Merge 78867966e350bb7f5f7d71eb50d4e642cebb0711 into 4e714f9df1ed2cccd51df60d45ff5504abe827b7

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

youtube_dl/extractor/adobepass.py

@@ -1319,6 +1319,11 @@ MSO_INFO = {
     'cou060': {
         'name': 'Zito Media'
     },
+    'slingtv': {
+        'name': 'Sling TV',
+        'username_field': 'username',
+        'password_field': 'password',
+    },
 }
 
 
@@ -1496,6 +1501,60 @@ class AdobePassIE(InfoExtractor):
                         }), headers={
                             'Content-Type': 'application/x-www-form-urlencoded'
                         })
+                elif mso_id == 'slingtv':
+                    # sling authentication requires several steps
+                    #
+                    # firstbookend - The first redirect is to a bookend page, which
+                    # is just an HTTP get that runs some JS to look at
+                    # window history (?) and count how many times
+                    # the browser has been on a page. To stop back buttons?
+                    # After resubmitting, we are redirected to the login form
+                    #
+                    # after the login form, there is a meta-refresh (bypassing some JS)
+                    # that redirects to another bookend page that once again
+                    # looks at the browser window history... It seems to increment
+                    # by two during the process, so do that here.
+                    #
+                    # after the last bookend, a manual form to finish the login
+
+                    first_bookend_page, urlh = provider_redirect_page_res
+
+                    # extract the form data from the first bookend and re-send via GET
+                    hidden_data = self._hidden_inputs(first_bookend_page)
+                    hidden_data['history'] = 1
+
+                    provider_login_page_res = self._download_webpage_handle(
+                        urlh.geturl(), video_id, 'Sending first bookend.', query=hidden_data)
+
+                    # log in after being redirected
+                    provider_redirect_post_login_res = post_form(provider_login_page_res, 'Logging in', {
+                        mso_info.get('username_field', 'username'): username,
+                        mso_info.get('password_field', 'password'): password,
+                    })
+
+                    provider_association_redirect, urlh = provider_redirect_post_login_res
+
+                    # extract the redirect URL (executes with JS in the browser)
+                    provider_refresh_redirect_url = extract_redirect_url(
+                        provider_association_redirect, url=urlh.geturl())
+
+                    # the redirected URL sends us to the final bookend page
+                    last_bookend_page_res = self._download_webpage_handle(
+                        provider_refresh_redirect_url, video_id,
+                        'Downloading Auth Association Redirect Page (meta refresh)')
+
+                    last_bookend_page, urlh = last_bookend_page_res
+
+                    # extract the form data from the final page
+                    hidden_data = self._hidden_inputs(last_bookend_page)
+                    hidden_data['history'] = 3
+
+                    # re-send via GET
+                    mvpd_confirm_page_res = self._download_webpage_handle(
+                        urlh.geturl(), video_id, 'Sending final bookend.', query=hidden_data)
+
+                    # press the "button" to confirm login
+                    post_form(mvpd_confirm_page_res, 'Confirming Login')
                 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',