Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/roosterteeth.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_HTTPError,
   7     compat_str,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     int_or_none,
  12     str_or_none,
  13     urlencode_postdata,
  14 )
  15
  16
  17 class RoosterTeethIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)'
  19     _NETRC_MACHINE = 'roosterteeth'
  20     _TESTS = [{
  21         'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  22         'md5': 'e2bd7764732d785ef797700a2489f212',
  23         'info_dict': {
  24             'id': '9156',
  25             'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  26             'ext': 'mp4',
  27             'title': 'Million Dollars, But... The Game Announcement',
  28             'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
  29             'thumbnail': r're:^https?://.*\.png$',
  30             'series': 'Million Dollars, But...',
  31             'episode': 'Million Dollars, But... The Game Announcement',
  32         },
  33     }, {
  34         'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
  44         'only_matching': True,
  45     }, {
  46         # only available for FIRST members
  47         'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
  48         'only_matching': True,
  49     }, {
  50         'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  51         'only_matching': True,
  52     }]
  53     _EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/'
  54
  55     def _login(self):
  56         username, password = self._get_login_info()
  57         if username is None:
  58             return
  59
  60         try:
  61             self._download_json(
  62                 'https://auth.roosterteeth.com/oauth/token',
  63                 None, 'Logging in', data=urlencode_postdata({
  64                     'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5',
  65                     'grant_type': 'password',
  66                     'username': username,
  67                     'password': password,
  68                 }))
  69         except ExtractorError as e:
  70             msg = 'Unable to login'
  71             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
  72                 resp = self._parse_json(e.cause.read().decode(), None, fatal=False)
  73                 if resp:
  74                     error = resp.get('extra_info') or resp.get('error_description') or resp.get('error')
  75                     if error:
  76                         msg += ': ' + error
  77             self.report_warning(msg)
  78
  79     def _real_initialize(self):
  80         if self._get_cookies(self._EPISODE_BASE_URL).get('rt_access_token'):
  81             return
  82         self._login()
  83
  84     def _real_extract(self, url):
  85         display_id = self._match_id(url)
  86         api_episode_url = self._EPISODE_BASE_URL + display_id
  87
  88         try:
  89             m3u8_url = self._download_json(
  90                 api_episode_url + '/videos', display_id,
  91                 'Downloading video JSON metadata')['data'][0]['attributes']['url']
  92         except ExtractorError as e:
  93             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
  94                 if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
  95                     self.raise_login_required(
  96                         '%s is only available for FIRST members' % display_id)
  97             raise
  98
  99         formats = self._extract_m3u8_formats(
 100             m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
 101         self._sort_formats(formats)
 102
 103         episode = self._download_json(
 104             api_episode_url, display_id,
 105             'Downloading episode JSON metadata')['data'][0]
 106         attributes = episode['attributes']
 107         title = attributes.get('title') or attributes['display_title']
 108         video_id = compat_str(episode['id'])
 109
 110         thumbnails = []
 111         for image in episode.get('included', {}).get('images', []):
 112             if image.get('type') == 'episode_image':
 113                 img_attributes = image.get('attributes') or {}
 114                 for k in ('thumb', 'small', 'medium', 'large'):
 115                     img_url = img_attributes.get(k)
 116                     if img_url:
 117                         thumbnails.append({
 118                             'id': k,
 119                             'url': img_url,
 120                         })
 121
 122         return {
 123             'id': video_id,
 124             'display_id': display_id,
 125             'title': title,
 126             'description': attributes.get('description') or attributes.get('caption'),
 127             'thumbnails': thumbnails,
 128             'series': attributes.get('show_title'),
 129             'season_number': int_or_none(attributes.get('season_number')),
 130             'season_id': attributes.get('season_id'),
 131             'episode': title,
 132             'episode_number': int_or_none(attributes.get('number')),
 133             'episode_id': str_or_none(episode.get('uuid')),
 134             'formats': formats,
 135             'channel_id': attributes.get('channel_id'),
 136             'duration': int_or_none(attributes.get('length')),
 137         }