X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Froosterteeth.py;h=8883639b290b9712eb94ef05ab41ecaff7b06ee3;hb=adc13b0748784db87faef580929b1adadaff732e;hp=4053747d3a994ccbea5165b7746775ebe5b97e60;hpb=3121b25639a06cc9cad48fad0ce222482a58b216;p=youtube-dl diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py index 4053747d3..8883639b2 100644 --- a/youtube_dl/extractor/roosterteeth.py +++ b/youtube_dl/extractor/roosterteeth.py @@ -2,31 +2,33 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( ExtractorError, + int_or_none, + str_or_none, urlencode_postdata, ) class RoosterTeethIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P[^/?#&]+)' - _LOGIN_URL = 'https://roosterteeth.com/login' + _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P[^/?#&]+)' _NETRC_MACHINE = 'roosterteeth' _TESTS = [{ 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement', + 'md5': 'e2bd7764732d785ef797700a2489f212', 'info_dict': { - 'id': '26576', + 'id': '9156', + 'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement', 'ext': 'mp4', 'title': 'Million Dollars, But... The Game Announcement', - 'thumbnail': 're:^https?://.*\.png$', - 'description': 'Introducing Million Dollars, But... The Game! Available for pre-order now at www.MDBGame.com ', - 'creator': 'Rooster Teeth', + 'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5', + 'thumbnail': r're:^https?://.*\.png$', 'series': 'Million Dollars, But...', 'episode': 'Million Dollars, But... The Game Announcement', - 'episode_id': '26576', - }, - 'params': { - 'skip_download': True, # m3u8 downloads }, }, { 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31', @@ -40,73 +42,96 @@ class RoosterTeethIE(InfoExtractor): }, { 'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better', 'only_matching': True, + }, { + # only available for FIRST members + 'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one', + 'only_matching': True, + }, { + 'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement', + 'only_matching': True, }] + _EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/' def _login(self): - (username, password) = self._get_login_info() - if username is None or password is None: - return False - - # token is required to authenticate request - login_page = self._download_webpage(self._LOGIN_URL, None, 'Getting login token', 'Unable to get login token') - - login_form = self._hidden_inputs(login_page) - login_form.update({ - 'username': username, - 'password': password, - }) - login_payload = urlencode_postdata(login_form) - - # required for proper responses - login_headers = { - 'Referer': self._LOGIN_URL, - } - - login_request = self._download_webpage( - self._LOGIN_URL, None, - note='Logging in as %s' % username, - data=login_payload, - headers=login_headers) - - if 'Authentication failed' in login_request: - raise ExtractorError( - 'Login failed (invalid username/password)', expected=True) + username, password = self._get_login_info() + if username is None: + return + + try: + self._download_json( + 'https://auth.roosterteeth.com/oauth/token', + None, 'Logging in', data=urlencode_postdata({ + 'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5', + 'grant_type': 'password', + 'username': username, + 'password': password, + })) + except ExtractorError as e: + msg = 'Unable to login' + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + resp = self._parse_json(e.cause.read().decode(), None, fatal=False) + if resp: + error = resp.get('extra_info') or resp.get('error_description') or resp.get('error') + if error: + msg += ': ' + error + self.report_warning(msg) def _real_initialize(self): + if self._get_cookies(self._EPISODE_BASE_URL).get('rt_access_token'): + return self._login() def _real_extract(self, url): - match_id = self._match_id(url) - webpage = self._download_webpage(url, match_id) - - episode_id = self._html_search_regex(r"commentControls\('#comment-([0-9]+)'\)", webpage, 'episode id', match_id, False) - - self.report_extraction(episode_id) - - title = self._html_search_regex(r'([^<]+)', webpage, 'episode title', self._og_search_title(webpage), False) - thumbnail = self._og_search_thumbnail(webpage) - description = self._og_search_description(webpage) - creator = self._html_search_regex(r'

Latest (.+) Gear

', webpage, 'site', 'Rooster Teeth', False) - series = self._html_search_regex(r'

More ([^<]+)

', webpage, 'series', fatal=False) - episode = self._html_search_regex(r'([^<]+)', webpage, 'episode title', fatal=False) - - if '
' in webpage: - self.raise_login_required('%s is only available for FIRST members' % title) - - if '
' in webpage: - self.raise_login_required('%s is not available yet' % title) - - formats = self._extract_m3u8_formats(self._html_search_regex(r"file: '(.+?)m3u8'", webpage, 'm3u8 url') + 'm3u8', episode_id, ext='mp4') + display_id = self._match_id(url) + api_episode_url = self._EPISODE_BASE_URL + display_id + + try: + m3u8_url = self._download_json( + api_episode_url + '/videos', display_id, + 'Downloading video JSON metadata')['data'][0]['attributes']['url'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if self._parse_json(e.cause.read().decode(), display_id).get('access') is False: + self.raise_login_required( + '%s is only available for FIRST members' % display_id) + raise + + formats = self._extract_m3u8_formats( + m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls') self._sort_formats(formats) + episode = self._download_json( + api_episode_url, display_id, + 'Downloading episode JSON metadata')['data'][0] + attributes = episode['attributes'] + title = attributes.get('title') or attributes['display_title'] + video_id = compat_str(episode['id']) + + thumbnails = [] + for image in episode.get('included', {}).get('images', []): + if image.get('type') == 'episode_image': + img_attributes = image.get('attributes') or {} + for k in ('thumb', 'small', 'medium', 'large'): + img_url = img_attributes.get(k) + if img_url: + thumbnails.append({ + 'id': k, + 'url': img_url, + }) + return { - 'id': episode_id, + 'id': video_id, + 'display_id': display_id, 'title': title, + 'description': attributes.get('description') or attributes.get('caption'), + 'thumbnails': thumbnails, + 'series': attributes.get('show_title'), + 'season_number': int_or_none(attributes.get('season_number')), + 'season_id': attributes.get('season_id'), + 'episode': title, + 'episode_number': int_or_none(attributes.get('number')), + 'episode_id': str_or_none(episode.get('uuid')), 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, - 'creator': creator, - 'series': series, - 'episode': episode, - 'episode_id': episode_id, + 'channel_id': attributes.get('channel_id'), + 'duration': int_or_none(attributes.get('length')), }