yt_dlp/extractor/tubitv.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     js_to_json,
   8     sanitized_Request,
   9     urlencode_postdata,
  10     traverse_obj,
  11 )
  12
  13
  14 class TubiTvIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     (?:
  17                         tubitv:|
  18                         https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/
  19                     )
  20                     (?P<id>[0-9]+)'''
  21     _LOGIN_URL = 'http://tubitv.com/login'
  22     _NETRC_MACHINE = 'tubitv'
  23     _GEO_COUNTRIES = ['US']
  24     _TESTS = [{
  25         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  26         'md5': '43ac06be9326f41912dc64ccf7a80320',
  27         'info_dict': {
  28             'id': '283829',
  29             'ext': 'mp4',
  30             'title': 'The Comedian at The Friday',
  31             'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.',
  32             'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  33         },
  34     }, {
  35         'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://tubitv.com/movies/383676/tracker',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
  42         'info_dict': {
  43             'id': '560057',
  44             'ext': 'mp4',
  45             'title': 'Penitentiary',
  46             'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
  47             'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
  48             'release_year': 1979,
  49         },
  50         'params': {
  51             'skip_download': True,
  52         },
  53     }]
  54
  55     def _perform_login(self, username, password):
  56         self.report_login()
  57         form_data = {
  58             'username': username,
  59             'password': password,
  60         }
  61         payload = urlencode_postdata(form_data)
  62         request = sanitized_Request(self._LOGIN_URL, payload)
  63         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  64         login_page = self._download_webpage(
  65             request, None, False, 'Wrong login info')
  66         if not re.search(r'id="tubi-logout"', login_page):
  67             raise ExtractorError(
  68                 'Login failed (invalid username/password)', expected=True)
  69
  70     def _real_extract(self, url):
  71         video_id = self._match_id(url)
  72         video_data = self._download_json(
  73             'https://tubitv.com/oz/videos/%s/content?video_resources=dash&video_resources=hlsv3&video_resources=hlsv6' % video_id, video_id)
  74         title = video_data['title']
  75
  76         formats = []
  77
  78         for resource in video_data['video_resources']:
  79             if resource['type'] in ('dash', ):
  80                 formats += self._extract_mpd_formats(resource['manifest']['url'], video_id, mpd_id=resource['type'], fatal=False)
  81             elif resource['type'] in ('hlsv3', 'hlsv6'):
  82                 formats += self._extract_m3u8_formats(resource['manifest']['url'], video_id, 'mp4', m3u8_id=resource['type'], fatal=False)
  83
  84         self._sort_formats(formats)
  85
  86         thumbnails = []
  87         for thumbnail_url in video_data.get('thumbnails', []):
  88             if not thumbnail_url:
  89                 continue
  90             thumbnails.append({
  91                 'url': self._proto_relative_url(thumbnail_url),
  92             })
  93
  94         subtitles = {}
  95         for sub in video_data.get('subtitles', []):
  96             sub_url = sub.get('url')
  97             if not sub_url:
  98                 continue
  99             subtitles.setdefault(sub.get('lang', 'English'), []).append({
 100                 'url': self._proto_relative_url(sub_url),
 101             })
 102
 103         season_number, episode_number, episode_title = self._search_regex(
 104             r'^S(\d+):E(\d+) - (.+)', title, 'episode info', fatal=False, group=(1, 2, 3), default=(None, None, None))
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'formats': formats,
 110             'subtitles': subtitles,
 111             'thumbnails': thumbnails,
 112             'description': video_data.get('description'),
 113             'duration': int_or_none(video_data.get('duration')),
 114             'uploader_id': video_data.get('publisher_id'),
 115             'release_year': int_or_none(video_data.get('year')),
 116             'season_number': int_or_none(season_number),
 117             'episode_number': int_or_none(episode_number),
 118             'episode_title': episode_title
 119         }
 120
 121
 122 class TubiTvShowIE(InfoExtractor):
 123     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
 124     _TESTS = [{
 125         'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
 126         'playlist_mincount': 390,
 127         'info_dict': {
 128             'id': 'the-joy-of-painting-with-bob-ross',
 129         }
 130     }]
 131
 132     def _entries(self, show_url, show_name):
 133         show_webpage = self._download_webpage(show_url, show_name)
 134
 135         show_json = self._parse_json(self._search_regex(
 136             r'window\.__data\s*=\s*({[^<]+});\s*</script>',
 137             show_webpage, 'data'), show_name, transform_source=js_to_json)['video']
 138
 139         for episode_id in show_json['fullContentById'].keys():
 140             if traverse_obj(show_json, ('byId', episode_id, 'type')) == 's':
 141                 continue
 142             yield self.url_result(
 143                 'tubitv:%s' % episode_id,
 144                 ie=TubiTvIE.ie_key(), video_id=episode_id)
 145
 146     def _real_extract(self, url):
 147         show_name = self._match_valid_url(url).group('show_name')
 148         return self.playlist_result(self._entries(url, show_name), playlist_id=show_name)