1# coding: utf-8 2from .common import InfoExtractor 3from ..compat import compat_HTTPError 4from ..utils import ( 5 ExtractorError, 6 int_or_none, 7 join_nonempty, 8 LazyList, 9 parse_qs, 10 str_or_none, 11 traverse_obj, 12 url_or_none, 13 urlencode_postdata, 14 urljoin, 15 update_url_query, 16) 17 18 19class RoosterTeethBaseIE(InfoExtractor): 20 _NETRC_MACHINE = 'roosterteeth' 21 _API_BASE = 'https://svod-be.roosterteeth.com' 22 _API_BASE_URL = f'{_API_BASE}/api/v1' 23 24 def _login(self): 25 username, password = self._get_login_info() 26 if username is None: 27 return 28 if self._get_cookies(self._API_BASE_URL).get('rt_access_token'): 29 return 30 31 try: 32 self._download_json( 33 'https://auth.roosterteeth.com/oauth/token', 34 None, 'Logging in', data=urlencode_postdata({ 35 'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5', 36 'grant_type': 'password', 37 'username': username, 38 'password': password, 39 })) 40 except ExtractorError as e: 41 msg = 'Unable to login' 42 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: 43 resp = self._parse_json(e.cause.read().decode(), None, fatal=False) 44 if resp: 45 error = resp.get('extra_info') or resp.get('error_description') or resp.get('error') 46 if error: 47 msg += ': ' + error 48 self.report_warning(msg) 49 50 def _real_initialize(self): 51 self._login() 52 53 def _extract_video_info(self, data): 54 thumbnails = [] 55 for image in traverse_obj(data, ('included', 'images')): 56 if image.get('type') not in ('episode_image', 'bonus_feature_image'): 57 continue 58 thumbnails.extend([{ 59 'id': name, 60 'url': url, 61 } for name, url in (image.get('attributes') or {}).items() if url_or_none(url)]) 62 63 attributes = data.get('attributes') or {} 64 title = traverse_obj(attributes, 'title', 'display_title') 65 sub_only = attributes.get('is_sponsors_only') 66 67 return { 68 'id': str(data.get('id')), 69 'display_id': attributes.get('slug'), 70 'title': title, 71 'description': traverse_obj(attributes, 'description', 'caption'), 72 'series': attributes.get('show_title'), 73 'season_number': int_or_none(attributes.get('season_number')), 74 'season_id': attributes.get('season_id'), 75 'episode': title, 76 'episode_number': int_or_none(attributes.get('number')), 77 'episode_id': str_or_none(data.get('uuid')), 78 'channel_id': attributes.get('channel_id'), 79 'duration': int_or_none(attributes.get('length')), 80 'thumbnails': thumbnails, 81 'availability': self._availability( 82 needs_premium=sub_only, needs_subscription=sub_only, needs_auth=sub_only, 83 is_private=False, is_unlisted=False), 84 'tags': attributes.get('genres') 85 } 86 87 88class RoosterTeethIE(RoosterTeethBaseIE): 89 _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)' 90 _TESTS = [{ 91 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement', 92 'info_dict': { 93 'id': '9156', 94 'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement', 95 'ext': 'mp4', 96 'title': 'Million Dollars, But... The Game Announcement', 97 'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5', 98 'thumbnail': r're:^https?://.*\.png$', 99 'series': 'Million Dollars, But...', 100 'episode': 'Million Dollars, But... The Game Announcement', 101 }, 102 'params': {'skip_download': True}, 103 }, { 104 'url': 'https://roosterteeth.com/watch/rwby-bonus-25', 105 'info_dict': { 106 'id': '40432', 107 'display_id': 'rwby-bonus-25', 108 'title': 'Grimm', 109 'description': 'md5:f30ff570741213418a8d2c19868b93ab', 110 'episode': 'Grimm', 111 'channel_id': '92f780eb-ebfe-4bf5-a3b5-c6ad5460a5f1', 112 'thumbnail': r're:^https?://.*\.(png|jpe?g)$', 113 'ext': 'mp4', 114 }, 115 'params': {'skip_download': True}, 116 }, { 117 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31', 118 'only_matching': True, 119 }, { 120 'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts', 121 'only_matching': True, 122 }, { 123 'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow', 124 'only_matching': True, 125 }, { 126 'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better', 127 'only_matching': True, 128 }, { 129 # only available for FIRST members 130 'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one', 131 'only_matching': True, 132 }, { 133 'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement', 134 'only_matching': True, 135 }] 136 137 def _real_extract(self, url): 138 display_id = self._match_id(url) 139 api_episode_url = f'{self._API_BASE_URL}/watch/{display_id}' 140 141 try: 142 video_data = self._download_json( 143 api_episode_url + '/videos', display_id, 144 'Downloading video JSON metadata')['data'][0] 145 m3u8_url = video_data['attributes']['url'] 146 # XXX: additional URL at video_data['links']['download'] 147 except ExtractorError as e: 148 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: 149 if self._parse_json(e.cause.read().decode(), display_id).get('access') is False: 150 self.raise_login_required( 151 '%s is only available for FIRST members' % display_id) 152 raise 153 154 formats, subtitles = self._extract_m3u8_formats_and_subtitles( 155 m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls') 156 self._sort_formats(formats) 157 158 episode = self._download_json( 159 api_episode_url, display_id, 160 'Downloading episode JSON metadata')['data'][0] 161 162 return { 163 'display_id': display_id, 164 'formats': formats, 165 'subtitles': subtitles, 166 **self._extract_video_info(episode) 167 } 168 169 170class RoosterTeethSeriesIE(RoosterTeethBaseIE): 171 _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/series/(?P<id>[^/?#&]+)' 172 _TESTS = [{ 173 'url': 'https://roosterteeth.com/series/rwby?season=7', 174 'playlist_count': 13, 175 'info_dict': { 176 'id': 'rwby-7', 177 'title': 'RWBY - Season 7', 178 } 179 }, { 180 'url': 'https://roosterteeth.com/series/role-initiative', 181 'playlist_mincount': 16, 182 'info_dict': { 183 'id': 'role-initiative', 184 'title': 'Role Initiative', 185 } 186 }, { 187 'url': 'https://roosterteeth.com/series/let-s-play-minecraft?season=9', 188 'playlist_mincount': 50, 189 'info_dict': { 190 'id': 'let-s-play-minecraft-9', 191 'title': 'Let\'s Play Minecraft - Season 9', 192 } 193 }] 194 195 def _entries(self, series_id, season_number): 196 display_id = join_nonempty(series_id, season_number) 197 # TODO: extract bonus material 198 for data in self._download_json( 199 f'{self._API_BASE_URL}/shows/{series_id}/seasons?order=asc&order_by', display_id)['data']: 200 idx = traverse_obj(data, ('attributes', 'number')) 201 if season_number and idx != season_number: 202 continue 203 season_url = update_url_query(urljoin(self._API_BASE, data['links']['episodes']), {'per_page': 1000}) 204 season = self._download_json(season_url, display_id, f'Downloading season {idx} JSON metadata')['data'] 205 for episode in season: 206 yield self.url_result( 207 f'https://www.roosterteeth.com{episode["canonical_links"]["self"]}', 208 RoosterTeethIE.ie_key(), 209 **self._extract_video_info(episode)) 210 211 def _real_extract(self, url): 212 series_id = self._match_id(url) 213 season_number = traverse_obj(parse_qs(url), ('season', 0), expected_type=int_or_none) 214 215 entries = LazyList(self._entries(series_id, season_number)) 216 return self.playlist_result( 217 entries, 218 join_nonempty(series_id, season_number), 219 join_nonempty(entries[0].get('series'), season_number, delim=' - Season ')) 220