yt_dlp/extractor/tubitv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     js_to_json,
  11     sanitized_Request,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class TubiTvIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     (?:
  19                         tubitv:|
  20                         https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/
  21                     )
  22                     (?P<id>[0-9]+)'''
  23     _LOGIN_URL = 'http://tubitv.com/login'
  24     _NETRC_MACHINE = 'tubitv'
  25     _GEO_COUNTRIES = ['US']
  26     _TESTS = [{
  27         'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
  28         'md5': '43ac06be9326f41912dc64ccf7a80320',
  29         'info_dict': {
  30             'id': '283829',
  31             'ext': 'mp4',
  32             'title': 'The Comedian at The Friday',
  33             '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.',
  34             'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
  35         },
  36     }, {
  37         'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://tubitv.com/movies/383676/tracker',
  41         'only_matching': True,
  42     }, {
  43         'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
  44         'info_dict': {
  45             'id': '560057',
  46             'ext': 'mp4',
  47             'title': 'Penitentiary',
  48             'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
  49             'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
  50             'release_year': 1979,
  51         },
  52         'params': {
  53             'skip_download': True,
  54         },
  55     }]
  56
  57     def _login(self):
  58         username, password = self._get_login_info()
  59         if username is None:
  60             return
  61         self.report_login()
  62         form_data = {
  63             'username': username,
  64             'password': password,
  65         }
  66         payload = urlencode_postdata(form_data)
  67         request = sanitized_Request(self._LOGIN_URL, payload)
  68         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  69         login_page = self._download_webpage(
  70             request, None, False, 'Wrong login info')
  71         if not re.search(r'id="tubi-logout"', login_page):
  72             raise ExtractorError(
  73                 'Login failed (invalid username/password)', expected=True)
  74
  75     def _real_initialize(self):
  76         self._login()
  77
  78     def _real_extract(self, url):
  79         video_id = self._match_id(url)
  80         video_data = self._download_json(
  81             'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
  82         title = video_data['title']
  83
  84         formats = []
  85         url = video_data['url']
  86         # URL can be sometimes empty. Does this only happen when there is DRM?
  87         if url:
  88             formats = self._extract_m3u8_formats(
  89                 self._proto_relative_url(url),
  90                 video_id, 'mp4', 'm3u8_native')
  91         self._sort_formats(formats)
  92
  93         thumbnails = []
  94         for thumbnail_url in video_data.get('thumbnails', []):
  95             if not thumbnail_url:
  96                 continue
  97             thumbnails.append({
  98                 'url': self._proto_relative_url(thumbnail_url),
  99             })
 100
 101         subtitles = {}
 102         for sub in video_data.get('subtitles', []):
 103             sub_url = sub.get('url')
 104             if not sub_url:
 105                 continue
 106             subtitles.setdefault(sub.get('lang', 'English'), []).append({
 107                 'url': self._proto_relative_url(sub_url),
 108             })
 109
 110         return {
 111             'id': video_id,
 112             'title': title,
 113             'formats': formats,
 114             'subtitles': subtitles,
 115             'thumbnails': thumbnails,
 116             'description': video_data.get('description'),
 117             'duration': int_or_none(video_data.get('duration')),
 118             'uploader_id': video_data.get('publisher_id'),
 119             'release_year': int_or_none(video_data.get('year')),
 120         }
 121
 122
 123 class TubiTvShowIE(InfoExtractor):
 124     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/series/[0-9]+/(?P<show_name>[^/?#]+)'
 125     _TESTS = [{
 126         'url': 'https://tubitv.com/series/3936/the-joy-of-painting-with-bob-ross?start=true',
 127         'playlist_mincount': 390,
 128         'info_dict': {
 129             'id': 'the-joy-of-painting-with-bob-ross',
 130         }
 131     }]
 132
 133     def _entries(self, show_url, show_name):
 134         show_webpage = self._download_webpage(show_url, show_name)
 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         for episode_id in show_json['fullContentById'].keys():
 139             yield self.url_result(
 140                 'tubitv:%s' % episode_id,
 141                 ie=TubiTvIE.ie_key(), video_id=episode_id)
 142
 143     def _real_extract(self, url):
 144         show_name = self._match_valid_url(url).group('show_name')
 145         return self.playlist_result(self._entries(url, show_name), playlist_id=show_name)