Merge f9d0a8cdcdf5c2edee13468125486c30f41f6af8 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

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

youtube_dl/extractor/adobepass.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 import time
 import xml.etree.ElementTree as etree
@@ -60,6 +61,11 @@ MSO_INFO = {
         'username_field': 'IDToken1',
         'password_field': 'IDToken2',
     },
+    'Spectrum': {
+        'name': 'Spectrum',
+        'username_field': 'IDToken1',
+        'password_field': 'IDToken2',
+    },
     'Verizon': {
         'name': 'Verizon FiOS',
         'username_field': 'IDToken1',
@@ -1496,6 +1502,41 @@ class AdobePassIE(InfoExtractor):
                         }), headers={
                             'Content-Type': 'application/x-www-form-urlencoded'
                         })
+                elif mso_id == 'Spectrum':
+                    # Spectrum's login for is dynamically loaded via JS so we need to hardcode the flow
+                    # as a one-off implementation.
+                    provider_redirect_page, urlh = provider_redirect_page_res
+                    provider_login_page_res = post_form(
+                        provider_redirect_page_res, self._DOWNLOADING_LOGIN_PAGE)
+                    saml_login_page, urlh = provider_login_page_res
+                    relay_state = self._search_regex(
+                        r'RelayState\s*=\s*"(?P<relay>.+?)";',
+                        saml_login_page, 'RelayState', group='relay')
+                    saml_request = self._search_regex(
+                        r'SAMLRequest\s*=\s*"(?P<saml_request>.+?)";',
+                        saml_login_page, 'SAMLRequest', group='saml_request')
+                    login_json = {
+                        mso_info['username_field']: username,
+                        mso_info['password_field']: password,
+                        'RelayState': relay_state,
+                        'SAMLRequest': saml_request,
+                    }
+                    saml_response_json = self._download_json(
+                        'https://tveauthn.spectrum.net/tveauthentication/api/v1/manualAuth', video_id,
+                        'Downloading SAML Response',
+                        data=json.dumps(login_json).encode(),
+                        headers={
+                            'Content-Type': 'application/json',
+                            'Accept': 'application/json',
+                        })
+                    self._download_webpage(
+                        saml_response_json['SAMLRedirectUri'], video_id,
+                        'Confirming Login', data=urlencode_postdata({
+                            'SAMLResponse': saml_response_json['SAMLResponse'],
+                            'RelayState': relay_state,
+                        }), headers={
+                            'Content-Type': 'application/x-www-form-urlencoded'
+                        })
                 else:
                     # Some providers (e.g. DIRECTV NOW) have another meta refresh
                     # based redirect that should be followed.

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/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',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: