2 from __future__ import unicode_literals
4 from .common import InfoExtractor
11 class RoosterTeethIE(InfoExtractor):
12 _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
13 _LOGIN_URL = 'https://roosterteeth.com/login'
14 _NETRC_MACHINE = 'roosterteeth'
16 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
20 'title': 'Million Dollars, But... The Game Announcement',
21 'thumbnail': 're:^https?://.*\.png$',
22 'description': 'Introducing Million Dollars, But... The Game! Available for pre-order now at www.MDBGame.com ',
23 'creator': 'Rooster Teeth',
24 'series': 'Million Dollars, But...',
25 'episode': 'Million Dollars, But... The Game Announcement',
26 'episode_id': '26576',
29 'skip_download': True, # m3u8 downloads
32 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
33 'only_matching': True,
35 'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
36 'only_matching': True,
38 'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
39 'only_matching': True,
41 'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
42 'only_matching': True,
46 (username, password) = self._get_login_info()
47 if username is None or password is None:
50 # token is required to authenticate request
51 login_page = self._download_webpage(self._LOGIN_URL, None, 'Getting login token', 'Unable to get login token')
53 login_form = self._hidden_inputs(login_page)
58 login_payload = urlencode_postdata(login_form)
60 # required for proper responses
62 'Referer': self._LOGIN_URL,
65 login_request = self._download_webpage(
66 self._LOGIN_URL, None,
67 note='Logging in as %s' % username,
69 headers=login_headers)
71 if 'Authentication failed' in login_request:
73 'Login failed (invalid username/password)', expected=True)
75 def _real_initialize(self):
78 def _real_extract(self, url):
79 match_id = self._match_id(url)
80 webpage = self._download_webpage(url, match_id)
82 episode_id = self._html_search_regex(r"commentControls\('#comment-([0-9]+)'\)", webpage, 'episode id', match_id, False)
84 self.report_extraction(episode_id)
86 title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', self._og_search_title(webpage), False)
87 thumbnail = self._og_search_thumbnail(webpage)
88 description = self._og_search_description(webpage)
89 creator = self._html_search_regex(r'<h3>Latest (.+) Gear</h3>', webpage, 'site', 'Rooster Teeth', False)
90 series = self._html_search_regex(r'<h2>More ([^<]+)</h2>', webpage, 'series', fatal=False)
91 episode = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'episode title', fatal=False)
93 if '<div class="non-sponsor">' in webpage:
94 self.raise_login_required('%s is only available for FIRST members' % title)
96 if '<div class="golive-gate">' in webpage:
97 self.raise_login_required('%s is not available yet' % title)
99 formats = self._extract_m3u8_formats(self._html_search_regex(r"file: '(.+?)m3u8'", webpage, 'm3u8 url') + 'm3u8', episode_id, ext='mp4')
100 self._sort_formats(formats)
106 'thumbnail': thumbnail,
107 'description': description,
111 'episode_id': episode_id,