Merge e0556cd956b62b9ea10e2a9478c1e1fad856c6e6 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/canvas.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from .gigya import GigyaBaseIE
@@ -17,6 +16,7 @@ from ..utils import (
     str_or_none,
     strip_or_none,
     url_or_none,
+    urlencode_postdata
 )
 
 
@@ -259,7 +259,7 @@ class VrtNUIE(GigyaBaseIE):
         'expected_warnings': ['Unable to download asset JSON', 'is not a supported codec', 'Unknown MIME type'],
     }]
     _NETRC_MACHINE = 'vrtnu'
-    _APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
+    _APIKEY = '3_qhEcPa5JGFROVwu5SWKqJ4mVOIkwlFNMSKwzPDAh8QZOtHqu6L4nD5Q7lk0eXOOG'
     _CONTEXT_ID = 'R3595707040'
 
     def _real_initialize(self):
@@ -270,35 +270,38 @@ class VrtNUIE(GigyaBaseIE):
         if username is None:
             return
 
-        auth_data = {
+        auth_info = self._download_json(
-            'APIKey': self._APIKEY,
+            'https://accounts.vrt.be/accounts.login', None,
-            'targetEnv': 'jssdk',
+            note='Login data', errnote='Could not get Login data',
-            'loginID': username,
+            headers={}, data=urlencode_postdata({
-            'password': password,
+                'loginID': username,
-            'authMode': 'cookie',
+                'password': password,
-        }
+                'sessionExpiration': '-2',
-
+                'APIKey': self._APIKEY,
-        auth_info = self._gigya_login(auth_data)
+                'targetEnv': 'jssdk',
+            }))
 
         # Sometimes authentication fails for no good reason, retry
         login_attempt = 1
         while login_attempt <= 3:
             try:
-                # When requesting a token, no actual token is returned, but the
+                self._request_webpage('https://token.vrt.be/vrtnuinitlogin',
-                # necessary cookies are set.
+                                      None, note='Requesting XSRF Token', errnote='Could not get XSRF Token',
+                                      query={'provider': 'site', 'destination': 'https://www.vrt.be/vrtnu/'})
+
+                post_data = {
+                    'UID': auth_info['UID'],
+                    'UIDSignature': auth_info['UIDSignature'],
+                    'signatureTimestamp': auth_info['signatureTimestamp'],
+                    'client_id': 'vrtnu-site',
+                    '_csrf': self._get_cookies('https://login.vrt.be/').get('OIDCXSRF').value
+                }
+
                 self._request_webpage(
-                    'https://token.vrt.be',
+                    'https://login.vrt.be/perform_login',
                     None, note='Requesting a token', errnote='Could not get a token',
-                    headers={
+                    headers={}, data=urlencode_postdata(post_data))
-                        'Content-Type': 'application/json',
+
-                        'Referer': 'https://www.vrt.be/vrtnu/',
-                    },
-                    data=json.dumps({
-                        'uid': auth_info['UID'],
-                        'uidsig': auth_info['UIDSignature'],
-                        'ts': auth_info['signatureTimestamp'],
-                        'email': auth_info['profile']['email'],
-                    }).encode('utf-8'))
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                     login_attempt += 1

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',