2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
16 class RoosterTeethIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
18 _LOGIN_URL
= 'https://roosterteeth.com/login'
19 _NETRC_MACHINE
= 'roosterteeth'
21 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
22 'md5': 'e2bd7764732d785ef797700a2489f212',
25 'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
27 'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
28 'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
29 'thumbnail': r
're:^https?://.*\.png$',
30 'series': 'Million Dollars, But...',
31 'episode': 'Million Dollars, But... The Game Announcement',
35 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
36 'only_matching': True,
38 'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
39 'only_matching': True,
41 'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
42 'only_matching': True,
44 'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
45 'only_matching': True,
47 # only available for FIRST members
48 'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
49 'only_matching': True,
53 username
, password
= self
._get
_login
_info
()
57 login_page
= self
._download
_webpage
(
58 self
._LOGIN
_URL
, None,
59 note
='Downloading login page',
60 errnote
='Unable to download login page')
62 login_form
= self
._hidden
_inputs
(login_page
)
69 login_request
= self
._download
_webpage
(
70 self
._LOGIN
_URL
, None,
72 data
=urlencode_postdata(login_form
),
74 'Referer': self
._LOGIN
_URL
,
77 if not any(re
.search(p
, login_request
) for p
in (
78 r
'href=["\']https?
://(?
:www\
.)?roosterteeth\
.com
/logout
"',
80 error = self._html_search_regex(
81 r'(?s)<div[^>]+class=(["\']).*?
\balert
-danger
\b.*?\
1[^
>]*>(?
:\s
*<button
[^
>]*>.*?
</button
>)?
(?P
<error
>.+?
)</div
>',
82 login_request, 'alert
', default=None, group='error
')
84 raise ExtractorError('Unable to login
: %s' % error, expected=True)
85 raise ExtractorError('Unable to log
in')
87 def _real_initialize(self):
90 def _real_extract(self, url):
91 display_id = self._match_id(url)
93 webpage = self._download_webpage(url, display_id)
95 episode = strip_or_none(unescapeHTML(self._search_regex(
96 (r'videoTitle\s
*=\s
*(["\'])(?P<title>(?:(?!\1).)+)\1',
97 r'<title>(?P<title>[^<]+)</title>'), webpage, 'title',
98 default=None, group='title')))
100 title = strip_or_none(self._og_search_title(
101 webpage, default=None)) or episode
103 m3u8_url = self._search_regex(
104 r'file\s*:\s*(["\'])(?P
<url
>http
.+?\
.m3u8
.*?
)\
1',
105 webpage, 'm3u8 url
', default=None, group='url
')
108 if re.search(r'<div
[^
>]+class=["\']non-sponsor', webpage):
109 self.raise_login_required(
110 '%s is only available for FIRST members' % display_id)
112 if re.search(r'<div[^>]+class=["\']golive
-gate
', webpage):
113 self.raise_login_required('%s is not available yet
' % display_id)
115 raise ExtractorError('Unable to extract m3u8 URL
')
117 formats = self._extract_m3u8_formats(
118 m3u8_url, display_id, ext='mp4
',
119 entry_protocol='m3u8_native
', m3u8_id='hls
')
120 self._sort_formats(formats)
122 description = strip_or_none(self._og_search_description(webpage))
123 thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
125 series = self._search_regex(
126 (r'<h2
>More ([^
<]+)</h2
>', r'<a
[^
>]+>See
All ([^
<]+) Videos
<'),
127 webpage, 'series
', fatal=False)
129 comment_count = int_or_none(self._search_regex(
130 r'>Comments \
((\d
+)\
)<', webpage,
131 'comment count
', fatal=False))
133 video_id = self._search_regex(
134 (r'containerId\s
*=\s
*["\']episode-(\d+)\1',
135 r'<div[^<]+id=["\']episode
-(\d
+)'), webpage,
136 'video
id', default=display_id)
140 'display_id
': display_id,
142 'description
': description,
143 'thumbnail
': thumbnail,
146 'comment_count
': comment_count,