]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/teachable.py
[ChangeLog] Actualize
[youtube-dl.git] / youtube_dl / extractor / teachable.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from .wistia import WistiaIE
7 from ..utils import (
8     clean_html,
9     ExtractorError,
10     int_or_none,
11     get_element_by_class,
12     strip_or_none,
13     urlencode_postdata,
14     urljoin,
15 )
16
17
18 class TeachableBaseIE(InfoExtractor):
19     _NETRC_MACHINE = 'teachable'
20     _URL_PREFIX = 'teachable:'
21
22     _SITES = {
23         # Only notable ones here
24         'v1.upskillcourses.com': 'upskill',
25         'gns3.teachable.com': 'gns3',
26         'academyhacker.com': 'academyhacker',
27         'stackskills.com': 'stackskills',
28         'market.saleshacker.com': 'saleshacker',
29         'learnability.org': 'learnability',
30         'edurila.com': 'edurila',
31         'courses.workitdaily.com': 'workitdaily',
32     }
33
34     _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
35
36     def _real_initialize(self):
37         self._logged_in = False
38
39     def _login(self, site):
40         if self._logged_in:
41             return
42
43         username, password = self._get_login_info(
44             netrc_machine=self._SITES.get(site, site))
45         if username is None:
46             return
47
48         login_page, urlh = self._download_webpage_handle(
49             'https://%s/sign_in' % site, None,
50             'Downloading %s login page' % site)
51
52         def is_logged(webpage):
53             return any(re.search(p, webpage) for p in (
54                 r'class=["\']user-signout',
55                 r'<a[^>]+\bhref=["\']/sign_out',
56                 r'Log\s+[Oo]ut\s*<'))
57
58         if is_logged(login_page):
59             self._logged_in = True
60             return
61
62         login_url = urlh.geturl()
63
64         login_form = self._hidden_inputs(login_page)
65
66         login_form.update({
67             'user[email]': username,
68             'user[password]': password,
69         })
70
71         post_url = self._search_regex(
72             r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
73             'post url', default=login_url, group='url')
74
75         if not post_url.startswith('http'):
76             post_url = urljoin(login_url, post_url)
77
78         response = self._download_webpage(
79             post_url, None, 'Logging in to %s' % site,
80             data=urlencode_postdata(login_form),
81             headers={
82                 'Content-Type': 'application/x-www-form-urlencoded',
83                 'Referer': login_url,
84             })
85
86         if '>I accept the new Privacy Policy<' in response:
87             raise ExtractorError(
88                 'Unable to login: %s asks you to accept new Privacy Policy. '
89                 'Go to https://%s/ and accept.' % (site, site), expected=True)
90
91         # Successful login
92         if is_logged(response):
93             self._logged_in = True
94             return
95
96         message = get_element_by_class('alert', response)
97         if message is not None:
98             raise ExtractorError(
99                 'Unable to login: %s' % clean_html(message), expected=True)
100
101         raise ExtractorError('Unable to log in')
102
103
104 class TeachableIE(TeachableBaseIE):
105     _VALID_URL = r'''(?x)
106                     (?:
107                         %shttps?://(?P<site_t>[^/]+)|
108                         https?://(?:www\.)?(?P<site>%s)
109                     )
110                     /courses/[^/]+/lectures/(?P<id>\d+)
111                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
112
113     _TESTS = [{
114         'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364',
115         'info_dict': {
116             'id': 'untlgzk1v7',
117             'ext': 'bin',
118             'title': 'Overview',
119             'description': 'md5:071463ff08b86c208811130ea1c2464c',
120             'duration': 736.4,
121             'timestamp': 1542315762,
122             'upload_date': '20181115',
123             'chapter': 'Welcome',
124             'chapter_number': 1,
125         },
126         'params': {
127             'skip_download': True,
128         },
129     }, {
130         'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100',
131         'only_matching': True,
132     }, {
133         'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939',
134         'only_matching': True,
135     }, {
136         'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
137         'only_matching': True,
138     }]
139
140     @staticmethod
141     def _is_teachable(webpage):
142         return 'teachableTracker.linker:autoLink' in webpage and re.search(
143             r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
144             webpage)
145
146     @staticmethod
147     def _extract_url(webpage, source_url):
148         if not TeachableIE._is_teachable(webpage):
149             return
150         if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
151             return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
152
153     def _real_extract(self, url):
154         mobj = re.match(self._VALID_URL, url)
155         site = mobj.group('site') or mobj.group('site_t')
156         video_id = mobj.group('id')
157
158         self._login(site)
159
160         prefixed = url.startswith(self._URL_PREFIX)
161         if prefixed:
162             url = url[len(self._URL_PREFIX):]
163
164         webpage = self._download_webpage(url, video_id)
165
166         wistia_urls = WistiaIE._extract_urls(webpage)
167         if not wistia_urls:
168             if any(re.search(p, webpage) for p in (
169                     r'class=["\']lecture-contents-locked',
170                     r'>\s*Lecture contents locked',
171                     r'id=["\']lecture-locked',
172                     # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
173                     r'class=["\'](?:inner-)?lesson-locked',
174                     r'>LESSON LOCKED<')):
175                 self.raise_login_required('Lecture contents locked')
176             raise ExtractorError('Unable to find video URL')
177
178         title = self._og_search_title(webpage, default=None)
179
180         chapter = None
181         chapter_number = None
182         section_item = self._search_regex(
183             r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id,
184             webpage, 'section item', default=None, group='li')
185         if section_item:
186             chapter_number = int_or_none(self._search_regex(
187                 r'data-ss-position=["\'](\d+)', section_item, 'section id',
188                 default=None))
189             if chapter_number is not None:
190                 sections = []
191                 for s in re.findall(
192                         r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage):
193                     section = strip_or_none(clean_html(s))
194                     if not section:
195                         sections = []
196                         break
197                     sections.append(section)
198                 if chapter_number <= len(sections):
199                     chapter = sections[chapter_number - 1]
200
201         entries = [{
202             '_type': 'url_transparent',
203             'url': wistia_url,
204             'ie_key': WistiaIE.ie_key(),
205             'title': title,
206             'chapter': chapter,
207             'chapter_number': chapter_number,
208         } for wistia_url in wistia_urls]
209
210         return self.playlist_result(entries, video_id, title)
211
212
213 class TeachableCourseIE(TeachableBaseIE):
214     _VALID_URL = r'''(?x)
215                         (?:
216                             %shttps?://(?P<site_t>[^/]+)|
217                             https?://(?:www\.)?(?P<site>%s)
218                         )
219                         /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
220                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
221     _TESTS = [{
222         'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/',
223         'info_dict': {
224             'id': 'essential-web-developer-course',
225             'title': 'The Essential Web Developer Course (Free)',
226         },
227         'playlist_count': 192,
228     }, {
229         'url': 'http://v1.upskillcourses.com/courses/119763/',
230         'only_matching': True,
231     }, {
232         'url': 'http://v1.upskillcourses.com/courses/enrolled/119763',
233         'only_matching': True,
234     }, {
235         'url': 'https://gns3.teachable.com/courses/enrolled/423415',
236         'only_matching': True,
237     }, {
238         'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
239         'only_matching': True,
240     }, {
241         'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
242         'only_matching': True,
243     }]
244
245     @classmethod
246     def suitable(cls, url):
247         return False if TeachableIE.suitable(url) else super(
248             TeachableCourseIE, cls).suitable(url)
249
250     def _real_extract(self, url):
251         mobj = re.match(self._VALID_URL, url)
252         site = mobj.group('site') or mobj.group('site_t')
253         course_id = mobj.group('id')
254
255         self._login(site)
256
257         prefixed = url.startswith(self._URL_PREFIX)
258         if prefixed:
259             prefix = self._URL_PREFIX
260             url = url[len(prefix):]
261
262         webpage = self._download_webpage(url, course_id)
263
264         url_base = 'https://%s/' % site
265
266         entries = []
267
268         for mobj in re.finditer(
269                 r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
270                 webpage):
271             li = mobj.group('li')
272             if 'fa-youtube-play' not in li:
273                 continue
274             lecture_url = self._search_regex(
275                 r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
276                 'lecture url', default=None, group='url')
277             if not lecture_url:
278                 continue
279             lecture_id = self._search_regex(
280                 r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
281             title = self._html_search_regex(
282                 r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
283                 'title', default=None)
284             entry_url = urljoin(url_base, lecture_url)
285             if prefixed:
286                 entry_url = self._URL_PREFIX + entry_url
287             entries.append(
288                 self.url_result(
289                     entry_url,
290                     ie=TeachableIE.ie_key(), video_id=lecture_id,
291                     video_title=clean_html(title)))
292
293         course_title = self._html_search_regex(
294             (r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
295              r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
296             webpage, 'course title', fatal=False)
297
298         return self.playlist_result(entries, course_id, course_title)