mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-01-31 04:22:25 +01:00
Code Activity

[ie/plutotv] Fix extractor

Browse source
This commit is contained in:
DTrombett 2024-12-29 19:05:40 +01:00
parent d298693b1b
commit 8658720414
No known key found for this signature in database
GPG key ID: FD8700F69650F6AA
1 changed files with 125 additions and 132 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

257
yt_dlp/extractor/plutotv.py
View file

@ -3,29 +3,11 @@ import urllib.parse
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
try_get,
url_or_none,
)
from ..utils import ExtractorError, float_or_none, int_or_none, traverse_obj
class PlutoTVIE(InfoExtractor):
_WORKING = False
_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 = {
class PlutoTVBase(InfoExtractor):
_START_QUERY = {
'appName': 'web',
'appVersion': 'na',
'clientID': str(uuid.uuid1()),
@ -35,66 +17,80 @@ class PlutoTVIE(InfoExtractor):
'deviceModel': 'web',
'deviceType': 'web',
'deviceVersion': 'unknown',
'sid': str(uuid.uuid1()),
}
_TESTS = [
{
'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
'info_dict': {
'id': '5de6c598e9379ae4912df0a8',
'ext': 'mp4',
'title': 'It\'s In The Cards',
'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',
'season_number': 2,
'episode_number': 3,
'duration': 3600,
},
}, {
'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
'playlist_count': 11,
'info_dict': {
'id': '5de6c582e9379ae4912dedbd',
'title': 'I Love Money - Season 1',
},
}, {
'url': 'https://pluto.tv/on-demand/series/i-love-money/',
'playlist_count': 26,
'info_dict': {
'id': '5de6c582e9379ae4912dedbd',
'title': 'I Love Money',
},
}, {
'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
'md5': '3cead001d317a018bf856a896dee1762',
'info_dict': {
'id': '5e83ac701fa6a9001bb9df24',
'ext': 'mp4',
'title': 'Arrival',
'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.',
'duration': 9000,
},
}, {
'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1',
'only_matching': True,
}, {
'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1',
'only_matching': True,
def _extract_formats(self, start, element):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(f"{start['servers']['stitcher']}/v2{element['stitched']['path']}?{start['stitcherParams']}&jwt={start['sessionToken']}", element.get('id') or element.get('_id'))
for f in formats:
f['url'] += f"&jwt={start['sessionToken']}"
f.setdefault('vcodec', 'avc1.64001f')
f.setdefault('acodec', 'mp4a.40.2')
f.setdefault('fps', 30)
return formats, subtitles
class PlutoTVIE(PlutoTVBase):
_VALID_URL = r'''(?x)
https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
/(movies|series)
/(?P<slug>[^/]+)
(?:
(?:/seasons?/(?P<season>\d+))?
(?:/episode/(?P<episode>[^/]+))?
)?
/?(?:$|[#?])'''
_TESTS = [{
'url': 'https://pluto.tv/it/on-demand/movies/6246b0adef11000014d220c3',
'md5': '5efe37ad6c1085a4ad4684b9b82cb1c1',
'info_dict': {
'id': '6246b0adef11000014d220c3',
'ext': 'mp4',
'episode_id': '6246b0adef11000014d220c3',
'description': 'md5:c9a412d330d3d73a527e9ba981c0ddb8',
'episode': 'Non Bussate A Quella Porta',
'thumbnail': 'http://images.pluto.tv/episodes/6246b0adef11000014d220c3/poster.jpg?fm=png&q=100',
'display_id': 'dont-knock-twice-it-2016-1-1',
'genres': ['Horror'],
'title': 'Non Bussate A Quella Porta',
'duration': 5940,
},
{
'url': 'https://pluto.tv/en/on-demand/movies/attack-of-the-killer-tomatoes-1977-1-1-ptv1',
'md5': '7db56369c0da626a32d505ec6eb3f89f',
'info_dict': {
'id': '5b190c7bb0875c36c90c29c4',
'ext': 'mp4',
'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,
},
}, {
'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',
},
]
'playlist_mincount': 100,
}, {
'url': 'https://pluto.tv/on-demand/series/66ab6d80b20e79001338fe4c/season/5',
'info_dict': {
'id': '66ab6d80b20e79001338fe4c-5',
'title': 'Squadra Speciale Cobra 11 - Season 5',
},
'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': 'Serie 2, Episodio 5',
'duration': 3120.0,
'season': 'Season 2',
'series': 'Doctor Who',
'description': 'md5:66965714ba60b02996bd1b551475f6fa',
'episode': 'Serie 2, Episodio 5',
},
}]
def _to_ad_free_formats(self, video_id, formats, subtitles):
ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
@ -130,63 +126,60 @@ class PlutoTVIE(InfoExtractor):
self.report_warning('Unable to find ad-free formats')
return formats, subtitles
def _get_video_info(self, video_json, slug, series_name=None):
video_id = video_json.get('_id', slug)
formats, subtitles = [], {}
for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
if video_url.get('type') != 'hls':
continue
url = url_or_none(video_url.get('url'))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
info = {
'id': video_id,
def _get_video_info(self, video_json, video, series=None, season_number=None):
formats, subtitles = self._extract_formats(video_json, video)
thumbnails = [{
'url': cover['url'],
'width': int(m.group(1)) if (m := re.search(r'w=(\d+)&h=(\d+)', cover['url'])) else None,
'height': int(m.group(2)) if m else None,
} for cover in video.get('covers', [])]
first_cover = traverse_obj(video, ('covers', 0, 'url'))
if first_cover:
thumbnails.append({
'id': 'original',
'url': re.sub(r'\?.*$', '?fm=png&q=100', first_cover),
'preference': 1,
})
return {
'id': video.get('id') or video.get('_id'),
'title': video.get('name'),
'display_id': video.get('slug'),
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles,
'title': video_json.get('name'),
'description': video_json.get('description'),
'duration': float_or_none(video_json.get('duration'), scale=1000),
'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.get('_id'),
'season_number': int_or_none(season_number),
}
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
def _season_playlist(self, video_json, series, season_number, season):
for ep in season['episodes']:
yield self._get_video_info(video_json, ep, series, season_number)
def _series_playlist(self, video_json, series):
for season in series['seasons']:
for ep in season['episodes']:
yield self._get_video_info(video_json, ep, series, season['number'])
def _real_extract(self, url):
mobj = self._match_valid_url(url).groupdict()
info_slug = mobj['series_or_movie_slug']
video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS)
if mobj['video_type'] == 'series':
series_name = video_json.get('name', info_slug)
season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug')
videos = []
for season in video_json['seasons']:
if season_number is not None and season_number != int_or_none(season.get('number')):
continue
for episode in season['episodes']:
if episode_slug is not None and episode_slug != episode.get('slug'):
continue
videos.append(self._get_video_info(episode, episode_slug, series_name))
if not videos:
raise ExtractorError('Failed to find any videos to extract')
if episode_slug is not None and len(videos) == 1:
return videos[0]
playlist_title = series_name
if season_number is not None:
playlist_title += ' - Season %d' % season_number
return self.playlist_result(videos,
playlist_id=video_json.get('_id', info_slug),
playlist_title=playlist_title)
return self._get_video_info(video_json, info_slug)
slug = mobj['slug']
season_number, episode_id = mobj.get('season'), mobj.get('episode')
query = {**self._START_QUERY, 'seriesIDs': slug}
if episode_id:
query['episodeIDs'] = episode_id
video_json = self._download_json('https://boot.pluto.tv/v4/start', slug, 'Downloading info json', query=query)
series = video_json['VOD'][0]
if episode_id:
return self._get_video_info(video_json, video_json['VOD'][1], series, season_number)
if season_number:
for season in series['seasons']:
if season['number'] == int(season_number):
return self.playlist_result(self._season_playlist(video_json, series, season_number, season), f"{series['id']}-{season_number}", f"{series['name']} - Season {season_number}")
raise ExtractorError(f'Failed to find season {season_number}')
return self.playlist_result(self._series_playlist(video_json, series), series['id'], series['name'], series.get('description')) if 'seasons' in series else self._get_video_info(video_json, series)