Merge 05709d989693f9ff988db9549ba0dea6ec76b218 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/rtvs.py

@@ -3,17 +3,36 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 
+from ..utils import (
+    extract_attributes,
+    merge_dicts,
+    mimetype2ext,
+    parse_duration,
+    parse_qs,
+    T,
+    traverse_obj,
+    unified_timestamp,
+    url_or_none,
+)
+
 
 class RTVSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:rtvs|stvr)\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)'
     _TESTS = [{
         # radio archive
         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
         'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
         'info_dict': {
             'id': '414872',
+            'display_id': '135331',
             'ext': 'mp3',
-            'title': 'Ostrov pokladov 1 časť.mp3'
+            'title': 'Ostrov pokladov 1 časť.mp3',
+            'duration': 2854,
+            'thumbnail': (
+                r're:https?://www\.(?:(?P<stvr>stvr)|rtvs)\.sk'
+                '/media/a501/image/file/2/0000'
+                r'/(?(stvr)rtvs-00009383\.png|b1R8\.rtvs\.jpg)$'
+            ),
         },
         'params': {
             'skip_download': True,
@@ -26,22 +45,99 @@ class RTVSIE(InfoExtractor):
             'id': '63118',
             'ext': 'mp4',
             'title': 'Amaro Džives - Náš deň',
-            'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
+            'description': r're:Cenu Romipen odovzdá .{292} Medzinárodný deň Rómov a prezentovať rómsku kultúru\.$',
+            'timestamp': 1428523500,
+            'upload_date': '20150408',
+            'thumbnail': (
+                r're:https://www\.(?:stvr|rtvs)\.sk'
+                '/media/a501/image/file/2/0031'
+                r'/L7Qm\.amaro_dzives_png\.jpg$'),
+            'duration': 4986,
         },
         'params': {
             'skip_download': True,
         }
+    }, {
+        # tv archive
+        'url': 'https://www.rtvs.sk/televizia/archiv/18083?utm_source=web&utm_medium=rozcestnik&utm_campaign=Robin',
+        'info_dict': {
+            'id': '18083',
+            'display_id': '457086',
+            'ext': 'mp4',
+            'title': 'Robin - Vodiace psy /2.časť/',
+            'description': r're:Richard so svojím psom Robinom .{49} úlohu vodiace psíky\.$',
+            'timestamp': 1711875000,
+            'upload_date': '20240331',
+            'duration': 931,
+            'thumbnail': r're:https://www\.(:rtvs|stvr)\.sk/media/a501/image/file/2/0916/robin\.jpg$',
+        }
+    }, {
+        # new domain
+        'url': 'https://www.stvr.sk/televizia/archiv/15135/512191',
+        'info_dict': {
+            'id': '512191',
+            'ext': 'mp4',
+            'title': 'Retro noviny',
+            'description': r're:Kolekciu spravodajských šotov .{62} uvádza Milan Antonič, archivár STV\.',
+            'timestamp': 1737797700,
+            'upload_date': '20250125',
+            'duration': 1686,
+            'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0519/NSF4.retro_noviny_jpg.jpg',
+        }
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+        info = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
+        iframe_url = info and self._search_regex(
+            r'"embedUrl"\s*:\s*"(https?://[^"]+)"', webpage, 'Iframe URL', default=None)
+        if not iframe_url:
+            iframe = self._search_regex(
+                r'''(<iframe\s[^>]*(?<!-)\bid\s*=\s*['"]?player_(?:(?!_)\w)+_\d+[^>]+>)''',
+                webpage, 'Iframe')
+            iframe = extract_attributes(iframe)
 
-        playlist_url = self._search_regex(
+            iframe_url = iframe['src']
-            r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
-            'playlist url', group='url')
 
-        data = self._download_json(
+        webpage = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
-            playlist_url, video_id, 'Downloading playlist')[0]
+        json_url = self._search_regex(r'var\s+url\s*=\s*"([^"]+)"\s*\+\s*ruurl', webpage, 'json URL')
-        return self._parse_jwplayer_data(data, video_id=video_id)
+        data = self._download_json('https:{0}b=mozilla&p=win&v=97&f=0&d=1'.format(json_url), video_id)
+
+        if traverse_obj(data, 'clip', expected_type=dict):
+            data['playlist'] = [data['clip']]
+
+        formats = []
+        _require = lambda k: (lambda x: x if x.get(k) else None)
+        for item in traverse_obj(data, (
+                'playlist', 0, 'sources', Ellipsis, {
+                    'src': ('src', T(url_or_none)),
+                    'type': 'type',
+                }, T(_require('src')))):
+            item_type = item.get('type')
+            if item_type == 'application/x-mpegurl':
+                formats.extend(self._extract_m3u8_formats(
+                    item['src'], video_id, ext='mp4',
+                    entry_protocol='m3u8_native', fatal=False))
+            elif item_type == 'application/dash+xml':
+                formats.extend(self._extract_mpd_formats(
+                    item['src'], video_id, fatal=False))
+            else:
+                formats.append({
+                    'url': item['src'],
+                    'ext': mimetype2ext(item_type),
+                })
+        self._sort_formats(formats)
+
+        return merge_dicts({
+            'id': video_id,
+            'display_id': traverse_obj(parse_qs(json_url), ('id', -1)),
+            'formats': formats,
+        }, info or traverse_obj(data, ('playlist', 0, {
+            'title': 'title',
+            'description': ('description', T(lambda s: s.strip())),
+            'duration': ('length', T(parse_duration)),
+            'thumbnail': ('image', T(url_or_none)),
+            'timestamp': ('datetime_create', T(unified_timestamp)),
+        })))

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: