', 'image', 'duration', 'created_at', 'tags',
|
||||
])
|
||||
stream_info = self._call_api('content_resources', video_id, 'media_url')
|
||||
|
||||
formats, subtitles = [], {}
|
||||
for stream_url in traverse_obj(stream_info, ('results', ..., 'media_url', {url_or_none})):
|
||||
if determine_ext(stream_url) == 'm3u8':
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
stream_url, video_id, m3u8_id='hls', fatal=False)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
else:
|
||||
formats.append({'url': stream_url})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(video_info, {
|
||||
'title': ('name', {str.strip}),
|
||||
'description': ('description', {str}),
|
||||
'thumbnail': ('image', {url_or_none}),
|
||||
'duration': ('duration', {float_or_none}),
|
||||
'timestamp': ('created_at', {parse_iso8601}),
|
||||
'tags': ('tags', ..., {str}),
|
||||
}),
|
||||
}
|
@ -1,142 +0,0 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
orderedSet,
|
||||
)
|
||||
|
||||
|
||||
class DeezerBaseInfoExtractor(InfoExtractor):
|
||||
def get_data(self, url):
|
||||
if not self.get_param('test'):
|
||||
self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
|
||||
|
||||
mobj = self._match_valid_url(url)
|
||||
data_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, data_id)
|
||||
geoblocking_msg = self._html_search_regex(
|
||||
r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
|
||||
default=None)
|
||||
if geoblocking_msg is not None:
|
||||
raise ExtractorError(
|
||||
f'Deezer said: {geoblocking_msg}', expected=True)
|
||||
|
||||
data_json = self._search_regex(
|
||||
(r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
|
||||
r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
|
||||
webpage, 'data JSON')
|
||||
data = json.loads(data_json)
|
||||
return data_id, webpage, data
|
||||
|
||||
|
||||
class DeezerPlaylistIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.deezer.com/playlist/176747451',
|
||||
'info_dict': {
|
||||
'id': '176747451',
|
||||
'title': 'Best!',
|
||||
'uploader': 'anonymous',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 29,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id, webpage, data = self.get_data(url)
|
||||
|
||||
playlist_title = data.get('DATA', {}).get('TITLE')
|
||||
playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
|
||||
playlist_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
|
||||
'playlist thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': playlist_id,
|
||||
'title': playlist_title,
|
||||
'uploader': playlist_uploader,
|
||||
'thumbnail': playlist_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class DeezerAlbumIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.deezer.com/fr/album/67505622',
|
||||
'info_dict': {
|
||||
'id': '67505622',
|
||||
'title': 'Last Week',
|
||||
'uploader': 'Home Brew',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 7,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
album_id, webpage, data = self.get_data(url)
|
||||
|
||||
album_title = data.get('DATA', {}).get('ALB_TITLE')
|
||||
album_uploader = data.get('DATA', {}).get('ART_NAME')
|
||||
album_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
|
||||
'album thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
'track': s.get('SNG_TITLE'),
|
||||
'track_number': int_or_none(s.get('TRACK_NUMBER')),
|
||||
'track_id': s.get('SNG_ID'),
|
||||
'artist': album_uploader,
|
||||
'album': album_title,
|
||||
'album_artist': album_uploader,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': album_id,
|
||||
'title': album_title,
|
||||
'uploader': album_uploader,
|
||||
'thumbnail': album_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
@ -0,0 +1,130 @@
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import clean_html, int_or_none, traverse_obj, url_or_none, urlencode_postdata
|
||||
|
||||
|
||||
class DigiviewIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ladigitale\.dev/digiview/#/v/(?P<id>[0-9a-f]+)'
|
||||
_TESTS = [{
|
||||
# normal video
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8e50aee2ec',
|
||||
'info_dict': {
|
||||
'id': '67a8e50aee2ec',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny 60fps 4K - Official Blender Foundation Short Film',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 635,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 635,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 0,
|
||||
'availability': 'public',
|
||||
},
|
||||
}, {
|
||||
# cut video
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8e51d0dd58',
|
||||
'info_dict': {
|
||||
'id': '67a8e51d0dd58',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny 60fps 4K - Official Blender Foundation Short Film',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 10,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 5,
|
||||
'availability': 'public',
|
||||
},
|
||||
}, {
|
||||
# changed title
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8ea5644d7a',
|
||||
'info_dict': {
|
||||
'id': '67a8ea5644d7a',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny (with title changed)',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 15,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 10,
|
||||
'availability': 'public',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json(
|
||||
'https://ladigitale.dev/digiview/inc/recuperer_video.php', video_id,
|
||||
data=urlencode_postdata({'id': video_id}))
|
||||
|
||||
clip_id = video_data['videoId']
|
||||
return self.url_result(
|
||||
f'https://www.youtube.com/watch?v={clip_id}',
|
||||
YoutubeIE, video_id, url_transparent=True,
|
||||
**traverse_obj(video_data, {
|
||||
'section_start': ('debut', {int_or_none}),
|
||||
'section_end': ('fin', {int_or_none}),
|
||||
'description': ('description', {clean_html}, filter),
|
||||
'title': ('titre', {str}),
|
||||
'thumbnail': ('vignette', {url_or_none}),
|
||||
'view_count': ('vues', {int_or_none}),
|
||||
}),
|
||||
)
|
@ -1,28 +1,37 @@
|
||||
import contextlib
|
||||
import inspect
|
||||
import os
|
||||
|
||||
from ..plugins import load_plugins
|
||||
from ..globals import LAZY_EXTRACTORS
|
||||
from ..globals import extractors as _extractors_context
|
||||
|
||||
# NB: Must be before other imports so that plugins can be correctly injected
|
||||
_PLUGIN_CLASSES = load_plugins('extractor', 'IE')
|
||||
_CLASS_LOOKUP = None
|
||||
if os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
|
||||
LAZY_EXTRACTORS.value = False
|
||||
else:
|
||||
try:
|
||||
from .lazy_extractors import _CLASS_LOOKUP
|
||||
LAZY_EXTRACTORS.value = True
|
||||
except ImportError:
|
||||
LAZY_EXTRACTORS.value = None
|
||||
|
||||
_LAZY_LOADER = False
|
||||
if not os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
|
||||
with contextlib.suppress(ImportError):
|
||||
from .lazy_extractors import * # noqa: F403
|
||||
from .lazy_extractors import _ALL_CLASSES
|
||||
_LAZY_LOADER = True
|
||||
if not _CLASS_LOOKUP:
|
||||
from . import _extractors
|
||||
|
||||
if not _LAZY_LOADER:
|
||||
from ._extractors import * # noqa: F403
|
||||
_ALL_CLASSES = [ # noqa: F811
|
||||
klass
|
||||
for name, klass in globals().items()
|
||||
_CLASS_LOOKUP = {
|
||||
name: value
|
||||
for name, value in inspect.getmembers(_extractors)
|
||||
if name.endswith('IE') and name != 'GenericIE'
|
||||
]
|
||||
_ALL_CLASSES.append(GenericIE) # noqa: F405
|
||||
}
|
||||
_CLASS_LOOKUP['GenericIE'] = _extractors.GenericIE
|
||||
|
||||
globals().update(_PLUGIN_CLASSES)
|
||||
_ALL_CLASSES[:0] = _PLUGIN_CLASSES.values()
|
||||
# We want to append to the main lookup
|
||||
_current = _extractors_context.value
|
||||
for name, ie in _CLASS_LOOKUP.items():
|
||||
_current.setdefault(name, ie)
|
||||
|
||||
from .common import _PLUGIN_OVERRIDES # noqa: F401
|
||||
|
||||
def __getattr__(name):
|
||||
value = _CLASS_LOOKUP.get(name)
|
||||
if not value:
|
||||
raise AttributeError(f'module {__name__} has no attribute {name}')
|
||||
return value
|
||||
|
@ -0,0 +1,87 @@
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FrancaisFacileIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://francaisfacile\.rfi\.fr/[a-z]{2}/(?:actualit%C3%A9|podcasts/[^/#?]+)/(?P<id>[^/#?]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250305-r%C3%A9concilier-les-jeunes-avec-la-lecture-gr%C3%A2ce-aux-r%C3%A9seaux-sociaux',
|
||||
'md5': '4f33674cb205744345cc835991100afa',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ58952-FLE-FR-20250305',
|
||||
'display_id': '20250305-réconcilier-les-jeunes-avec-la-lecture-grâce-aux-réseaux-sociaux',
|
||||
'title': 'Réconcilier les jeunes avec la lecture grâce aux réseaux sociaux',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/05/6b6af52a-f9ba-11ef-a1f8-005056a97652.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:b903c63d8585bd59e8cc4d5f80c4272d',
|
||||
'duration': 103.15,
|
||||
'timestamp': 1741177984,
|
||||
'upload_date': '20250305',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250307-argentine-le-sac-d-un-alpiniste-retrouv%C3%A9-40-ans-apr%C3%A8s-sa-mort',
|
||||
'md5': 'b8c3a63652d4ae8e8092dda5700c1cd9',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ59102-FLE-FR-20250307',
|
||||
'display_id': '20250307-argentine-le-sac-d-un-alpiniste-retrouvé-40-ans-après-sa-mort',
|
||||
'title': 'Argentine: le sac d\'un alpiniste retrouvé 40 ans après sa mort',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/07/8edf4082-fb46-11ef-8a37-005056bf762b.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:7fd088fbdf4a943bb68cf82462160dca',
|
||||
'duration': 117.74,
|
||||
'timestamp': 1741352789,
|
||||
'upload_date': '20250307',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/podcasts/un-mot-une-histoire/20250317-le-mot-de-david-foenkinos-peut-%C3%AAtre',
|
||||
'md5': 'db83c2cc2589b4c24571c6b6cf14f5f1',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ59441-FLE-FR-20250317',
|
||||
'display_id': '20250317-le-mot-de-david-foenkinos-peut-être',
|
||||
'title': 'Le mot de David Foenkinos: «peut-être» - Un mot, une histoire',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/17/4ca6cbbe-0315-11f0-a85b-005056a97652.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:3fe35fae035803df696bfa7af2496e49',
|
||||
'duration': 198.96,
|
||||
'timestamp': 1742210897,
|
||||
'upload_date': '20250317',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = urllib.parse.unquote(self._match_id(url))
|
||||
|
||||
try: # yt-dlp's default user-agents are too old and blocked by the site
|
||||
webpage = self._download_webpage(url, display_id, headers={
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
|
||||
})
|
||||
except ExtractorError as e:
|
||||
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
|
||||
raise
|
||||
# Retry with impersonation if hardcoded UA is insufficient
|
||||
webpage = self._download_webpage(url, display_id, impersonate=True)
|
||||
|
||||
data = self._search_json(
|
||||
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
|
||||
webpage, 'audio data', display_id)
|
||||
|
||||
return {
|
||||
'id': data['mediaId'],
|
||||
'display_id': display_id,
|
||||
'vcodec': 'none',
|
||||
'title': self._html_extract_title(webpage),
|
||||
**self._search_json_ld(webpage, display_id, fatal=False),
|
||||
**traverse_obj(data, {
|
||||
'title': ('title', {str}),
|
||||
'url': ('sources', ..., 'url', {url_or_none}, any),
|
||||
'duration': ('sources', ..., 'duration', {float_or_none}, any),
|
||||
}),
|
||||
}
|
@ -1,19 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class GigyaBaseIE(InfoExtractor):
|
||||
def _gigya_login(self, auth_data):
|
||||
auth_info = self._download_json(
|
||||
'https://accounts.eu1.gigya.com/accounts.login', None,
|
||||
note='Logging in', errnote='Unable to log in',
|
||||
data=urlencode_postdata(auth_data))
|
||||
|
||||
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
f'Unable to login: {error_message}', expected=True)
|
||||
return auth_info
|
@ -0,0 +1,78 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none, parse_iso8601, url_or_none, urljoin
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class IvooxIE(InfoExtractor):
|
||||
_VALID_URL = (
|
||||
r'https?://(?:www\.)?ivoox\.com/(?:\w{2}/)?[^/?#]+_rf_(?P<id>[0-9]+)_1\.html',
|
||||
r'https?://go\.ivoox\.com/rf/(?P<id>[0-9]+)',
|
||||
)
|
||||
_TESTS = [{
|
||||
'url': 'https://www.ivoox.com/dex-08x30-rostros-del-mal-los-asesinos-en-audios-mp3_rf_143594959_1.html',
|
||||
'md5': '993f712de5b7d552459fc66aa3726885',
|
||||
'info_dict': {
|
||||
'id': '143594959',
|
||||
'ext': 'mp3',
|
||||
'timestamp': 1742731200,
|
||||
'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
|
||||
'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
|
||||
'description': 'md5:eae8b4b9740d0216d3871390b056bb08',
|
||||
'uploader': 'Santiago Camacho',
|
||||
'thumbnail': 'https://static-1.ivoox.com/audios/c/d/5/2/cd52f46783fe735000c33a803dce2554_XXL.jpg',
|
||||
'upload_date': '20250323',
|
||||
'episode': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
|
||||
'duration': 11837,
|
||||
'tags': ['españa', 'asesinos en serie', 'arropiero', 'historia criminal', 'mataviejas'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://go.ivoox.com/rf/143594959',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.ivoox.com/en/campodelgas-28-03-2025-audios-mp3_rf_144036942_1.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
media_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, media_id, fatal=False)
|
||||
|
||||
data = self._search_nuxt_data(
|
||||
webpage, media_id, fatal=False, traverse=('data', 0, 'data', 'audio'))
|
||||
|
||||
direct_download = self._download_json(
|
||||
f'https://vcore-web.ivoox.com/v1/public/audios/{media_id}/download-url', media_id, fatal=False,
|
||||
note='Fetching direct download link', headers={'Referer': url})
|
||||
|
||||
download_paths = {
|
||||
*traverse_obj(direct_download, ('data', 'downloadUrl', {str}, filter, all)),
|
||||
*traverse_obj(data, (('downloadUrl', 'mediaUrl'), {str}, filter)),
|
||||
}
|
||||
|
||||
formats = []
|
||||
for path in download_paths:
|
||||
formats.append({
|
||||
'url': urljoin('https://ivoox.com', path),
|
||||
'http_headers': {'Referer': url},
|
||||
})
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'formats': formats,
|
||||
'uploader': self._html_search_regex(r'data-prm-author="([^"]+)"', webpage, 'author', default=None),
|
||||
'timestamp': parse_iso8601(
|
||||
self._html_search_regex(r'data-prm-pubdate="([^"]+)"', webpage, 'timestamp', default=None)),
|
||||
'channel': self._html_search_regex(r'data-prm-podname="([^"]+)"', webpage, 'channel', default=None),
|
||||
'title': self._html_search_regex(r'data-prm-title="([^"]+)"', webpage, 'title', default=None),
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'description': self._og_search_description(webpage, default=None),
|
||||
**self._search_json_ld(webpage, media_id, default={}),
|
||||
**traverse_obj(data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('description', {str}),
|
||||
'thumbnail': ('image', {url_or_none}),
|
||||
'timestamp': ('uploadDate', {parse_iso8601(delimiter=' ')}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'tags': ('tags', ..., 'name', {str}),
|
||||
}),
|
||||
}
|
@ -0,0 +1,159 @@
|
||||
import json
|
||||
import random
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none, jwt_decode_hs256, try_call, url_or_none
|
||||
from ..utils.traversal import require, traverse_obj
|
||||
|
||||
|
||||
class LocoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?loco\.com/(?P<type>streamers|stream)/(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://loco.com/streamers/teuzinfps',
|
||||
'info_dict': {
|
||||
'id': 'teuzinfps',
|
||||
'ext': 'mp4',
|
||||
'title': r're:MS BOLADAO, RESENHA & GAMEPLAY ALTO NIVEL',
|
||||
'description': 'bom e novo',
|
||||
'uploader_id': 'RLUVE3S9JU',
|
||||
'channel': 'teuzinfps',
|
||||
'channel_follower_count': int,
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
'concurrent_view_count': int,
|
||||
'like_count': int,
|
||||
'thumbnail': 'https://static.ivory.getloconow.com/default_thumb/743701a9-98ca-41ae-9a8b-70bd5da070ad.jpg',
|
||||
'tags': ['MMORPG', 'Gameplay'],
|
||||
'series': 'Tibia',
|
||||
'timestamp': int,
|
||||
'modified_timestamp': int,
|
||||
'live_status': 'is_live',
|
||||
'upload_date': str,
|
||||
'modified_date': str,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'Livestream',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://loco.com/stream/c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
|
||||
'md5': '45ebc8a47ee1c2240178757caf8881b5',
|
||||
'info_dict': {
|
||||
'id': 'c64916eb-10fb-46a9-9a19-8c4b7ed064e7',
|
||||
'ext': 'mp4',
|
||||
'title': 'PAULINHO LOKO NA LOCO!',
|
||||
'description': 'live on na loco',
|
||||
'uploader_id': '2MDO7Z1DPM',
|
||||
'channel': 'paulinholokobr',
|
||||
'channel_follower_count': int,
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
'concurrent_view_count': int,
|
||||
'like_count': int,
|
||||
'duration': 14491,
|
||||
'thumbnail': 'https://static.ivory.getloconow.com/default_thumb/59b5970b-23c1-4518-9e96-17ce341299fe.jpg',
|
||||
'tags': ['Gameplay'],
|
||||
'series': 'GTA 5',
|
||||
'timestamp': 1740612872,
|
||||
'modified_timestamp': 1740613037,
|
||||
'upload_date': '20250226',
|
||||
'modified_date': '20250226',
|
||||
},
|
||||
}, {
|
||||
# Requires video authorization
|
||||
'url': 'https://loco.com/stream/ac854641-ae0f-497c-a8ea-4195f6d8cc53',
|
||||
'md5': '0513edf85c1e65c9521f555f665387d5',
|
||||
'info_dict': {
|
||||
'id': 'ac854641-ae0f-497c-a8ea-4195f6d8cc53',
|
||||
'ext': 'mp4',
|
||||
'title': 'DUAS CONTAS DESAFIANTE, RUSH TOP 1 NO BRASIL!',
|
||||
'description': 'md5:aa77818edd6fe00dd4b6be75cba5f826',
|
||||
'uploader_id': '7Y9JNAZC3Q',
|
||||
'channel': 'ayellol',
|
||||
'channel_follower_count': int,
|
||||
'comment_count': int,
|
||||
'view_count': int,
|
||||
'concurrent_view_count': int,
|
||||
'like_count': int,
|
||||
'duration': 1229,
|
||||
'thumbnail': 'https://static.ivory.getloconow.com/default_thumb/f5aa678b-6d04-45d9-a89a-859af0a8028f.jpg',
|
||||
'tags': ['Gameplay', 'Carry'],
|
||||
'series': 'League of Legends',
|
||||
'timestamp': 1741182253,
|
||||
'upload_date': '20250305',
|
||||
'modified_timestamp': 1741182419,
|
||||
'modified_date': '20250305',
|
||||
},
|
||||
}]
|
||||
|
||||
# From _app.js
|
||||
_CLIENT_ID = 'TlwKp1zmF6eKFpcisn3FyR18WkhcPkZtzwPVEEC3'
|
||||
_CLIENT_SECRET = 'Kp7tYlUN7LXvtcSpwYvIitgYcLparbtsQSe5AdyyCdiEJBP53Vt9J8eB4AsLdChIpcO2BM19RA3HsGtqDJFjWmwoonvMSG3ZQmnS8x1YIM8yl82xMXZGbE3NKiqmgBVU'
|
||||
|
||||
def _is_jwt_expired(self, token):
|
||||
return jwt_decode_hs256(token)['exp'] - time.time() < 300
|
||||
|
||||
def _get_access_token(self, video_id):
|
||||
access_token = try_call(lambda: self._get_cookies('https://loco.com')['access_token'].value)
|
||||
if access_token and not self._is_jwt_expired(access_token):
|
||||
return access_token
|
||||
access_token = traverse_obj(self._download_json(
|
||||
'https://api.getloconow.com/v3/user/device_profile/', video_id,
|
||||
'Downloading access token', fatal=False, data=json.dumps({
|
||||
'platform': 7,
|
||||
'client_id': self._CLIENT_ID,
|
||||
'client_secret': self._CLIENT_SECRET,
|
||||
'model': 'Mozilla',
|
||||
'os_name': 'Win32',
|
||||
'os_ver': '5.0 (Windows)',
|
||||
'app_ver': '5.0 (Windows)',
|
||||
}).encode(), headers={
|
||||
'Content-Type': 'application/json;charset=utf-8',
|
||||
'DEVICE-ID': ''.join(random.choices('0123456789abcdef', k=32)) + 'live',
|
||||
'X-APP-LANG': 'en',
|
||||
'X-APP-LOCALE': 'en-US',
|
||||
'X-CLIENT-ID': self._CLIENT_ID,
|
||||
'X-CLIENT-SECRET': self._CLIENT_SECRET,
|
||||
'X-PLATFORM': '7',
|
||||
}), 'access_token')
|
||||
if access_token and not self._is_jwt_expired(access_token):
|
||||
self._set_cookie('.loco.com', 'access_token', access_token)
|
||||
return access_token
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_type, video_id = self._match_valid_url(url).group('type', 'id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
stream = traverse_obj(self._search_nextjs_data(webpage, video_id), (
|
||||
'props', 'pageProps', ('liveStreamData', 'stream', 'liveStream'), {dict}, any, {require('stream info')}))
|
||||
|
||||
if access_token := self._get_access_token(video_id):
|
||||
self._request_webpage(
|
||||
'https://drm.loco.com/v1/streams/playback/', video_id,
|
||||
'Downloading video authorization', fatal=False, headers={
|
||||
'authorization': access_token,
|
||||
}, query={
|
||||
'stream_uid': stream['uid'],
|
||||
})
|
||||
|
||||
return {
|
||||
'formats': self._extract_m3u8_formats(stream['conf']['hls'], video_id),
|
||||
'id': video_id,
|
||||
'is_live': video_type == 'streamers',
|
||||
**traverse_obj(stream, {
|
||||
'title': ('title', {str}),
|
||||
'series': ('game_name', {str}),
|
||||
'uploader_id': ('user_uid', {str}),
|
||||
'channel': ('alias', {str}),
|
||||
'description': ('description', {str}),
|
||||
'concurrent_view_count': ('viewersCurrent', {int_or_none}),
|
||||
'view_count': ('total_views', {int_or_none}),
|
||||
'thumbnail': ('thumbnail_url_small', {url_or_none}),
|
||||
'like_count': ('likes', {int_or_none}),
|
||||
'tags': ('tags', ..., {str}),
|
||||
'timestamp': ('started_at', {int_or_none(scale=1000)}),
|
||||
'modified_timestamp': ('updated_at', {int_or_none(scale=1000)}),
|
||||
'comment_count': ('comments_count', {int_or_none}),
|
||||
'channel_follower_count': ('followers_count', {int_or_none}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
}),
|
||||
}
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue