yt_dlp/extractor/scte.py

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