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 ..compat import compat_str
   8 from ..utils import (
   9     clean_html,
  10     ExtractorError,
  11     get_element_by_class,
  12     urlencode_postdata,
  13     urljoin,
  14 )
  15
  16
  17 class TeachableBaseIE(InfoExtractor):
  18     _NETRC_MACHINE = 'teachable'
  19     _URL_PREFIX = 'teachable:'
  20
  21     _SITES = {
  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',
  30         'courses.workitdaily.com': 'workitdaily',
  31     }
  32
  33     _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))
  34
  35     def _real_initialize(self):
  36         self._logged_in = False
  37
  38     def _login(self, site):
  39         if self._logged_in:
  40             return
  41
  42         username, password = self._get_login_info(
  43             netrc_machine=self._SITES.get(site, site))
  44         if username is None:
  45             return
  46
  47         login_page, urlh = self._download_webpage_handle(
  48             'https://%s/sign_in' % site, None,
  49             'Downloading %s login page' % site)
  50
  51         def is_logged(webpage):
  52             return any(re.search(p, webpage) for p in (
  53                 r'class=["\']user-signout',
  54                 r'<a[^>]+\bhref=["\']/sign_out',
  55                 r'Log\s+[Oo]ut\s*<'))
  56
  57         if is_logged(login_page):
  58             self._logged_in = True
  59             return
  60
  61         login_url = compat_str(urlh.geturl())
  62
  63         login_form = self._hidden_inputs(login_page)
  64
  65         login_form.update({
  66             'user[email]': username,
  67             'user[password]': password,
  68         })
  69
  70         post_url = self._search_regex(
  71             r'<form[^>]+action=(["\'])(?P<url>(?:(?!\1).)+)\1', login_page,
  72             'post url', default=login_url, group='url')
  73
  74         if not post_url.startswith('http'):
  75             post_url = urljoin(login_url, post_url)
  76
  77         response = self._download_webpage(
  78             post_url, None, 'Logging in to %s' % site,
  79             data=urlencode_postdata(login_form),
  80             headers={
  81                 'Content-Type': 'application/x-www-form-urlencoded',
  82                 'Referer': login_url,
  83             })
  84
  85         if '>I accept the new Privacy Policy<' in response:
  86             raise ExtractorError(
  87                 'Unable to login: %s asks you to accept new Privacy Policy. '
  88                 'Go to https://%s/ and accept.' % (site, site), expected=True)
  89
  90         # Successful login
  91         if is_logged(response):
  92             self._logged_in = True
  93             return
  94
  95         message = get_element_by_class('alert', response)
  96         if message is not None:
  97             raise ExtractorError(
  98                 'Unable to login: %s' % clean_html(message), expected=True)
  99
 100         raise ExtractorError('Unable to log in')
 101
 102
 103 class TeachableIE(TeachableBaseIE):
 104     _VALID_URL = r'''(?x)
 105                     (?:
 106                         %shttps?://(?P<site_t>[^/]+)|
 107                         https?://(?:www\.)?(?P<site>%s)
 108                     )
 109                     /courses/[^/]+/lectures/(?P<id>\d+)
 110                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 111
 112     _TESTS = [{
 113         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
 114         'info_dict': {
 115             'id': 'uzw6zw58or',
 116             'ext': 'mp4',
 117             'title': 'Welcome to the Course!',
 118             'description': 'md5:65edb0affa582974de4625b9cdea1107',
 119             'duration': 138.763,
 120             'timestamp': 1479846621,
 121             'upload_date': '20161122',
 122         },
 123         'params': {
 124             'skip_download': True,
 125         },
 126     }, {
 127         'url': 'http://upskillcourses.com/courses/119763/lectures/1747100',
 128         'only_matching': True,
 129     }, {
 130         'url': 'https://academy.gns3.com/courses/423415/lectures/6885939',
 131         'only_matching': True,
 132     }, {
 133         'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100',
 134         'only_matching': True,
 135     }]
 136
 137     @staticmethod
 138     def _is_teachable(webpage):
 139         return 'teachableTracker.linker:autoLink' in webpage and re.search(
 140             r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
 141             webpage)
 142
 143     @staticmethod
 144     def _extract_url(webpage, source_url):
 145         if not TeachableIE._is_teachable(webpage):
 146             return
 147         if re.match(r'https?://[^/]+/(?:courses|p)', source_url):
 148             return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url)
 149
 150     def _real_extract(self, url):
 151         mobj = re.match(self._VALID_URL, url)
 152         site = mobj.group('site') or mobj.group('site_t')
 153         video_id = mobj.group('id')
 154
 155         self._login(site)
 156
 157         prefixed = url.startswith(self._URL_PREFIX)
 158         if prefixed:
 159             url = url[len(self._URL_PREFIX):]
 160
 161         webpage = self._download_webpage(url, video_id)
 162
 163         wistia_url = WistiaIE._extract_url(webpage)
 164         if not wistia_url:
 165             if any(re.search(p, webpage) for p in (
 166                     r'class=["\']lecture-contents-locked',
 167                     r'>\s*Lecture contents locked',
 168                     r'id=["\']lecture-locked')):
 169                 self.raise_login_required('Lecture contents locked')
 170
 171         title = self._og_search_title(webpage, default=None)
 172
 173         return {
 174             '_type': 'url_transparent',
 175             'url': wistia_url,
 176             'ie_key': WistiaIE.ie_key(),
 177             'title': title,
 178         }
 179
 180
 181 class TeachableCourseIE(TeachableBaseIE):
 182     _VALID_URL = r'''(?x)
 183                         (?:
 184                             %shttps?://(?P<site_t>[^/]+)|
 185                             https?://(?:www\.)?(?P<site>%s)
 186                         )
 187                         /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+)
 188                     ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE
 189     _TESTS = [{
 190         'url': 'http://upskillcourses.com/courses/essential-web-developer-course/',
 191         'info_dict': {
 192             'id': 'essential-web-developer-course',
 193             'title': 'The Essential Web Developer Course (Free)',
 194         },
 195         'playlist_count': 192,
 196     }, {
 197         'url': 'http://upskillcourses.com/courses/119763/',
 198         'only_matching': True,
 199     }, {
 200         'url': 'http://upskillcourses.com/courses/enrolled/119763',
 201         'only_matching': True,
 202     }, {
 203         'url': 'https://academy.gns3.com/courses/enrolled/423415',
 204         'only_matching': True,
 205     }, {
 206         'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini',
 207         'only_matching': True,
 208     }, {
 209         'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course',
 210         'only_matching': True,
 211     }]
 212
 213     @classmethod
 214     def suitable(cls, url):
 215         return False if TeachableIE.suitable(url) else super(
 216             TeachableCourseIE, cls).suitable(url)
 217
 218     def _real_extract(self, url):
 219         mobj = re.match(self._VALID_URL, url)
 220         site = mobj.group('site') or mobj.group('site_t')
 221         course_id = mobj.group('id')
 222
 223         self._login(site)
 224
 225         prefixed = url.startswith(self._URL_PREFIX)
 226         if prefixed:
 227             prefix = self._URL_PREFIX
 228             url = url[len(prefix):]
 229
 230         webpage = self._download_webpage(url, course_id)
 231
 232         url_base = 'https://%s/' % site
 233
 234         entries = []
 235
 236         for mobj in re.finditer(
 237                 r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
 238                 webpage):
 239             li = mobj.group('li')
 240             if 'fa-youtube-play' not in li:
 241                 continue
 242             lecture_url = self._search_regex(
 243                 r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
 244                 'lecture url', default=None, group='url')
 245             if not lecture_url:
 246                 continue
 247             lecture_id = self._search_regex(
 248                 r'/lectures/(\d+)', lecture_url, 'lecture id', default=None)
 249             title = self._html_search_regex(
 250                 r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li,
 251                 'title', default=None)
 252             entry_url = urljoin(url_base, lecture_url)
 253             if prefixed:
 254                 entry_url = self._URL_PREFIX + entry_url
 255             entries.append(
 256                 self.url_result(
 257                     entry_url,
 258                     ie=TeachableIE.ie_key(), video_id=lecture_id,
 259                     video_title=clean_html(title)))
 260
 261         course_title = self._html_search_regex(
 262             (r'(?s)<img[^>]+class=["\']course-image[^>]+>\s*<h\d>(.+?)</h',
 263              r'(?s)<h\d[^>]+class=["\']course-title[^>]+>(.+?)</h'),
 264             webpage, 'course title', fatal=False)
 265
 266         return self.playlist_result(entries, course_id, course_title)