1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from .wistia
import WistiaIE
7 from ..compat
import compat_str
17 class TeachableBaseIE(InfoExtractor
):
18 _NETRC_MACHINE
= 'teachable'
19 _URL_PREFIX
= 'teachable:'
22 # Only notable ones here
23 'upskillcourses.com': 'upskill',
24 'academy.gns3.com': 'gns3',
25 'academyhacker.com': 'academyhacker',
26 'stackskills.com': 'stackskills',
27 'market.saleshacker.com': 'saleshacker',
28 'learnability.org': 'learnability',
29 'edurila.com': 'edurila',
32 _VALID_URL_SUB_TUPLE
= (_URL_PREFIX
, '|'.join(re
.escape(site
) for site
in _SITES
.keys()))
34 def _real_initialize(self
):
35 self
._logged
_in
= False
37 def _login(self
, site
):
41 username
, password
= self
._get
_login
_info
(
42 netrc_machine
=self
._SITES
.get(site
, site
))
46 login_page
, urlh
= self
._download
_webpage
_handle
(
47 'https://%s/sign_in' % site
, None,
48 'Downloading %s login page' % site
)
50 login_url
= compat_str(urlh
.geturl())
52 login_form
= self
._hidden
_inputs
(login_page
)
55 'user[email]': username
,
56 'user[password]': password
,
59 post_url
= self
._search
_regex
(
60 r
'<form[^>]+action=(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1', login_page,
61 'post url
', default=login_url, group='url
')
63 if not post_url.startswith('http
'):
64 post_url = urljoin(login_url, post_url)
66 response = self._download_webpage(
67 post_url, None, 'Logging
in to
%s' % site,
68 data=urlencode_postdata(login_form),
70 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
',
74 if '>I accept the new Privacy Policy
<' in response:
76 'Unable to login
: %s asks you to accept new Privacy Policy
. '
77 'Go to https
://%s/ and accept
.' % (site, site), expected=True)
80 if any(re.search(p, response) for p in (
81 r'class=["\']user-signout',
82 r'<a[^>]+\bhref=["\']/sign_out
',
84 self._logged_in = True
87 message = get_element_by_class('alert
', response)
88 if message is not None:
90 'Unable to login
: %s' % clean_html(message), expected=True)
92 raise ExtractorError('Unable to log
in')
95 class TeachableIE(TeachableBaseIE):
98 %shttps?://(?P<site_t>[^/]+)|
99 https?://(?:www\.)?(?P<site>%s)
101 /courses/[^/]+/lectures/(?P<id>\d+)
102 ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
105 'url
': 'http
://upskillcourses
.com
/courses
/essential
-web
-developer
-course
/lectures
/1747100',
109 'title
': 'Welcome to the Course
!',
110 'description
': 'md5
:65edb0affa582974de4625b9cdea1107
',
112 'timestamp
': 1479846621,
113 'upload_date
': '20161122',
116 'skip_download
': True,
119 'url
': 'http
://upskillcourses
.com
/courses
/119763/lectures
/1747100',
120 'only_matching
': True,
122 'url
': 'https
://academy
.gns3
.com
/courses
/423415/lectures
/6885939',
123 'only_matching
': True,
125 'url
': 'teachable
:https
://upskillcourses
.com
/courses
/essential
-web
-developer
-course
/lectures
/1747100',
126 'only_matching
': True,
130 def _is_teachable(webpage):
131 return 'teachableTracker
.linker
:autoLink
' in webpage and re.search(
132 r'<link
[^
>]+href
=["\']https?://process\.fs\.teachablecdn\.com',
136 def _extract_url(webpage, source_url):
137 if not TeachableIE._is_teachable(webpage):
139 if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
140 return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
142 def _real_extract(self, url):
143 mobj = re.match(self._VALID_URL, url)
144 site = mobj.group('site') or mobj.group('site_t')
145 video_id = mobj.group('id')
149 prefixed = url.startswith(self._URL_PREFIX)
151 url = url[len(self._URL_PREFIX):]
153 webpage = self._download_webpage(url, video_id)
155 wistia_url = WistiaIE._extract_url(webpage)
157 if any(re.search(p, webpage) for p in (
158 r'class=["\']lecture
-contents
-locked
',
159 r'>\s
*Lecture contents locked
',
160 r'id=["\']lecture-locked')):
161 self.raise_login_required('Lecture contents locked')
163 title = self._og_search_title(webpage, default=None)
166 '_type': 'url_transparent',
168 'ie_key': WistiaIE.ie_key(),
173 class TeachableCourseIE(TeachableBaseIE):
174 _VALID_URL = r'''(?x)
176 %shttps?://(?P<site_t>[^/]+)|
177 https?://(?:www\.)?(?P<site>%s)
179 /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
180 ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
182 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
184 'id': 'essential-web-developer-course',
185 'title': 'The Essential Web Developer Course (Free)',
187 'playlist_count': 192,
189 'url': 'http://upskillcourses.com/courses/119763/',
190 'only_matching': True,
192 'url': 'http://upskillcourses.com/courses/enrolled/119763',
193 'only_matching': True,
195 'url': 'https://academy.gns3.com/courses/enrolled/423415',
196 'only_matching': True,
198 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
199 'only_matching': True,
201 'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
202 'only_matching': True,
206 def suitable(cls, url):
207 return False if TeachableIE.suitable(url) else super(
208 TeachableCourseIE, cls).suitable(url)
210 def _real_extract(self, url):
211 mobj = re.match(self._VALID_URL, url)
212 site = mobj.group('site') or mobj.group('site_t')
213 course_id = mobj.group('id')
217 prefixed = url.startswith(self._URL_PREFIX)
219 prefix = self._URL_PREFIX
220 url = url[len(prefix):]
222 webpage = self._download_webpage(url, course_id)
224 url_base = 'https://%s/' % site
228 for mobj in re.finditer(
229 r'(?s)(?P<li><li[^>]+class=(["\'])(?
:(?
!\
2).)*?section
-item
[^
>]+>.+?
</li
>)',
231 li = mobj.group('li
')
232 if 'fa
-youtube
-play
' not in li:
234 lecture_url = self._search_regex(
235 r'<a
[^
>]+href
=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
236 'lecture url', default=None, group='url')
239 lecture_id = self._search_regex(
240 r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
241 title = self._html_search_regex(
242 r'<span[^>]+class=["\']lecture
-name
[^
>]+>([^
<]+)', li,
243 'title
', default=None)
244 entry_url = urljoin(url_base, lecture_url)
246 entry_url = self._URL_PREFIX + entry_url
250 ie=TeachableIE.ie_key(), video_id=lecture_id,
251 video_title=clean_html(title)))
253 course_title = self._html_search_regex(
254 (r'(?s
)<img
[^
>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
255 r'(?s)<h\d[^>]+class=["\']course
-title
[^
>]+>(.+?
)</h
'),
256 webpage, 'course title
', fatal=False)
258 return self.playlist_result(entries, course_id, course_title)