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