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 )
  11
  12
  13 class TubiTvIE(InfoExtractor):
  14     _VALID_URL = r'''(?x)
  15                     (?:
  16                         tubitv:|
  17                         https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/
  18                     )
  19                     (?P<id>[0-9]+)'''
  20     _LOGIN_URL = 'http://tubitv.com/login'
  21     _NETRC_MACHINE = 'tubitv'
  22     _GEO_COUNTRIES = ['US']
  23     _TESTS = [{
  24         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  25         'md5': '43ac06be9326f41912dc64ccf7a80320',
  26         'info_dict': {
  27             'id': '283829',
  28             'ext': 'mp4',
  29             'title': 'The Comedian at The Friday',
  30             '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.',
  31             'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  32         },
  33     }, {
  34         'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://tubitv.com/movies/383676/tracker',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
  41         'info_dict': {
  42             'id': '560057',
  43             'ext': 'mp4',
  44             'title': 'Penitentiary',
  45             'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
  46             'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
  47             'release_year': 1979,
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52     }]
  53
  54     def _perform_login(self, username, password):
  55         self.report_login()
  56         form_data = {
  57             'username': username,
  58             'password': password,
  59         }
  60         payload = urlencode_postdata(form_data)
  61         request = sanitized_Request(self._LOGIN_URL, payload)
  62         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  63         login_page = self._download_webpage(
  64             request, None, False, 'Wrong login info')
  65         if not re.search(r'id="tubi-logout"', login_page):
  66             raise ExtractorError(
  67                 'Login failed (invalid username/password)', expected=True)
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71         video_data = self._download_json(
  72             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  73         title = video_data['title']
  74
  75         formats = []
  76         url = video_data['url']
  77         # URL can be sometimes empty. Does this only happen when there is DRM?
  78         if url:
  79             formats = self._extract_m3u8_formats(
  80                 self._proto_relative_url(url),
  81                 video_id, 'mp4', 'm3u8_native')
  82         self._sort_formats(formats)
  83
  84         thumbnails = []
  85         for thumbnail_url in video_data.get('thumbnails', []):
  86             if not thumbnail_url:
  87                 continue
  88             thumbnails.append({
  89                 'url': self._proto_relative_url(thumbnail_url),
  90             })
  91
  92         subtitles = {}
  93         for sub in video_data.get('subtitles', []):
  94             sub_url = sub.get('url')
  95             if not sub_url:
  96                 continue
  97             subtitles.setdefault(sub.get('lang', 'English'), []).append({
  98                 'url': self._proto_relative_url(sub_url),
  99             })
 100
 101         season_number, episode_number, episode_title = self._search_regex(
 102             r'^S(\d+):E(\d+) - (.+)', title, 'episode info', fatal=False, group=(1, 2, 3), default=(None, None, None))
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'formats': formats,
 108             'subtitles': subtitles,
 109             'thumbnails': thumbnails,
 110             'description': video_data.get('description'),
 111             'duration': int_or_none(video_data.get('duration')),
 112             'uploader_id': video_data.get('publisher_id'),
 113             'release_year': int_or_none(video_data.get('year')),
 114             'season_number': int_or_none(season_number),
 115             'episode_number': int_or_none(episode_number),
 116             'episode_title': episode_title
 117         }
 118
 119
 120 class TubiTvShowIE(InfoExtractor):
 121     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
 122     _TESTS = [{
 123         'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
 124         'playlist_mincount': 390,
 125         'info_dict': {
 126             'id': 'the-joy-of-painting-with-bob-ross',
 127         }
 128     }]
 129
 130     def _entries(self, show_url, show_name):
 131         show_webpage = self._download_webpage(show_url, show_name)
 132
 133         show_json = self._parse_json(self._search_regex(
 134             r'window\.__data\s*=\s*({[^<]+});\s*</script>',
 135             show_webpage, 'data'), show_name, transform_source=js_to_json)['video']
 136
 137         for episode_id in show_json['fullContentById'].keys():
 138             yield self.url_result(
 139                 'tubitv:%s' % episode_id,
 140                 ie=TubiTvIE.ie_key(), video_id=episode_id)
 141
 142     def _real_extract(self, url):
 143         show_name = self._match_valid_url(url).group('show_name')
 144         return self.playlist_result(self._entries(url, show_name), playlist_id=show_name)