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