Mirroring
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Releases Wiki Activity

Merge 562083e557 into 404bd889d0

Browse Source
pull/11944/merge
D Trombett 12 hours ago committed by GitHub
parent 404bd889d0 562083e557
commit 0e9d63f641
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 157 additions and 134 deletions
Show Stats Download Patch File Download Diff File

291
yt_dlp/extractor/plutotv.py
Unescape Escape View File

@ -3,29 +3,11 @@ import urllib.parse
import uuid import uuid
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import ExtractorError, float_or_none, int_or_none, smuggle_url, traverse_obj, unsmuggle_url
ExtractorError,
float_or_none,
int_or_none,
try_get,
url_or_none,
)
class PlutoTVIE(InfoExtractor): class PlutoTVBase(InfoExtractor):
_WORKING = False _START_QUERY = {
_VALID_URL = r'''(?x)
https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
/(?P<video_type>movies|series)
/(?P<series_or_movie_slug>[^/]+)
(?:
(?:/seasons?/(?P<season_no>\d+))?
(?:/episode/(?P<episode_slug>[^/]+))?
)?
/?(?:$|[#?])'''
_INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
_INFO_QUERY_PARAMS = {
'appName': 'web', 'appName': 'web',
'appVersion': 'na', 'appVersion': 'na',
'clientID': str(uuid.uuid1()), 'clientID': str(uuid.uuid1()),
@ -35,66 +17,92 @@ class PlutoTVIE(InfoExtractor):
'deviceModel': 'web', 'deviceModel': 'web',
'deviceType': 'web', 'deviceType': 'web',
'deviceVersion': 'unknown', 'deviceVersion': 'unknown',
'sid': str(uuid.uuid1()),
} }
_TESTS = [
{ def _resolve_data(self, start, element):
'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3', return {
'md5': 'ebcdd8ed89aaace9df37924f722fd9bd', 'stitcher': start['servers']['stitcher'],
'info_dict': { 'path': element['stitched']['path'],
'id': '5de6c598e9379ae4912df0a8', 'stitcherParams': start['stitcherParams'],
'ext': 'mp4', 'sessionToken': start['sessionToken'],
'title': 'It\'s In The Cards', 'id': element.get('id') or element['_id'],
'episode': 'It\'s In The Cards', }
'description': 'The teams face off against each other in a 3-on-2 soccer showdown. Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.',
'series': 'I Love Money', def _extract_formats(self, video_data):
'season_number': 2, formats, subtitles = self._extract_m3u8_formats_and_subtitles(f"{video_data['stitcher']}/v2{video_data['path']}?{video_data['stitcherParams']}&jwt={video_data['sessionToken']}", video_data['id'])
'episode_number': 3, for f in formats:
'duration': 3600, f['url'] += f"&jwt={video_data['sessionToken']}"
}, f.setdefault('vcodec', 'avc1.64001f')
}, { f.setdefault('acodec', 'mp4a.40.2')
'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/', f.setdefault('fps', 30)
'playlist_count': 11, return {
'info_dict': { 'formats': formats,
'id': '5de6c582e9379ae4912dedbd', 'subtitles': subtitles,
'title': 'I Love Money - Season 1', }
},
}, {
'url': 'https://pluto.tv/on-demand/series/i-love-money/', class PlutoTVIE(PlutoTVBase):
'playlist_count': 26, _VALID_URL = r'''(?x)
'info_dict': { https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
'id': '5de6c582e9379ae4912dedbd', /(movies|series)
'title': 'I Love Money', /(?P<slug>[^/]+)
}, (?:
}, { (?:/seasons?/(?P<season>\d+))?
'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1', (?:/episode/(?P<episode>[^/]+))?
'md5': '3cead001d317a018bf856a896dee1762', )?'''
'info_dict': { _TESTS = [{
'id': '5e83ac701fa6a9001bb9df24', 'url': 'https://pluto.tv/it/on-demand/movies/6246b0adef11000014d220c3',
'ext': 'mp4', 'md5': '5efe37ad6c1085a4ad4684b9b82cb1c1',
'title': 'Arrival', 'info_dict': {
'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.', 'id': '6246b0adef11000014d220c3',
'duration': 9000, 'ext': 'mp4',
}, 'episode_id': '6246b0adef11000014d220c3',
}, { 'description': 'md5:c9a412d330d3d73a527e9ba981c0ddb8',
'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1', 'episode': 'Non Bussate A Quella Porta',
'only_matching': True, 'thumbnail': 'http://images.pluto.tv/episodes/6246b0adef11000014d220c3/poster.jpg?fm=png&q=100',
}, { 'display_id': 'dont-knock-twice-it-2016-1-1',
'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1', 'genres': ['Horror'],
'only_matching': True, 'title': 'Non Bussate A Quella Porta',
'duration': 5940,
},
}, {
'url': 'https://pluto.tv/on-demand/movies/6246b0adef11000014d220c3',
'only_matching': True,
}, {
'url': 'https://pluto.tv/on-demand/series/6655b0c5cceea000134aee27',
'info_dict': {
'id': '6655b0c5cceea000134aee27',
'title': 'Mission Impossible',
'description': 'md5:21604bf9971528825c359e0f4977d572',
}, },
{ 'playlist_mincount': 113,
'url': 'https://pluto.tv/en/on-demand/movies/attack-of-the-killer-tomatoes-1977-1-1-ptv1', }, {
'md5': '7db56369c0da626a32d505ec6eb3f89f', 'url': 'https://pluto.tv/on-demand/series/66ab6d80b20e79001338fe4c/season/5',
'info_dict': { 'info_dict': {
'id': '5b190c7bb0875c36c90c29c4', 'id': '66ab6d80b20e79001338fe4c-5',
'ext': 'mp4', 'title': 'Squadra Speciale Cobra 11 - Season 5',
'title': 'Attack of the Killer Tomatoes',
'description': 'A group of scientists band together to save the world from mutated tomatoes that KILL! (1978)',
'duration': 5700,
},
}, },
] 'playlist_count': 17,
}, {
'url': 'https://pluto.tv/on-demand/series/62f5fb1b51b268001a993666/season/2/episode/62fb6e32946347001bf008ca',
'md5': '7e100cd3b771e9dd9b6af81abdd812af',
'info_dict': {
'id': '62fb6e32946347001bf008ca',
'ext': 'mp4',
'display_id': 'serie-2-episodio-5-2006-2-5',
'episode_id': '62fb6e32946347001bf008ca',
'genres': ['Sci-Fi & Fantasy'],
'thumbnail': 'http://images.pluto.tv/episodes/62fb6e32946347001bf008ca/poster.jpg?fm=png&q=100',
'season_number': 2,
'series_id': '62f5fb1b51b268001a993666',
'title': 'L\'ascesa dei Cyber-uomini (parte 1)',
'duration': 3120.0,
'season': 'Season 2',
'series': 'Doctor Who',
'description': 'md5:66965714ba60b02996bd1b551475f6fa',
'episode': 'L\'ascesa dei Cyber-uomini (parte 1)',
},
}]
def _to_ad_free_formats(self, video_id, formats, subtitles): def _to_ad_free_formats(self, video_id, formats, subtitles):
ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set() ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
@ -130,63 +138,78 @@ class PlutoTVIE(InfoExtractor):
self.report_warning('Unable to find ad-free formats') self.report_warning('Unable to find ad-free formats')
return formats, subtitles return formats, subtitles
def _get_video_info(self, video_json, slug, series_name=None): def _get_video_info(self, video, series=None, season_number=None):
video_id = video_json.get('_id', slug) thumbnails = [{
formats, subtitles = [], {} 'url': cover['url'],
for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []: 'width': int(m.group(1)) if (m := re.search(r'w=(\d+)&h=(\d+)', cover['url'])) else None,
if video_url.get('type') != 'hls': 'height': int(m.group(2)) if m else None,
continue } for cover in video.get('covers', [])]
url = url_or_none(video_url.get('url')) first_cover = traverse_obj(video, ('covers', 0, 'url'))
if first_cover:
fmts, subs = self._extract_m3u8_formats_and_subtitles( thumbnails.append({
url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) 'id': 'original',
formats.extend(fmts) 'url': re.sub(r'\?.*$', '?fm=png&q=100', first_cover),
subtitles = self._merge_subtitles(subtitles, subs) 'preference': 1,
formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
info = {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'title': video_json.get('name'),
'description': video_json.get('description'),
'duration': float_or_none(video_json.get('duration'), scale=1000),
}
if series_name:
info.update({
'series': series_name,
'episode': video_json.get('name'),
'season_number': int_or_none(video_json.get('season')),
'episode_number': int_or_none(video_json.get('number')),
}) })
return info return {
'id': video.get('id') or video['_id'],
'title': video.get('name'),
'display_id': video.get('slug'),
'thumbnails': thumbnails,
'description': video.get('description'),
'duration': float_or_none(video.get('duration'), scale=1000),
'genres': [video.get('genre')],
'series_id': series and series.get('id'),
'series': series and series.get('name'),
'episode': video.get('name'),
'episode_id': video.get('id') or video['_id'],
'season_number': int_or_none(season_number),
}
def _playlist_entry(self, video_json, series, season, ep):
episode_id = ep.get('id') or ep['_id']
return self.url_result(
smuggle_url(
f"https://pluto.tv/on-demand/series/{series.get('id') or series['_id']}/season/{season['number']}/episode/{episode_id}",
self._resolve_data(video_json, ep),
),
PlutoTVIE,
episode_id,
ep.get('name'),
**self._get_video_info(ep, series, season.get('number')),
)
def _real_extract(self, url): def _real_extract(self, url):
url, video_data = unsmuggle_url(url)
if video_data:
return {**self._extract_formats(video_data), 'id': video_data['id']}
mobj = self._match_valid_url(url).groupdict() mobj = self._match_valid_url(url).groupdict()
info_slug = mobj['series_or_movie_slug'] slug = mobj['slug']
video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS) season_number, episode_id = mobj.get('season'), mobj.get('episode')
query = {**self._START_QUERY, 'seriesIDs': slug}
if mobj['video_type'] == 'series': if episode_id:
series_name = video_json.get('name', info_slug) query['episodeIDs'] = episode_id
season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug')
video_json = self._download_json('https://boot.pluto.tv/v4/start', slug, 'Downloading info json', query=query)
videos = [] series = video_json['VOD'][0]
for season in video_json['seasons']:
if season_number is not None and season_number != int_or_none(season.get('number')): if episode_id:
continue episode = traverse_obj(video_json, ('VOD', 1))
for episode in season['episodes']: if not episode:
if episode_slug is not None and episode_slug != episode.get('slug'): raise ExtractorError('Failed to find episode')
continue return {**self._get_video_info(episode, series, season_number), **self._extract_formats(self._resolve_data(video_json, episode))}
videos.append(self._get_video_info(episode, episode_slug, series_name))
if not videos: if season_number:
raise ExtractorError('Failed to find any videos to extract') season = next((s for s in series['seasons'] if s['number'] == int(season_number)), None)
if episode_slug is not None and len(videos) == 1: if not season:
return videos[0] raise ExtractorError(f'Failed to find season {season_number}')
playlist_title = series_name return self.playlist_result(
if season_number is not None: [self._playlist_entry(video_json, series, season, ep) for ep in season['episodes']],
playlist_title += ' - Season %d' % season_number f"{series['id']}-{season_number}", f"{series['name']} - Season {season_number}",
return self.playlist_result(videos, )
playlist_id=video_json.get('_id', info_slug),
playlist_title=playlist_title) return self.playlist_result(
return self._get_video_info(video_json, info_slug) [self._playlist_entry(video_json, series, season, ep) for season in series.get('seasons', []) for ep in season['episodes']],
series['id'], series['name'], series.get('description'),
) if 'seasons' in series else {**self._get_video_info(series), **self._extract_formats(self._resolve_data(video_json, series))}

Write Preview
Loading…
Cancel
Save