_ Git - youtube-dl/blob - youtube_dl/extractor/roosterteeth.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_HTTPError,
   9     compat_str,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14     str_or_none,
  15     urlencode_postdata,
  16 )
  17
  18
  19 class RoosterTeethIE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)'
  21     _LOGIN_URL = 'https://roosterteeth.com/login'
  22     _NETRC_MACHINE = 'roosterteeth'
  23     _TESTS = [{
  24         'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  25         'md5': 'e2bd7764732d785ef797700a2489f212',
  26         'info_dict': {
  27             'id': '9156',
  28             'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  29             'ext': 'mp4',
  30             'title': 'Million Dollars, But... The Game Announcement',
  31             'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
  32             'thumbnail': r're:^https?://.*\.png$',
  33             'series': 'Million Dollars, But...',
  34             'episode': 'Million Dollars, But... The Game Announcement',
  35         },
  36     }, {
  37         'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
  47         'only_matching': True,
  48     }, {
  49         # only available for FIRST members
  50         'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
  54         'only_matching': True,
  55     }]
  56
  57     def _login(self):
  58         username, password = self._get_login_info()
  59         if username is None:
  60             return
  61
  62         login_page = self._download_webpage(
  63             self._LOGIN_URL, None,
  64             note='Downloading login page',
  65             errnote='Unable to download login page')
  66
  67         login_form = self._hidden_inputs(login_page)
  68
  69         login_form.update({
  70             'username': username,
  71             'password': password,
  72         })
  73
  74         login_request = self._download_webpage(
  75             self._LOGIN_URL, None,
  76             note='Logging in',
  77             data=urlencode_postdata(login_form),
  78             headers={
  79                 'Referer': self._LOGIN_URL,
  80             })
  81
  82         if not any(re.search(p, login_request) for p in (
  83                 r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"',
  84                 r'>Sign Out<')):
  85             error = self._html_search_regex(
  86                 r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>',
  87                 login_request, 'alert', default=None, group='error')
  88             if error:
  89                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  90             raise ExtractorError('Unable to log in')
  91
  92     def _real_initialize(self):
  93         self._login()
  94
  95     def _real_extract(self, url):
  96         display_id = self._match_id(url)
  97         api_episode_url = 'https://svod-be.roosterteeth.com/api/v1/episodes/%s' % display_id
  98
  99         try:
 100             m3u8_url = self._download_json(
 101                 api_episode_url + '/videos', display_id,
 102                 'Downloading video JSON metadata')['data'][0]['attributes']['url']
 103         except ExtractorError as e:
 104             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 105                 if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
 106                     self.raise_login_required(
 107                         '%s is only available for FIRST members' % display_id)
 108             raise
 109
 110         formats = self._extract_m3u8_formats(
 111             m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
 112         self._sort_formats(formats)
 113
 114         episode = self._download_json(
 115             api_episode_url, display_id,
 116             'Downloading episode JSON metadata')['data'][0]
 117         attributes = episode['attributes']
 118         title = attributes.get('title') or attributes['display_title']
 119         video_id = compat_str(episode['id'])
 120
 121         thumbnails = []
 122         for image in episode.get('included', {}).get('images', []):
 123             if image.get('type') == 'episode_image':
 124                 img_attributes = image.get('attributes') or {}
 125                 for k in ('thumb', 'small', 'medium', 'large'):
 126                     img_url = img_attributes.get(k)
 127                     if img_url:
 128                         thumbnails.append({
 129                             'id': k,
 130                             'url': img_url,
 131                         })
 132
 133         return {
 134             'id': video_id,
 135             'display_id': display_id,
 136             'title': title,
 137             'description': attributes.get('description') or attributes.get('caption'),
 138             'thumbnails': thumbnails,
 139             'series': attributes.get('show_title'),
 140             'season_number': int_or_none(attributes.get('season_number')),
 141             'season_id': attributes.get('season_id'),
 142             'episode': title,
 143             'episode_number': int_or_none(attributes.get('number')),
 144             'episode_id': str_or_none(episode.get('uuid')),
 145             'formats': formats,
 146             'channel_id': attributes.get('channel_id'),
 147             'duration': int_or_none(attributes.get('length')),
 148         }