yt_dlp/extractor/plutotv.py

   1 import re
   2 import urllib.parse
   3 import uuid
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     float_or_none,
   9     int_or_none,
  10     try_get,
  11     url_or_none,
  12 )
  13
  14
  15 class PlutoTVIE(InfoExtractor):
  16     _WORKING = False
  17     _VALID_URL = r'''(?x)
  18         https?://(?:www\.)?pluto\.tv(?:/[^/]+)?/on-demand
  19         /(?P<video_type>movies|series)
  20         /(?P<series_or_movie_slug>[^/]+)
  21         (?:
  22             (?:/seasons?/(?P<season_no>\d+))?
  23             (?:/episode/(?P<episode_slug>[^/]+))?
  24         )?
  25         /?(?:$|[#?])'''
  26
  27     _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
  28     _INFO_QUERY_PARAMS = {
  29         'appName': 'web',
  30         'appVersion': 'na',
  31         'clientID': str(uuid.uuid1()),
  32         'clientModelNumber': 'na',
  33         'serverSideAds': 'false',
  34         'deviceMake': 'unknown',
  35         'deviceModel': 'web',
  36         'deviceType': 'web',
  37         'deviceVersion': 'unknown',
  38         'sid': str(uuid.uuid1()),
  39     }
  40     _TESTS = [
  41         {
  42             'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
  43             'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
  44             'info_dict': {
  45                 'id': '5de6c598e9379ae4912df0a8',
  46                 'ext': 'mp4',
  47                 'title': 'It\'s In The Cards',
  48                 'episode': 'It\'s In The Cards',
  49                 '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.',
  50                 'series': 'I Love Money',
  51                 'season_number': 2,
  52                 'episode_number': 3,
  53                 'duration': 3600,
  54             },
  55         }, {
  56             'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
  57             'playlist_count': 11,
  58             'info_dict': {
  59                 'id': '5de6c582e9379ae4912dedbd',
  60                 'title': 'I Love Money - Season 1',
  61             },
  62         }, {
  63             'url': 'https://pluto.tv/on-demand/series/i-love-money/',
  64             'playlist_count': 26,
  65             'info_dict': {
  66                 'id': '5de6c582e9379ae4912dedbd',
  67                 'title': 'I Love Money',
  68             },
  69         }, {
  70             'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
  71             'md5': '3cead001d317a018bf856a896dee1762',
  72             'info_dict': {
  73                 'id': '5e83ac701fa6a9001bb9df24',
  74                 'ext': 'mp4',
  75                 'title': 'Arrival',
  76                 '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.',
  77                 'duration': 9000,
  78             },
  79         }, {
  80             'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1',
  81             'only_matching': True,
  82         }, {
  83             'url': 'https://pluto.tv/it/on-demand/series/csi-vegas/episode/legacy-2021-1-1',
  84             'only_matching': True,
  85         },
  86         {
  87             'url': 'https://pluto.tv/en/on-demand/movies/attack-of-the-killer-tomatoes-1977-1-1-ptv1',
  88             'md5': '7db56369c0da626a32d505ec6eb3f89f',
  89             'info_dict': {
  90                 'id': '5b190c7bb0875c36c90c29c4',
  91                 'ext': 'mp4',
  92                 'title': 'Attack of the Killer Tomatoes',
  93                 'description': 'A group of scientists band together to save the world from mutated tomatoes that KILL! (1978)',
  94                 'duration': 5700,
  95             },
  96         },
  97     ]
  98
  99     def _to_ad_free_formats(self, video_id, formats, subtitles):
 100         ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
 101         for fmt in formats:
 102             res = self._download_webpage(
 103                 fmt.get('url'), video_id, note='Downloading m3u8 playlist',
 104                 fatal=False)
 105             if not res:
 106                 continue
 107             first_segment_url = re.search(
 108                 r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res,
 109                 re.MULTILINE)
 110             if first_segment_url:
 111                 m3u8_urls.add(
 112                     urllib.parse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
 113                 continue
 114             first_segment_url = re.search(
 115                 r'^(https?://.*/).+\-0+[0-1]0\.ts$', res,
 116                 re.MULTILINE)
 117             if first_segment_url:
 118                 m3u8_urls.add(
 119                     urllib.parse.urljoin(first_segment_url.group(1), 'master.m3u8'))
 120                 continue
 121
 122         for m3u8_url in m3u8_urls:
 123             fmts, subs = self._extract_m3u8_formats_and_subtitles(
 124                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 125             ad_free_formats.extend(fmts)
 126             ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs)
 127         if ad_free_formats:
 128             formats, subtitles = ad_free_formats, ad_free_subtitles
 129         else:
 130             self.report_warning('Unable to find ad-free formats')
 131         return formats, subtitles
 132
 133     def _get_video_info(self, video_json, slug, series_name=None):
 134         video_id = video_json.get('_id', slug)
 135         formats, subtitles = [], {}
 136         for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
 137             if video_url.get('type') != 'hls':
 138                 continue
 139             url = url_or_none(video_url.get('url'))
 140
 141             fmts, subs = self._extract_m3u8_formats_and_subtitles(
 142                 url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 143             formats.extend(fmts)
 144             subtitles = self._merge_subtitles(subtitles, subs)
 145
 146         formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
 147
 148         info = {
 149             'id': video_id,
 150             'formats': formats,
 151             'subtitles': subtitles,
 152             'title': video_json.get('name'),
 153             'description': video_json.get('description'),
 154             'duration': float_or_none(video_json.get('duration'), scale=1000),
 155         }
 156         if series_name:
 157             info.update({
 158                 'series': series_name,
 159                 'episode': video_json.get('name'),
 160                 'season_number': int_or_none(video_json.get('season')),
 161                 'episode_number': int_or_none(video_json.get('number')),
 162             })
 163         return info
 164
 165     def _real_extract(self, url):
 166         mobj = self._match_valid_url(url).groupdict()
 167         info_slug = mobj['series_or_movie_slug']
 168         video_json = self._download_json(self._INFO_URL + info_slug, info_slug, query=self._INFO_QUERY_PARAMS)
 169
 170         if mobj['video_type'] == 'series':
 171             series_name = video_json.get('name', info_slug)
 172             season_number, episode_slug = mobj.get('season_number'), mobj.get('episode_slug')
 173
 174             videos = []
 175             for season in video_json['seasons']:
 176                 if season_number is not None and season_number != int_or_none(season.get('number')):
 177                     continue
 178                 for episode in season['episodes']:
 179                     if episode_slug is not None and episode_slug != episode.get('slug'):
 180                         continue
 181                     videos.append(self._get_video_info(episode, episode_slug, series_name))
 182             if not videos:
 183                 raise ExtractorError('Failed to find any videos to extract')
 184             if episode_slug is not None and len(videos) == 1:
 185                 return videos[0]
 186             playlist_title = series_name
 187             if season_number is not None:
 188                 playlist_title += ' - Season %d' % season_number
 189             return self.playlist_result(videos,
 190                                         playlist_id=video_json.get('_id', info_slug),
 191                                         playlist_title=playlist_title)
 192         return self._get_video_info(video_json, info_slug)