yt_dlp/extractor/teachable.py

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