Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/linuxacademy.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import random
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_b64decode,
  10     compat_HTTPError,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     orderedSet,
  15     unescapeHTML,
  16     urlencode_postdata,
  17     urljoin,
  18 )
  19
  20
  21 class LinuxAcademyIE(InfoExtractor):
  22     _VALID_URL = r'''(?x)
  23                     https?://
  24                         (?:www\.)?linuxacademy\.com/cp/
  25                         (?:
  26                             courses/lesson/course/(?P<chapter_id>\d+)/lesson/(?P<lesson_id>\d+)|
  27                             modules/view/id/(?P<course_id>\d+)
  28                         )
  29                     '''
  30     _TESTS = [{
  31         'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154',
  32         'info_dict': {
  33             'id': '1498-2',
  34             'ext': 'mp4',
  35             'title': "Introduction to the Practitioner's Brief",
  36         },
  37         'params': {
  38             'skip_download': True,
  39         },
  40         'skip': 'Requires Linux Academy account credentials',
  41     }, {
  42         'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2',
  43         'only_matching': True,
  44     }, {
  45         'url': 'https://linuxacademy.com/cp/modules/view/id/154',
  46         'info_dict': {
  47             'id': '154',
  48             'title': 'AWS Certified Cloud Practitioner',
  49             'description': 'md5:039db7e60e4aac9cf43630e0a75fa834',
  50         },
  51         'playlist_count': 41,
  52         'skip': 'Requires Linux Academy account credentials',
  53     }]
  54
  55     _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
  56     _ORIGIN_URL = 'https://linuxacademy.com'
  57     _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx'
  58     _NETRC_MACHINE = 'linuxacademy'
  59
  60     def _real_initialize(self):
  61         self._login()
  62
  63     def _login(self):
  64         username, password = self._get_login_info()
  65         if username is None:
  66             return
  67
  68         def random_string():
  69             return ''.join([
  70                 random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~')
  71                 for _ in range(32)])
  72
  73         webpage, urlh = self._download_webpage_handle(
  74             self._AUTHORIZE_URL, None, 'Downloading authorize page', query={
  75                 'client_id': self._CLIENT_ID,
  76                 'response_type': 'token id_token',
  77                 'redirect_uri': self._ORIGIN_URL,
  78                 'scope': 'openid email user_impersonation profile',
  79                 'audience': self._ORIGIN_URL,
  80                 'state': random_string(),
  81                 'nonce': random_string(),
  82             })
  83
  84         login_data = self._parse_json(
  85             self._search_regex(
  86                 r'atob\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
  87                 'login info', group='value'), None,
  88             transform_source=lambda x: compat_b64decode(x).decode('utf-8')
  89         )['extraParams']
  90
  91         login_data.update({
  92             'client_id': self._CLIENT_ID,
  93             'redirect_uri': self._ORIGIN_URL,
  94             'tenant': 'lacausers',
  95             'connection': 'Username-Password-Authentication',
  96             'username': username,
  97             'password': password,
  98             'sso': 'true',
  99         })
 100
 101         login_state_url = urlh.geturl()
 102
 103         try:
 104             login_page = self._download_webpage(
 105                 'https://login.linuxacademy.com/usernamepassword/login', None,
 106                 'Downloading login page', data=json.dumps(login_data).encode(),
 107                 headers={
 108                     'Content-Type': 'application/json',
 109                     'Origin': 'https://login.linuxacademy.com',
 110                     'Referer': login_state_url,
 111                 })
 112         except ExtractorError as e:
 113             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 114                 error = self._parse_json(e.cause.read(), None)
 115                 message = error.get('description') or error['code']
 116                 raise ExtractorError(
 117                     '%s said: %s' % (self.IE_NAME, message), expected=True)
 118             raise
 119
 120         callback_page, urlh = self._download_webpage_handle(
 121             'https://login.linuxacademy.com/login/callback', None,
 122             'Downloading callback page',
 123             data=urlencode_postdata(self._hidden_inputs(login_page)),
 124             headers={
 125                 'Content-Type': 'application/x-www-form-urlencoded',
 126                 'Origin': 'https://login.linuxacademy.com',
 127                 'Referer': login_state_url,
 128             })
 129
 130         access_token = self._search_regex(
 131             r'access_token=([^=&]+)', urlh.geturl(),
 132             'access token')
 133
 134         self._download_webpage(
 135             'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s'
 136             % access_token, None, 'Downloading token validation page')
 137
 138     def _real_extract(self, url):
 139         mobj = re.match(self._VALID_URL, url)
 140         chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id')
 141         item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id)
 142
 143         webpage = self._download_webpage(url, item_id)
 144
 145         # course path
 146         if course_id:
 147             entries = [
 148                 self.url_result(
 149                     urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key())
 150                 for lesson_url in orderedSet(re.findall(
 151                     r'<a[^>]+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)',
 152                     webpage))]
 153             title = unescapeHTML(self._html_search_regex(
 154                 (r'class=["\']course-title["\'][^>]*>(?P<value>[^<]+)',
 155                  r'var\s+title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'),
 156                 webpage, 'title', default=None, group='value'))
 157             description = unescapeHTML(self._html_search_regex(
 158                 r'var\s+description\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
 159                 webpage, 'description', default=None, group='value'))
 160             return self.playlist_result(entries, course_id, title, description)
 161
 162         # single video path
 163         info = self._extract_jwplayer_data(
 164             webpage, item_id, require_title=False, m3u8_id='hls',)
 165         title = self._search_regex(
 166             (r'>Lecture\s*:\s*(?P<value>[^<]+)',
 167              r'lessonName\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
 168             'title', group='value')
 169         info.update({
 170             'id': item_id,
 171             'title': title,
 172         })
 173         return info