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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     decode_packed_codes,
   8     ExtractorError,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class SCTEBaseIE(InfoExtractor):
  14     _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx'
  15     _NETRC_MACHINE = 'scte'
  16
  17     def _real_initialize(self):
  18         self._login()
  19
  20     def _login(self):
  21         username, password = self._get_login_info()
  22         if username is None:
  23             return
  24
  25         login_popup = self._download_webpage(
  26             self._LOGIN_URL, None, 'Downloading login popup')
  27
  28         def is_logged(webpage):
  29             return any(re.search(p, webpage) for p in (
  30                 r'class=["\']welcome\b', r'>Sign Out<'))
  31
  32         # already logged in
  33         if is_logged(login_popup):
  34             return
  35
  36         login_form = self._hidden_inputs(login_popup)
  37
  38         login_form.update({
  39             'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username,
  40             'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password,
  41             'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on',
  42         })
  43
  44         response = self._download_webpage(
  45             self._LOGIN_URL, None, 'Logging in',
  46             data=urlencode_postdata(login_form))
  47
  48         if '|pageRedirect|' not in response and not is_logged(response):
  49             error = self._html_search_regex(
  50                 r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</',
  51                 response, 'error message', default=None)
  52             if error:
  53                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  54             raise ExtractorError('Unable to log in')
  55
  56
  57 class SCTEIE(SCTEBaseIE):
  58     _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)'
  59     _TESTS = [{
  60         'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484',
  61         'info_dict': {
  62             'title': 'Introduction to DOCSIS Engineering Professional',
  63             'id': '31484',
  64         },
  65         'playlist_count': 5,
  66         'skip': 'Requires account credentials',
  67     }]
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71
  72         webpage = self._download_webpage(url, video_id)
  73
  74         title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
  75
  76         context_id = self._search_regex(r'context-(\d+)', webpage, video_id)
  77         content_base = 'https://learning.scte.org/pluginfile.php/%s/mod_scorm/content/8/' % context_id
  78         context = decode_packed_codes(self._download_webpage(
  79             '%smobile/data.js' % content_base, video_id))
  80
  81         data = self._parse_xml(
  82             self._search_regex(
  83                 r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"),
  84             video_id)
  85
  86         entries = []
  87         for asset in data.findall('.//asset'):
  88             asset_url = asset.get('url')
  89             if not asset_url or not asset_url.endswith('.mp4'):
  90                 continue
  91             asset_id = self._search_regex(
  92                 r'video_([^_]+)_', asset_url, 'asset id', default=None)
  93             if not asset_id:
  94                 continue
  95             entries.append({
  96                 'id': asset_id,
  97                 'title': title,
  98                 'url': content_base + asset_url,
  99             })
 100
 101         return self.playlist_result(entries, video_id, title)
 102
 103
 104 class SCTECourseIE(SCTEBaseIE):
 105     _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)'
 106     _TESTS = [{
 107         'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491',
 108         'only_matching': True,
 109     }, {
 110         'url': 'https://learning.scte.org/course/view.php?id=3639',
 111         'only_matching': True,
 112     }, {
 113         'url': 'https://learning.scte.org/course/view.php?id=3073',
 114         'only_matching': True,
 115     }]
 116
 117     def _real_extract(self, url):
 118         course_id = self._match_id(url)
 119
 120         webpage = self._download_webpage(url, course_id)
 121
 122         title = self._search_regex(
 123             r'<h1>(.+?)</h1>', webpage, 'title', default=None)
 124
 125         entries = []
 126         for mobj in re.finditer(
 127                 r'''(?x)
 128                     <a[^>]+
 129                         href=(["\'])
 130                         (?P<url>
 131                             https?://learning\.scte\.org/mod/
 132                             (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*?
 133                             \bid=\d+
 134                         )
 135                     ''',
 136                 webpage):
 137             item_url = mobj.group('url')
 138             if item_url == url:
 139                 continue
 140             ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm'
 141                   else SCTECourseIE.ie_key())
 142             entries.append(self.url_result(item_url, ie=ie))
 143
 144         return self.playlist_result(entries, course_id, title)