Merge 5b088ccdd9ebb83ccd32a0a0a2cacd537fd2e03e 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/extractors.py

@@ -560,6 +560,7 @@ from .jwplatform import JWPlatformIE
 from .kakao import KakaoIE
 from .kaltura import KalturaIE
 from .kankan import KankanIE
+from .kankids import KanKidsIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE

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/kankids.py

@@ -0,0 +1,76 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+
+CONTENT_DIR = r'/content/kids/'
+DOMAIN = r'kankids.org.il'
+
+
+class KanKidsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?' +\
+        DOMAIN.replace('.', '\\.') + CONTENT_DIR +\
+        r'(?P<category>[a-z]+)-main/(?P<id>[\w\-0-9]+)/(?P<season>\w+)?/?$'
+    _TESTS = [
+        {
+            'url': 'https://www.kankids.org.il/content/kids/ktantanim-main/p-11732/',
+            'info_dict': {
+                '_type': 'playlist',
+                'id': 'p-11732',
+                'title': 'בית ספר לקוסמים',
+            },
+            'playlist_count': 60,
+        },
+        {
+            'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/cramel_main/s1/',
+            'info_dict': {
+                '_type': 'playlist',
+                'id': 'cramel_main',
+                'title': 'כראמל - עונה 1',
+            },
+            'playlist_count': 21,
+        },
+    ]
+
+    def _real_extract(self, url):
+        m = super()._match_valid_url(url)
+        series_id = m.group('id')
+        category = m.group('category')
+        playlist_season = m.group('season')
+
+        webpage = self._download_webpage(url, series_id)
+
+        title_pattern = r'<title>(?P<title>.+) \|'
+        series_title = re.search(title_pattern, webpage)
+        if not series_title:
+            series_title = re.search(title_pattern[:-1] + r'-', webpage)
+        if series_title:
+            series_title = series_title.group('title')
+
+        season = playlist_season if playlist_season else r'(?P<season>\w+)'
+        content_dir = CONTENT_DIR + category + r'-main/'
+        playlist = set(re.findall(
+            r'href="' + content_dir         # Content dir
+            + series_id + r'/'              # Series
+            + season + r'/'                 # Season
+            + r'(?P<id>[0-9]+)/"'           # Episode
+            + r'.+title="(?P<title>.+)"',   # Title
+            webpage))
+
+        entries = []
+        content_dir = r'https://www.' + DOMAIN + content_dir
+        for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
+            entries.append(self.url_result(
+                content_dir + season + r'/' + video_id + r'/',
+                ie='Generic',
+                video_id=video_id,
+                video_title=title,
+            ))
+
+        return {
+            '_type': 'playlist',
+            'id': series_id,
+            'title': series_title,
+            'entries': entries,
+        }

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: