1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
|
# coding: utf-8
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|watch)/(?P<id>[^/?#&]+)'
_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': '9156',
'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
'ext': 'mp4',
'title': 'Million Dollars, But... The Game Announcement',
'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
'thumbnail': r're:^https?://.*\.png$',
'series': 'Million Dollars, But...',
'episode': 'Million Dollars, But... The Game Announcement',
},
}, {
'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
'only_matching': True,
}, {
'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
'only_matching': True,
}, {
'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
'only_matching': True,
}, {
'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:
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):
display_id = self._match_id(url)
api_episode_url = self._EPISODE_BASE_URL + display_id
try:
video_data = self._download_json(
api_episode_url + '/videos', display_id,
'Downloading video JSON metadata')['data'][0]
m3u8_url = video_data['attributes']['url']
subtitle_m3u8_url = video_data['links']['download']
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,
})
subtitles = {}
res = self._download_webpage_handle(
subtitle_m3u8_url, display_id,
'Downloading m3u8 information',
'Failed to download m3u8 information',
fatal=True, data=None, headers={}, query={})
if res is not False:
subtitle_m3u8_doc, _ = res
for line in subtitle_m3u8_doc.split('\n'):
if 'EXT-X-MEDIA:TYPE=SUBTITLES' in line:
parts = line.split(',')
for part in parts:
if 'LANGUAGE' in part:
lang = part[part.index('=') + 2:-1]
elif 'URI' in part:
uri = part[part.index('=') + 2:-1]
res = self._download_webpage_handle(
uri, display_id,
'Downloading m3u8 information',
'Failed to download m3u8 information',
fatal=True, data=None, headers={}, query={})
doc, _ = res
for l in doc.split('\n'):
if not l.startswith('#'):
subtitles[lang] = [{'url': uri[:-uri[::-1].index('/')] + l}]
break
return {
'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,
'channel_id': attributes.get('channel_id'),
'duration': int_or_none(attributes.get('length')),
'subtitles': subtitles
}
|
