yt_dlp/extractor/plutotv.py

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