Merge 47217e7b547c08a5e20c94aa9e31828183bdb5ca into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* 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/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/extractor/twentythreevideo.py

@@ -4,11 +4,12 @@ import re
 
 from .common import InfoExtractor
 from ..utils import int_or_none
+from ..compat import compat_urllib_parse_urlencode
 
 
 class TwentyThreeVideoIE(InfoExtractor):
     IE_NAME = '23video'
-    _VALID_URL = r'https?://(?P<domain>[^.]+\.(?:twentythree\.net|23video\.com|filmweb\.no))/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)'
+    _VALID_URL = r'https?://(?P<domain>[^.]+\.(?:twentythree\.net|kglteater\.dk|23video\.com|filmweb\.no))/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)'
     _TESTS = [{
         'url': 'https://video.twentythree.net/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=20448876&autoPlay=1',
         'md5': '75fcf216303eb1dae9920d651f85ced4',
@@ -23,18 +24,93 @@ class TwentyThreeVideoIE(InfoExtractor):
         }
     }, {
         'url': 'https://bonnier-publications-danmark.23video.com/v.ihtml/player.html?token=f0dc46476e06e13afd5a1f84a29e31e8&source=embed&photo%5fid=36137620',
-        'only_matching': True,
+        'md5': '772a91f83d129ee5f015b12bea61a78b',
+        'info_dict': {
+            'id': '36137620',
+            'ext': 'mp4',
+            'title': 'Photoshop Elements 2019 - Photo Text',
+            'timestamp': 1538664032,
+            'upload_date': '20181004',
+            'uploader_id': '10801356',
+            'uploader': 'Kristoffer Engbo',
+        }
+    }, {
+        'url': 'https://video.kglteater.dk/v.ihtml/player.html?source=share&photo%5fid=65098499',
+        'md5': '4e20a33ce86b13ca114ee44a0a8d8efb',
+        'info_dict': {
+            'id': '65098499',
+            'ext': 'mp4',
+            'title': 'Askepot',
+            'timestamp': 1605173942,
+            'upload_date': '20201112',
+            'uploader_id': '62151179',
+            'uploader': 'jbny',
+        }
+    }, {
+        'url': 'https://video.kglteater.dk/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=52486482&autoPlay=1',
+        'md5': 'c39ffb965079fb4395788e6814ec3cdc',
+        'info_dict': {
+            'id': '52486482',
+            'ext': 'mp4',
+            'title': 'N\xf8ddekn\xe6kkeren 2019',
+            'timestamp': 1558953133,
+            'upload_date': '20190527',
+            'uploader_id': '7450690',
+            'uploader': 'Tejs Holm',
+        }
     }]
 
     def _real_extract(self, url):
         domain, query, photo_id = re.match(self._VALID_URL, url).groups()
         base_url = 'https://%s' % domain
-        photo_data = self._download_json(
-            base_url + '/api/photo/list?' + query, photo_id, query={
-                'format': 'json',
-            }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo']
-        title = photo_data['title']
 
+        def is_geo_blocked():
+            # /api/player/settings
+            playersettings_0 = {'player_id': 0, 'parameters': 'showDescriptions=0&source=site&photo%5fid=' + photo_id + '&autoPlay=1', '_li': 0, '_bot': 0}
+            playersettings_0_param = '/api/player/settings?' + compat_urllib_parse_urlencode(playersettings_0)
+
+            # /api/live/list
+            livelist_1 = {'include_actions_p': 1, 'showDescriptions': 0, 'source': 'site', 'photo_id': photo_id, 'autoPlay': 1, 'upcoming_p': 1, 'ordering': 'streaming', 'player_id': 0}
+            livelist_1_param = '/api/live/list?' + compat_urllib_parse_urlencode(livelist_1)
+
+            # /api/photo/list
+            photolist_2 = {'size': 10, 'include_actions_p': 1, 'showDescriptions': 0, 'source': 'site', 'photo_id': photo_id, 'autoPlay': 1, 'player_id': 0}
+            photolist_2_param = '/api/photo/list?' + compat_urllib_parse_urlencode(photolist_2)
+
+            new_query = {'format': 'json', 'callback': 'test', 'playersettings_0': playersettings_0_param, 'livelist_1': livelist_1_param, 'photolist_2': photolist_2_param}
+            photolist_result = self._download_json(
+                base_url + '/api/concatenate',
+                photo_id,
+                query=new_query,
+                transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photolist_2')
+            )["photolist_2"]
+
+            if "photos" in photolist_result:
+                for photo in photolist_result['photos']:
+                    if photo['photo_id'] == photo_id:
+                        return photo['protection_method'] == 'geoblocking'
+
+            return False
+
+        def get_video_query():
+            if is_geo_blocked():
+                token = self._download_json(
+                    base_url + '/api/protection/verify',
+                    photo_id,
+                    query={'protection_method': 'geoblocking', 'object_id': photo_id, 'object_type': 'photo', 'format': 'json', 'callback': 'visualplatform_1'},
+                    transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'protectedtoken'))['protectedtoken']['protected_token']
+
+                return {'format': 'json', 'token': token}
+            else:
+                return {'format': 'json'}
+
+        video_query = get_video_query()
+        photo_data = self._download_json(
+            base_url + '/api/photo/list?' + query, photo_id,
+            query=video_query,
+            transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo']
+
+        title = photo_data['title']
         formats = []
 
         audio_path = photo_data.get('audio_download')

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: