yt_dlp/extractor/brilliantpala.py

   1 import hashlib
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     traverse_obj,
   7     urlencode_postdata,
   8 )
   9
  10
  11 class BrilliantpalaBaseIE(InfoExtractor):
  12     _NETRC_MACHINE = 'brilliantpala'
  13     _DOMAIN = '{subdomain}.brilliantpala.org'
  14
  15     def _initialize_pre_login(self):
  16         self._HOMEPAGE = f'https://{self._DOMAIN}'
  17         self._LOGIN_API = f'{self._HOMEPAGE}/login/'
  18         self._LOGOUT_DEVICES_API = f'{self._HOMEPAGE}/logout_devices/?next=/'
  19         self._CONTENT_API = f'{self._HOMEPAGE}/api/v2.4/contents/{{content_id}}/'
  20         self._HLS_AES_URI = f'{self._HOMEPAGE}/api/v2.5/video_contents/{{content_id}}/key/'
  21
  22     def _get_logged_in_username(self, url, video_id):
  23         webpage, urlh = self._download_webpage_handle(url, video_id)
  24         if urlh.url.startswith(self._LOGIN_API):
  25             self.raise_login_required()
  26         return self._html_search_regex(
  27             r'"username"\s*:\s*"(?P<username>[^"]+)"', webpage, 'logged-in username')
  28
  29     def _perform_login(self, username, password):
  30         login_page, urlh = self._download_webpage_handle(
  31             self._LOGIN_API, None, 'Downloading login page', expected_status=401)
  32         if urlh.status != 401 and not urlh.url.startswith(self._LOGIN_API):
  33             self.write_debug('Cookies are valid, no login required.')
  34             return
  35
  36         if urlh.status == 401:
  37             self.write_debug('Got HTTP Error 401; cookies have been invalidated')
  38             login_page = self._download_webpage(self._LOGIN_API, None, 'Re-downloading login page')
  39
  40         login_form = self._hidden_inputs(login_page)
  41         login_form.update({
  42             'username': username,
  43             'password': password,
  44         })
  45         self._set_cookie(self._DOMAIN, 'csrftoken', login_form['csrfmiddlewaretoken'])
  46
  47         logged_page = self._download_webpage(
  48             self._LOGIN_API, None, note='Logging in', headers={'Referer': self._LOGIN_API},
  49             data=urlencode_postdata(login_form))
  50
  51         if self._html_search_regex(
  52                 r'(Your username / email and password)', logged_page, 'auth fail', default=None):
  53             raise ExtractorError('wrong username or password', expected=True)
  54
  55         # the maximum number of logins is one
  56         if self._html_search_regex(
  57                 r'(Logout Other Devices)', logged_page, 'logout devices button', default=None):
  58             logout_device_form = self._hidden_inputs(logged_page)
  59             self._download_webpage(
  60                 self._LOGOUT_DEVICES_API, None, headers={'Referer': self._LOGIN_API},
  61                 note='Logging out other devices', data=urlencode_postdata(logout_device_form))
  62
  63     def _real_extract(self, url):
  64         course_id, content_id = self._match_valid_url(url).group('course_id', 'content_id')
  65         video_id = f'{course_id}-{content_id}'
  66
  67         username = self._get_logged_in_username(url, video_id)
  68
  69         content_json = self._download_json(
  70             self._CONTENT_API.format(content_id=content_id), video_id,
  71             note='Fetching content info', errnote='Unable to fetch content info')
  72
  73         entries = []
  74         for stream in traverse_obj(content_json, ('video', 'streams', lambda _, v: v['id'] and v['url'])):
  75             formats = self._extract_m3u8_formats(stream['url'], video_id, fatal=False)
  76             if not formats:
  77                 continue
  78             entries.append({
  79                 'id': str(stream['id']),
  80                 'title': content_json.get('title'),
  81                 'formats': formats,
  82                 'hls_aes': {'uri': self._HLS_AES_URI.format(content_id=content_id)},
  83                 'http_headers': {'X-Key': hashlib.sha256(username.encode('ascii')).hexdigest()},
  84                 'thumbnail': content_json.get('cover_image'),
  85             })
  86
  87         return self.playlist_result(
  88             entries, playlist_id=video_id, playlist_title=content_json.get('title'))
  89
  90
  91 class BrilliantpalaElearnIE(BrilliantpalaBaseIE):
  92     IE_NAME = 'Brilliantpala:Elearn'
  93     IE_DESC = 'VoD on elearn.brilliantpala.org'
  94     _VALID_URL = r'https?://elearn\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
  95     _TESTS = [{
  96         'url': 'https://elearn.brilliantpala.org/courses/42/contents/12345/',
  97         'only_matching': True,
  98     }, {
  99         'url': 'https://elearn.brilliantpala.org/courses/98/contents/36683/',
 100         'info_dict': {
 101             'id': '23577',
 102             'ext': 'mp4',
 103             'title': 'Physical World, Units and Measurements  - 1',
 104             'thumbnail': 'https://d1j3vi2u94ebt0.cloudfront.net/institute/brilliantpalalms/chapter_contents/26237/e657f81b90874be19795c7ea081f8d5c.png',
 105             'live_status': 'not_live',
 106         },
 107         'params': {
 108             'skip_download': True,
 109         },
 110     }]
 111
 112     _DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='elearn')
 113
 114
 115 class BrilliantpalaClassesIE(BrilliantpalaBaseIE):
 116     IE_NAME = 'Brilliantpala:Classes'
 117     IE_DESC = 'VoD on classes.brilliantpala.org'
 118     _VALID_URL = r'https?://classes\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
 119     _TESTS = [{
 120         'url': 'https://classes.brilliantpala.org/courses/42/contents/12345/',
 121         'only_matching': True,
 122     }, {
 123         'url': 'https://classes.brilliantpala.org/courses/416/contents/25445/',
 124         'info_dict': {
 125             'id': '9128',
 126             'ext': 'mp4',
 127             'title': 'Motion in a Straight Line - Class 1',
 128             'thumbnail': 'https://d3e4y8hquds3ek.cloudfront.net/institute/brilliantpalaelearn/chapter_contents/ff5ba838d0ec43419f67387fe1a01fa8.png',
 129             'live_status': 'not_live',
 130         },
 131         'params': {
 132             'skip_download': True,
 133         },
 134     }]
 135
 136     _DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='classes')