1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
24 class LinuxAcademyIE(InfoExtractor
):
27 (?:www\.)?linuxacademy\.com/cp/
29 courses/lesson/course/(?P<chapter_id>\d+)/lesson/(?P<lesson_id>\d+)|
30 modules/view/id/(?P<course_id>\d+)
34 'url': 'https://linuxacademy.com/cp/courses/lesson/course/7971/lesson/2/module/675',
38 'title': 'What Is Data Science',
39 'description': 'md5:c574a3c20607144fb36cb65bdde76c99',
40 'timestamp': int, # The timestamp and upload date changes
41 'upload_date': r
're:\d+',
45 'skip_download': True,
47 'skip': 'Requires Linux Academy account credentials',
49 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2',
50 'only_matching': True,
52 'url': 'https://linuxacademy.com/cp/modules/view/id/154',
55 'title': 'AWS Certified Cloud Practitioner',
56 'description': 'md5:a68a299ca9bb98d41cca5abc4d4ce22c',
60 'skip': 'Requires Linux Academy account credentials',
62 'url': 'https://linuxacademy.com/cp/modules/view/id/39',
65 'title': 'Red Hat Certified Systems Administrator - RHCSA (EX200) Exam Prep (legacy)',
66 'description': 'md5:0f1d3369e90c3fb14a79813b863c902f',
70 'skip': 'Requires Linux Academy account credentials',
73 _AUTHORIZE_URL
= 'https://login.linuxacademy.com/authorize'
74 _ORIGIN_URL
= 'https://linuxacademy.com'
75 _CLIENT_ID
= 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx'
76 _NETRC_MACHINE
= 'linuxacademy'
78 def _perform_login(self
, username
, password
):
81 random
.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~')
84 webpage
, urlh
= self
._download
_webpage
_handle
(
85 self
._AUTHORIZE
_URL
, None, 'Downloading authorize page', query
={
86 'client_id': self
._CLIENT
_ID
,
87 'response_type': 'token id_token',
88 'response_mode': 'web_message',
89 'redirect_uri': self
._ORIGIN
_URL
,
90 'scope': 'openid email user_impersonation profile',
91 'audience': self
._ORIGIN
_URL
,
92 'state': random_string(),
93 'nonce': random_string(),
96 login_data
= self
._parse
_json
(
98 r
'atob\(\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1', webpage,
99 'login info
', group='value
'), None,
100 transform_source=lambda x: compat_b64decode(x).decode('utf
-8')
104 'client_id
': self._CLIENT_ID,
105 'redirect_uri
': self._ORIGIN_URL,
106 'tenant
': 'lacausers
',
107 'connection
': 'Username
-Password
-ACG
-Proxy
',
108 'username
': username,
109 'password
': password,
113 login_state_url = urlh.geturl()
116 login_page = self._download_webpage(
117 'https
://login
.linuxacademy
.com
/usernamepassword
/login
', None,
118 'Downloading login page
', data=json.dumps(login_data).encode(),
120 'Content
-Type
': 'application
/json
',
121 'Origin
': 'https
://login
.linuxacademy
.com
',
122 'Referer
': login_state_url,
124 except ExtractorError as e:
125 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
126 error = self._parse_json(e.cause.read(), None)
127 message = error.get('description
') or error['code
']
128 raise ExtractorError(
129 '%s said
: %s' % (self.IE_NAME, message), expected=True)
132 callback_page, urlh = self._download_webpage_handle(
133 'https
://login
.linuxacademy
.com
/login
/callback
', None,
134 'Downloading callback page
',
135 data=urlencode_postdata(self._hidden_inputs(login_page)),
137 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
138 'Origin
': 'https
://login
.linuxacademy
.com
',
139 'Referer
': login_state_url,
142 access_token = self._search_regex(
143 r'access_token
=([^
=&]+)', urlh.geturl(),
144 'access token
', default=None)
146 access_token = self._parse_json(
148 r'authorizationResponse\s
*=\s
*({.+?}
)\s
*;', callback_page,
149 'authorization response
'), None,
150 transform_source=js_to_json)['response
']['access_token
']
152 self._download_webpage(
153 'https
://linuxacademy
.com
/cp
/login
/tokenValidateLogin
/token
/%s'
154 % access_token, None, 'Downloading token validation page
')
156 def _real_extract(self, url):
157 mobj = self._match_valid_url(url)
158 chapter_id, lecture_id, course_id = mobj.group('chapter_id
', 'lesson_id
', 'course_id
')
159 item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id)
161 webpage = self._download_webpage(url, item_id)
165 module = self._parse_json(
167 r'window\
.module\s
*=\s
*({(?:(?!}
;)[^
"]|"([^
"]|\\")*")+})\s*;', webpage, 'module'),
170 chapter_number = None
173 for item in module['items']:
174 if not isinstance(item, dict):
178 return (try_get(item, lambda x: x['type'][key], compat_str) or '').lower()
179 type_fields = (type_field('name'), type_field('slug'))
180 # Move to next module section
181 if 'section' in type_fields:
182 chapter = item.get('course_name')
183 chapter_id = item.get('course_module')
184 chapter_number = 1 if not chapter_number else chapter_number + 1
187 if 'lesson' not in type_fields:
189 lesson_url = urljoin(url, item.get('url'))
192 title = item.get('title') or item.get('lesson_name')
193 description = item.get('md_desc') or clean_html(item.get('description')) or clean_html(item.get('text'))
195 '_type': 'url_transparent',
197 'ie_key': LinuxAcademyIE.ie_key(),
199 'description': description,
200 'timestamp': unified_timestamp(item.get('date')) or unified_timestamp(item.get('created_on')),
201 'duration': parse_duration(item.get('duration')),
203 'chapter_id': chapter_id,
204 'chapter_number': chapter_number,
210 'title': module.get('title'),
211 'description': module.get('md_desc') or clean_html(module.get('desc')),
212 'duration': parse_duration(module.get('duration')),
216 m3u8_url = self._parse_json(
218 r'player\.playlist\s*=\s*(\[.+?\])\s*;', webpage, 'playlist'),
220 formats = self._extract_m3u8_formats(
221 m3u8_url, item_id, 'mp4', entry_protocol='m3u8_native',
223 self._sort_formats(formats)
228 lesson = self._parse_json(
230 (r'window\.lesson\s*=\s*({.+?})\s*;',
231 r'player\.lesson\s*=\s*({.+?})\s*;'),
232 webpage, 'lesson', default='{}'), item_id, fatal=False)
235 'title': lesson.get('lesson_name'),
236 'description': lesson.get('md_desc') or clean_html(lesson.get('desc')),
237 'timestamp': unified_timestamp(lesson.get('date')) or unified_timestamp(lesson.get('created_on')),
238 'duration': parse_duration(lesson.get('duration')),
240 if not info.get('title'):
241 info['title'] = self._search_regex(
242 (r'>Lecture\s*:\s*(?P<value>[^<]+)',
243 r'lessonName\s*=\s*(["\'])(?P
<value
>(?
:(?
!\
1).)+)\
1'), webpage,
244 'title
', group='value
')