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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .wistia import WistiaIE
from ..utils import (
clean_html,
ExtractorError,
int_or_none,
get_element_by_class,
strip_or_none,
urlencode_postdata,
urljoin,
)
class TeachableBaseIE(InfoExtractor):
_NETRC_MACHINE = 'teachable'
_URL_PREFIX = 'teachable:'
_SITES = {
# Only notable ones here
'v1.upskillcourses.com': 'upskill',
'gns3.teachable.com': 'gns3',
'academyhacker.com': 'academyhacker',
'stackskills.com': 'stackskills',
'market.saleshacker.com': 'saleshacker',
'learnability.org': 'learnability',
'edurila.com': 'edurila',
'courses.workitdaily.com': 'workitdaily',
}
_VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
def _real_initialize(self):
self._logged_in = False
def _login(self, site):
if self._logged_in:
return
username, password = self._get_login_info(
netrc_machine=self._SITES.get(site, site))
if username is None:
return
login_page, urlh = self._download_webpage_handle(
'https://%s/sign_in' % site, None,
'Downloading %s login page' % site)
def is_logged(webpage):
return any(re.search(p, webpage) for p in (
r'class=["\']user-signout',
r'<a[^>]+\bhref=["\']/sign_out',
r'Log\s+[Oo]ut\s*<'))
if is_logged(login_page):
self._logged_in = True
return
login_url = urlh.geturl()
login_form = self._hidden_inputs(login_page)
login_form.update({
'user[email]': username,
'user[password]': password,
})
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
'post url', default=login_url, group='url')
if not post_url.startswith('http'):
post_url = urljoin(login_url, post_url)
response = self._download_webpage(
post_url, None, 'Logging in to %s' % site,
data=urlencode_postdata(login_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': login_url,
})
if '>I accept the new Privacy Policy<' in response:
raise ExtractorError(
'Unable to login: %s asks you to accept new Privacy Policy. '
'Go to https://%s/ and accept.' % (site, site), expected=True)
# Successful login
if is_logged(response):
self._logged_in = True
return
message = get_element_by_class('alert', response)
if message is not None:
raise ExtractorError(
'Unable to login: %s' % clean_html(message), expected=True)
raise ExtractorError('Unable to log in')
class TeachableIE(TeachableBaseIE):
_VALID_URL = r'''(?x)
(?:
%shttps?://(?P<site_t>[^/]+)|
https?://(?:www\.)?(?P<site>%s)
)
/courses/[^/]+/lectures/(?P<id>\d+)
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
_TESTS = [{
'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
'info_dict': {
'id': 'uzw6zw58or',
'ext': 'mp4',
'title': 'Welcome to the Course!',
'description': 'md5:65edb0affa582974de4625b9cdea1107',
'duration': 138.763,
'timestamp': 1479846621,
'upload_date': '20161122',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
'only_matching': True,
}, {
'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
'only_matching': True,
}, {
'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
'only_matching': True,
}]
@staticmethod
def _is_teachable(webpage):
return 'teachableTracker.linker:autoLink' in webpage and re.search(
r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
webpage)
@staticmethod
def _extract_url(webpage, source_url):
if not TeachableIE._is_teachable(webpage):
return
if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site = mobj.group('site') or mobj.group('site_t')
video_id = mobj.group('id')
self._login(site)
prefixed = url.startswith(self._URL_PREFIX)
if prefixed:
url = url[len(self._URL_PREFIX):]
webpage = self._download_webpage(url, video_id)
wistia_urls = WistiaIE._extract_urls(webpage)
if not wistia_urls:
if any(re.search(p, webpage) for p in (
r'class=["\']lecture-contents-locked',
r'>\s*Lecture contents locked',
r'id=["\']lecture-locked',
# https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
r'class=["\'](?:inner-)?lesson-locked',
r'>LESSON LOCKED<')):
self.raise_login_required('Lecture contents locked')
raise ExtractorError('Unable to find video URL')
title = self._og_search_title(webpage, default=None)
chapter = None
chapter_number = None
section_item = self._search_regex(
r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
webpage, 'section item', default=None, group='li')
if section_item:
chapter_number = int_or_none(self._search_regex(
r'data-ss-position=["\'](\d+)', section_item, 'section id',
default=None))
if chapter_number is not None:
sections = []
for s in re.findall(
r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
section = strip_or_none(clean_html(s))
if not section:
sections = []
break
sections.append(section)
if chapter_number <= len(sections):
chapter = sections[chapter_number - 1]
entries = [{
'_type': 'url_transparent',
'url': wistia_url,
'ie_key': WistiaIE.ie_key(),
'title': title,
'chapter': chapter,
'chapter_number': chapter_number,
} for wistia_url in wistia_urls]
return self.playlist_result(entries, video_id, title)
class TeachableCourseIE(TeachableBaseIE):
_VALID_URL = r'''(?x)
(?:
%shttps?://(?P<site_t>[^/]+)|
https?://(?:www\.)?(?P<site>%s)
)
/(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
_TESTS = [{
'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
'info_dict': {
'id': 'essential-web-developer-course',
'title': 'The Essential Web Developer Course (Free)',
},
'playlist_count': 192,
}, {
'url': 'http://v1.upskillcourses.com/courses/119763/',
'only_matching': True,
}, {
'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
'only_matching': True,
}, {
'url': 'https://gns3.teachable.com/courses/enrolled/423415',
'only_matching': True,
}, {
'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
'only_matching': True,
}, {
'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if TeachableIE.suitable(url) else super(
TeachableCourseIE, cls).suitable(url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site = mobj.group('site') or mobj.group('site_t')
course_id = mobj.group('id')
self._login(site)
prefixed = url.startswith(self._URL_PREFIX)
if prefixed:
prefix = self._URL_PREFIX
url = url[len(prefix):]
webpage = self._download_webpage(url, course_id)
url_base = 'https://%s/' % site
entries = []
for mobj in re.finditer(
r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
webpage):
li = mobj.group('li')
if 'fa-youtube-play' not in li:
continue
lecture_url = self._search_regex(
r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
'lecture url', default=None, group='url')
if not lecture_url:
continue
lecture_id = self._search_regex(
r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
title = self._html_search_regex(
r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
'title', default=None)
entry_url = urljoin(url_base, lecture_url)
if prefixed:
entry_url = self._URL_PREFIX + entry_url
entries.append(
self.url_result(
entry_url,
ie=TeachableIE.ie_key(), video_id=lecture_id,
video_title=clean_html(title)))
course_title = self._html_search_regex(
(r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
webpage, 'course title', fatal=False)
return self.playlist_result(entries, course_id, course_title)
|
