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     get_element_by_class,
  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         'upskillcourses.com': 'upskill',
  23         'academy.gns3.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.keys()))
  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(
  42             netrc_machine=self._SITES.get(site, site))
  43         if username is None:
  44             return
  45
  46         login_page, urlh = self._download_webpage_handle(
  47             'https://%s/sign_in' % site, None,
  48             'Downloading %s login page' % site)
  49
  50         def is_logged(webpage):
  51             return any(re.search(p, webpage) for p in (
  52                 r'class=["\']user-signout',
  53                 r'<a[^>]+\bhref=["\']/sign_out',
  54                 r'Log\s+[Oo]ut\s*<'))
  55
  56         if is_logged(login_page):
  57             self._logged_in = True
  58             return
  59
  60         login_url = urlh.geturl()
  61
  62         login_form = self._hidden_inputs(login_page)
  63
  64         login_form.update({
  65             'user[email]': username,
  66             'user[password]': password,
  67         })
  68
  69         post_url = self._search_regex(
  70             r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
  71             'post url', default=login_url, group='url')
  72
  73         if not post_url.startswith('http'):
  74             post_url = urljoin(login_url, post_url)
  75
  76         response = self._download_webpage(
  77             post_url, None, 'Logging in to %s' % site,
  78             data=urlencode_postdata(login_form),
  79             headers={
  80                 'Content-Type': 'application/x-www-form-urlencoded',
  81                 'Referer': login_url,
  82             })
  83
  84         if '>I accept the new Privacy Policy<' in response:
  85             raise ExtractorError(
  86                 'Unable to login: %s asks you to accept new Privacy Policy. '
  87                 'Go to https://%s/ and accept.' % (site, site), expected=True)
  88
  89         # Successful login
  90         if is_logged(response):
  91             self._logged_in = True
  92             return
  93
  94         message = get_element_by_class('alert', response)
  95         if message is not None:
  96             raise ExtractorError(
  97                 'Unable to login: %s' % clean_html(message), expected=True)
  98
  99         raise ExtractorError('Unable to log in')
 100
 101
 102 class TeachableIE(TeachableBaseIE):
 103     _VALID_URL = r'''(?x)
 104                     (?:
 105                         %shttps?://(?P<site_t>[^/]+)|
 106                         https?://(?:www\.)?(?P<site>%s)
 107                     )
 108                     /courses/[^/]+/lectures/(?P<id>\d+)
 109                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 110
 111     _TESTS = [{
 112         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
 113         'info_dict': {
 114             'id': 'uzw6zw58or',
 115             'ext': 'mp4',
 116             'title': 'Welcome to the Course!',
 117             'description': 'md5:65edb0affa582974de4625b9cdea1107',
 118             'duration': 138.763,
 119             'timestamp': 1479846621,
 120             'upload_date': '20161122',
 121         },
 122         'params': {
 123             'skip_download': True,
 124         },
 125     }, {
 126         'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
 127         'only_matching': True,
 128     }, {
 129         'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
 130         'only_matching': True,
 131     }, {
 132         'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
 133         'only_matching': True,
 134     }]
 135
 136     @staticmethod
 137     def _is_teachable(webpage):
 138         return 'teachableTracker.linker:autoLink' in webpage and re.search(
 139             r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
 140             webpage)
 141
 142     @staticmethod
 143     def _extract_url(webpage, source_url):
 144         if not TeachableIE._is_teachable(webpage):
 145             return
 146         if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
 147             return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
 148
 149     def _real_extract(self, url):
 150         mobj = re.match(self._VALID_URL, url)
 151         site = mobj.group('site') or mobj.group('site_t')
 152         video_id = mobj.group('id')
 153
 154         self._login(site)
 155
 156         prefixed = url.startswith(self._URL_PREFIX)
 157         if prefixed:
 158             url = url[len(self._URL_PREFIX):]
 159
 160         webpage = self._download_webpage(url, video_id)
 161
 162         wistia_urls = WistiaIE._extract_urls(webpage)
 163         if not wistia_urls:
 164             if any(re.search(p, webpage) for p in (
 165                     r'class=["\']lecture-contents-locked',
 166                     r'>\s*Lecture contents locked',
 167                     r'id=["\']lecture-locked',
 168                     # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
 169                     r'class=["\'](?:inner-)?lesson-locked',
 170                     r'>LESSON LOCKED<')):
 171                 self.raise_login_required('Lecture contents locked')
 172             raise ExtractorError('Unable to find video URL')
 173
 174         title = self._og_search_title(webpage, default=None)
 175
 176         entries = [{
 177             '_type': 'url_transparent',
 178             'url': wistia_url,
 179             'ie_key': WistiaIE.ie_key(),
 180             'title': title,
 181         } for wistia_url in wistia_urls]
 182
 183         return self.playlist_result(entries, video_id, title)
 184
 185
 186 class TeachableCourseIE(TeachableBaseIE):
 187     _VALID_URL = r'''(?x)
 188                         (?:
 189                             %shttps?://(?P<site_t>[^/]+)|
 190                             https?://(?:www\.)?(?P<site>%s)
 191                         )
 192                         /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
 193                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 194     _TESTS = [{
 195         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
 196         'info_dict': {
 197             'id': 'essential-web-developer-course',
 198             'title': 'The Essential Web Developer Course (Free)',
 199         },
 200         'playlist_count': 192,
 201     }, {
 202         'url': 'http://upskillcourses.com/courses/119763/',
 203         'only_matching': True,
 204     }, {
 205         'url': 'http://upskillcourses.com/courses/enrolled/119763',
 206         'only_matching': True,
 207     }, {
 208         'url': 'https://academy.gns3.com/courses/enrolled/423415',
 209         'only_matching': True,
 210     }, {
 211         'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
 212         'only_matching': True,
 213     }, {
 214         'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
 215         'only_matching': True,
 216     }]
 217
 218     @classmethod
 219     def suitable(cls, url):
 220         return False if TeachableIE.suitable(url) else super(
 221             TeachableCourseIE, cls).suitable(url)
 222
 223     def _real_extract(self, url):
 224         mobj = re.match(self._VALID_URL, url)
 225         site = mobj.group('site') or mobj.group('site_t')
 226         course_id = mobj.group('id')
 227
 228         self._login(site)
 229
 230         prefixed = url.startswith(self._URL_PREFIX)
 231         if prefixed:
 232             prefix = self._URL_PREFIX
 233             url = url[len(prefix):]
 234
 235         webpage = self._download_webpage(url, course_id)
 236
 237         url_base = 'https://%s/' % site
 238
 239         entries = []
 240
 241         for mobj in re.finditer(
 242                 r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
 243                 webpage):
 244             li = mobj.group('li')
 245             if 'fa-youtube-play' not in li:
 246                 continue
 247             lecture_url = self._search_regex(
 248                 r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
 249                 'lecture url', default=None, group='url')
 250             if not lecture_url:
 251                 continue
 252             lecture_id = self._search_regex(
 253                 r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
 254             title = self._html_search_regex(
 255                 r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
 256                 'title', default=None)
 257             entry_url = urljoin(url_base, lecture_url)
 258             if prefixed:
 259                 entry_url = self._URL_PREFIX + entry_url
 260             entries.append(
 261                 self.url_result(
 262                     entry_url,
 263                     ie=TeachableIE.ie_key(), video_id=lecture_id,
 264                     video_title=clean_html(title)))
 265
 266         course_title = self._html_search_regex(
 267             (r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
 268              r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
 269             webpage, 'course title', fatal=False)
 270
 271         return self.playlist_result(entries, course_id, course_title)