mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'master' of https://github.com/yt-dlp/yt-dlp into fix/ie/EuroParlWebstream
DTrombett
1 day ago
commit
7a29f46c5e
@ -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),
|
||||
}),
|
||||
}
|
||||
@ -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 +1,101 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import UserNotLive, int_or_none, parse_iso8601, url_or_none, urljoin
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class PartiBaseIE(InfoExtractor):
|
||||
def _call_api(self, path, video_id, note=None):
|
||||
return self._download_json(
|
||||
f'https://api-backend.parti.com/parti_v2/profile/{path}', video_id, note)
|
||||
|
||||
|
||||
class PartiVideoIE(PartiBaseIE):
|
||||
IE_NAME = 'parti:video'
|
||||
_VALID_URL = r'https?://(?:www\.)?parti\.com/video/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://parti.com/video/66284',
|
||||
'info_dict': {
|
||||
'id': '66284',
|
||||
'ext': 'mp4',
|
||||
'title': 'NOW LIVE ',
|
||||
'upload_date': '20250327',
|
||||
'categories': ['Gaming'],
|
||||
'thumbnail': 'https://assets.parti.com/351424_eb9e5250-2821-484a-9c5f-ca99aa666c87.png',
|
||||
'channel': 'ItZTMGG',
|
||||
'timestamp': 1743044379,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
data = self._call_api(f'get_livestream_channel_info/recent/{video_id}', video_id)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': self._extract_m3u8_formats(
|
||||
urljoin('https://watch.parti.com', data['livestream_recording']), video_id, 'mp4'),
|
||||
**traverse_obj(data, {
|
||||
'title': ('event_title', {str}),
|
||||
'channel': ('user_name', {str}),
|
||||
'thumbnail': ('event_file', {url_or_none}),
|
||||
'categories': ('category_name', {str}, filter, all),
|
||||
'timestamp': ('event_start_ts', {int_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
|
||||
class PartiLivestreamIE(PartiBaseIE):
|
||||
IE_NAME = 'parti:livestream'
|
||||
_VALID_URL = r'https?://(?:www\.)?parti\.com/creator/(?P<service>[\w]+)/(?P<id>[\w/-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://parti.com/creator/parti/Capt_Robs_Adventures',
|
||||
'info_dict': {
|
||||
'id': 'Capt_Robs_Adventures',
|
||||
'ext': 'mp4',
|
||||
'title': r"re:I'm Live on Parti \d{4}-\d{2}-\d{2} \d{2}:\d{2}",
|
||||
'view_count': int,
|
||||
'thumbnail': r're:https://assets\.parti\.com/.+\.png',
|
||||
'timestamp': 1743879776,
|
||||
'upload_date': '20250405',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://parti.com/creator/discord/sazboxgaming/0',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
service, creator_slug = self._match_valid_url(url).group('service', 'id')
|
||||
|
||||
encoded_creator_slug = creator_slug.replace('/', '%23')
|
||||
creator_id = self._call_api(
|
||||
f'get_user_by_social_media/{service}/{encoded_creator_slug}',
|
||||
creator_slug, note='Fetching user ID')
|
||||
|
||||
data = self._call_api(
|
||||
f'get_livestream_channel_info/{creator_id}', creator_id,
|
||||
note='Fetching user profile feed')['channel_info']
|
||||
|
||||
if not traverse_obj(data, ('channel', 'is_live', {bool})):
|
||||
raise UserNotLive(video_id=creator_id)
|
||||
|
||||
channel_info = data['channel']
|
||||
|
||||
return {
|
||||
'id': creator_slug,
|
||||
'formats': self._extract_m3u8_formats(
|
||||
channel_info['playback_url'], creator_slug, live=True, query={
|
||||
'token': channel_info['playback_auth_token'],
|
||||
'player_version': '1.17.0',
|
||||
}),
|
||||
'is_live': True,
|
||||
**traverse_obj(data, {
|
||||
'title': ('livestream_event_info', 'event_name', {str}),
|
||||
'description': ('livestream_event_info', 'event_description', {str}),
|
||||
'thumbnail': ('livestream_event_info', 'livestream_preview_file', {url_or_none}),
|
||||
'timestamp': ('stream', 'start_time', {parse_iso8601}),
|
||||
'view_count': ('stream', 'viewer_count', {int_or_none}),
|
||||
}),
|
||||
}
|
||||
@ -0,0 +1,43 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class RoyaLiveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://roya\.tv/live-stream/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://roya.tv/live-stream/1',
|
||||
'info_dict': {
|
||||
'id': '1',
|
||||
'title': r're:Roya TV \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://roya.tv/live-stream/21',
|
||||
'info_dict': {
|
||||
'id': '21',
|
||||
'title': r're:Roya News \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
|
||||
'ext': 'mp4',
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://roya.tv/live-stream/10000',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
media_id = self._match_id(url)
|
||||
|
||||
stream_url = self._download_json(
|
||||
f'https://ticket.roya-tv.com/api/v5/fastchannel/{media_id}', media_id)['data']['secured_url']
|
||||
|
||||
title = traverse_obj(
|
||||
self._download_json('https://backend.roya.tv/api/v01/channels/schedule-pagination', media_id, fatal=False),
|
||||
('data', 0, 'channel', lambda _, v: str(v['id']) == media_id, 'title', {str}, any))
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'formats': self._extract_m3u8_formats(stream_url, media_id, 'mp4', m3u8_id='hls', live=True),
|
||||
'title': title,
|
||||
'is_live': True,
|
||||
}
|
||||
Loading…
Reference in New Issue