Merge 57c3cb420c31e78732566b77dfb16fd78ebfd310 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/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

@@ -559,6 +559,10 @@ from .joj import JojIE
 from .jwplatform import JWPlatformIE
 from .kakao import KakaoIE
 from .kaltura import KalturaIE
+from .kan import (
+    KanEpisodeIE,
+    KanPlaylistIE
+)
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE

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/kan.py

@@ -0,0 +1,116 @@
+# coding: utf-8
+from __future__ import unicode_literals
+from ..compat import compat_str
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+    try_get,
+    unified_strdate)
+
+
+def get_thumbnail(data):
+    for media in data.get('media_group', []):
+        if media.get('type') == 'image':
+            for item in media.get('media_item', []):
+                thumbnail = item.get('src')
+                if thumbnail:
+                    return thumbnail
+
+
+class KanBaseIE(InfoExtractor):
+    def download_webpage(self, url, video_id):
+        return self._download_webpage(
+            url,
+            video_id)
+
+    def extract_item(self, video_id, webpage):
+        data = self._parse_json(
+            self._search_regex(
+                r'<script[^>]+id="kan_app_search_data"[^>]*>([^<]+)</script>',
+                webpage,
+                'data'),
+            video_id)
+        title = data.get('title') or self._og_search_title(webpage)
+        m3u8_url = try_get(data, lambda x: x['content']['src'], compat_str)
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        if not formats:
+            raise ExtractorError('Unable to extract video formats')
+        description = data.get('summary') or \
+            self._og_search_description(webpage, fatal=False)
+        creator = try_get(data, lambda x: x['author']['name'], compat_str) or \
+            self._og_search_property('site_name', webpage, fatal=False)
+        thumbnail = get_thumbnail(data)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+            'description': description,
+            'creator': creator,
+            'release_date': unified_strdate(data.get('published')),
+            'duration': parse_duration(
+                try_get(data, lambda x: x['extensions']['duration']))
+        }
+
+
+class KanEpisodeIE(KanBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?kan\.org\.il/[iI]tem/\?item[iI]d=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.kan.org.il/Item/?itemId=74658',
+        'md5': 'c28763bdb61c1bb7823528dd024e6129',
+        'info_dict': {
+            'id': '74658',
+            'ext': 'mp4',
+            'title': 'העד - פרק 2',
+            'thumbnail': r're:^https://.*36805_A\.jpeg$',
+            'description': 'הגופות ממשיכות להיערם, אך איזי עדיין מפקפק בחשדות נגד ברק',
+            'creator': 'מערכת כאן',
+            'release_date': '20200803',
+            'duration': 2393,
+        },
+        'params': {
+            'skip_download': True
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.extract_item(video_id, self.download_webpage(url, video_id))
+
+
+class KanPlaylistIE(KanBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?kan\.org\.il/program/\?cat[iI]d=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.kan.org.il/program/?catId=1636',
+        'playlist_mincount': 9,
+        'info_dict': {
+            'id': '1636',
+            'title': 'מנאייכ - פרקים מלאים לצפייה ישירה | כאן',
+            'description': 'md5:9dfbd501189d08674d20762464c5301b',
+        },
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self.download_webpage(url, list_id)
+        video_ids = re.findall(r'onclick="playVideo\(.*,\'([0-9]+)\'\)', webpage)
+        entries = []
+        for video_id in video_ids:
+            video_url = 'https://www.kan.org.il/Item/?itemId=%s' % video_id
+            entries.append(self.extract_item(
+                video_id,
+                self.download_webpage(video_url, video_id)))
+        if not entries:
+            raise ExtractorError('Unable to extract playlist entries')
+
+        return {
+            '_type': 'playlist',
+            'id': list_id,
+            'entries': entries,
+            'title': self._og_search_title(webpage, fatal=False),
+            'description': self._og_search_description(webpage),
+        }

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',