Merge d5de6295cf294cc5f93b07dad4f868b4d12b380a into 2b4fbfce25902d557b86b003cf48f738129efce4

thx seproDev, bashonly: yt-dlp/yt-dlp#12748

test/test_youtube_signature.py

@@ -84,6 +84,21 @@ _SIG_TESTS = [
         '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
         '0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
     ),
+    (
+        'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
+    ),
+    (
+        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+    ),
 ]
 
 _NSIG_TESTS = [
@@ -153,7 +168,7 @@ _NSIG_TESTS = [
     ),
     (
         'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
-        '-Txvy6bT5R6LqgnQNx', 'dcklJCnRUHbgSg',
+        'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
     ),
     (
         'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
@@ -173,7 +188,7 @@ _NSIG_TESTS = [
     ),
     (
         'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
-        'qO0NiMtYQ7TeJnfFG2', 'k9cuJDHNS5O7kQ',
+        'aCi3iElgd2kq0bxVbQ', 'QX1y8jGb2IbZ0w',
     ),
     (
         'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
@@ -231,10 +246,6 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
         'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
     ),
-    (
-        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
-    ),
     (
         'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
         'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
@@ -259,6 +270,22 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
         'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
     ),
+    (
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+        'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
+    ),
+    (
+        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+        'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/tv-player-ias.vflset/tv-player-ias.js',
+        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+    ),
 ]
 
 
@@ -271,6 +298,8 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js', 'e7567ecf'),
+            ('https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js', '643afba4'),
             # obsolete
             ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
             ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -280,8 +309,9 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
         )
+        ie = YoutubeIE(FakeYDL({'cachedir': False}))
         for player_url, expected_player_id in PLAYER_URLS:
-            player_id = YoutubeIE._extract_player_info(player_url)
+            player_id = ie._extract_player_info(player_url)
             self.assertEqual(player_id, expected_player_id)
 
 
@@ -301,8 +331,8 @@ class TestSignature(unittest.TestCase):
 def t_factory(name, sig_func, url_pattern):
     def make_tfunc(url, sig_input, expected_sig):
         m = url_pattern.match(url)
-        assert m, '%r should follow URL format' % url
-        test_id = m.group('id')
+        assert m, '{0!r} should follow URL format'.format(url)
+        test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
 
         def test_func(self):
             basename = 'player-{0}-{1}.js'.format(name, test_id)
@@ -335,12 +365,16 @@ def n_sig(jscode, sig_input):
 
 
 make_sig_test = t_factory(
-    'signature', signature, re.compile(r'.*(?:-|/player/)(?P<id>[a-zA-Z0-9_-]+)(?:/.+\.js|(?:/watch_as3|/html5player)?\.[a-z]+)$'))
+    'signature', signature,
+    re.compile(r'''(?x)
+        .+/(?P<h5>html5)?player(?(h5)(?:-en_US)?-|/)(?P<id>[a-zA-Z0-9/._-]+)
+        (?(h5)/(?:watch_as3|html5player))?\.js$
+    '''))
 for test_spec in _SIG_TESTS:
     make_sig_test(*test_spec)
 
 make_nsig_test = t_factory(
-    'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_-]+)/.+.js$'))
+    'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_/.-]+)\.js$'))
 for test_spec in _NSIG_TESTS:
     make_nsig_test(*test_spec)
 

youtube_dl/extractor/toggle.py

@@ -1,13 +1,9 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    ExtractorError,
     float_or_none,
     int_or_none,
     parse_iso8601,
@@ -16,219 +12,292 @@ from ..utils import (
 
 
 class ToggleIE(InfoExtractor):
-    IE_NAME = 'toggle'
-    _VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}|toggle:)(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
-        'info_dict': {
-            'id': '343115',
-            'ext': 'mp4',
-            'title': 'Lion Moms Premiere',
-            'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
-            'upload_date': '20150910',
-            'timestamp': 1441858274,
+    IE_NAME = "toggle"
+    _VALID_URL = r"(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:[^/]+/){1,}|toggle:)[^/]+-(?P<id>[0-9]+)"
+    _TESTS = [
+        {
+            ### to be updated
+            ### deprecated
+            # 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
+            "info_dict": {
+                "id": "343115",
+                "ext": "mp4",
+                "title": "Lion Moms Premiere",
+                "description": "md5:aea1149404bff4d7f7b6da11fafd8e6b",
+                "upload_date": "20150910",
+                "timestamp": 1441858274,
+            },
+            "params": {
+                "skip_download": "m3u8 download",
+            },
         },
-        'params': {
-            'skip_download': 'm3u8 download',
-        }
-    }, {
-        'note': 'DRM-protected video',
-        'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
-        'info_dict': {
-            'id': '341413',
-            'ext': 'wvm',
-            'title': 'Dug\'s Special Mission',
-            'description': 'md5:e86c6f4458214905c1772398fabc93e0',
-            'upload_date': '20150827',
-            'timestamp': 1440644006,
+        {
+            "note": "DRM-protected video",
+            ### url deprecated
+            # 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
+            "info_dict": {
+                "id": "341413",
+                "ext": "wvm",
+                "title": "Dug's Special Mission",
+                "description": "md5:e86c6f4458214905c1772398fabc93e0",
+                "upload_date": "20150827",
+                "timestamp": 1440644006,
+            },
+            "params": {
+                "skip_download": "DRM-protected wvm download",
+            },
         },
-        'params': {
-            'skip_download': 'DRM-protected wvm download',
-        }
-    }, {
-        # this also tests correct video id extraction
-        'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
-        'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
-        'info_dict': {
-            'id': '332861',
-            'ext': 'mp4',
-            'title': '28th SEA Games (5 Show) -  Episode  11',
-            'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
-            'upload_date': '20150605',
-            'timestamp': 1433480166,
+        {
+            # this also tests correct video id extraction
+            "note": "m3u8 links are geo-restricted, but Android/mp4 is okay",
+            ### url deprecated
+            # 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
+            "info_dict": {
+                "id": "332861",
+                "ext": "mp4",
+                "title": "28th SEA Games (5 Show) -  Episode  11",
+                "description": "md5:3cd4f5f56c7c3b1340c50a863f896faa",
+                "upload_date": "20150605",
+                "timestamp": 1433480166,
+            },
+            "params": {
+                "skip_download": "DRM-protected wvm download",
+            },
+            "skip": "m3u8 links are geo-restricted",
         },
-        'params': {
-            'skip_download': 'DRM-protected wvm download',
+        {
+            ### video.toggle.sg seems deprecated
+            # 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
+            "only_matching": True,
         },
-        'skip': 'm3u8 links are geo-restricted'
-    }, {
-        'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
-        'only_matching': True,
-    }]
+        {
+            "url": "https://www.mewatch.sg/clips/Seraph-Sun-Aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set-84901",
+            "only_matching": True,
+        },
+        {
+            "url": "https://www.mewatch.sg/episode/Zero-Calling-S2-E13-The-End-of-The-Beginning-55137",
+            "only_matching": True,
+        },
+        {
+            ### webisodes no longer used
+            "url": "https://www.mewatch.sg/clips/Jeeva-is-an-orphan-Vetri-S2-Webisode-7-84944",
+            # 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
+            "only_matching": True,
+        },
+        {
+            ### only available in Singapore 403 forbidden
+            "url": "https://www.mewatch.sg/movie/Seven-Days-79641",
+            "only_matching": True,
+        },
+        {
+            ### not working for this list, but not a big issue since old path deprecated
+            "url": "https://www.mewatch.sg/list/CNA-Singapore-Tonight-154904",
+            # 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
+            "only_matching": True,
+        },
+        {
+            ### not working. seems deprecated
+            # 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
+            "only_matching": True,
+        },
+        {
+            ### [20230507:shouldsee] working
+            "url": "https://www.mewatch.sg/watch/Seraph-Sun-Aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set-84901",
+            "only_matching": True,
+        },
+    ]
 
-    _API_USER = 'tvpapi_147'
-    _API_PASS = '11111'
+    _API_USER = "tvpapi_147"
+    _API_PASS = "11111"
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        lang = "en"
         params = {
-            'initObj': {
-                'Locale': {
-                    'LocaleLanguage': '',
-                    'LocaleCountry': '',
-                    'LocaleDevice': '',
-                    'LocaleUserState': 0
-                },
-                'Platform': 0,
-                'SiteGuid': 0,
-                'DomainID': '0',
-                'UDID': '',
-                'ApiUser': self._API_USER,
-                'ApiPass': self._API_PASS
-            },
-            'MediaID': video_id,
-            'mediaType': 0,
+            "delivery": "stream,progressive",
+            "resolution": "External",
+            "segments": "all",
+            "lang": lang,
+            "ff": "idp,ldp,rpt,cd",
         }
+        video_info = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + video_id + "/videos",
+            video_id,
+            "Downloading video info json",
+            query=params,
+        )
 
-        info = self._download_json(
-            'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
-            video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))
+        params = {
+            # 'delivery':'stream,progressive',
+            # 'resolution':'External',
+            "segments": "all",
+            "lang": lang,
+            "ff": "idp,ldp,rpt,cd",
+        }
+        meta_info = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + video_id,
+            video_id,
+            "Downloading video info json",
+            query=params,
+        )
 
-        title = info['MediaName']
+        # urls = info
+        info = {"Files": video_info}
+        info.update(meta_info)
 
+        title = info["path"].rsplit("/", 1)[-1]
         formats = []
-        for video_file in info.get('Files', []):
-            video_url, vid_format = video_file.get('URL'), video_file.get('Format')
-            if not video_url or video_url == 'NA' or not vid_format:
+
+        for video_file in info.get("Files", []):
+            video_url, vid_format = video_file.get("url"), video_file.get("format")
+            if not video_url or video_url == "NA" or not vid_format:
                 continue
             ext = determine_ext(video_url)
-            vid_format = vid_format.replace(' ', '')
+            vid_format = vid_format.replace(" ", "")
             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
-            if ext == 'm3u8':
+            if ext == "m3u8":
                 m3u8_formats = self._extract_m3u8_formats(
-                    video_url, video_id, ext='mp4', m3u8_id=vid_format,
-                    note='Downloading %s m3u8 information' % vid_format,
-                    errnote='Failed to download %s m3u8 information' % vid_format,
-                    fatal=False)
+                    video_url,
+                    video_id,
+                    ext="mp4",
+                    m3u8_id=vid_format,
+                    note="Downloading %s m3u8 information" % vid_format,
+                    errnote="Failed to download %s m3u8 information" % vid_format,
+                    fatal=False,
+                )
                 for f in m3u8_formats:
                     # Apple FairPlay Streaming
-                    if '/fpshls/' in f['url']:
+                    if "/fpshls/" in f["url"]:
                         continue
                     formats.append(f)
-            elif ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
-                    video_url, video_id, mpd_id=vid_format,
-                    note='Downloading %s MPD manifest' % vid_format,
-                    errnote='Failed to download %s MPD manifest' % vid_format,
-                    fatal=False))
-            elif ext == 'ism':
-                formats.extend(self._extract_ism_formats(
-                    video_url, video_id, ism_id=vid_format,
-                    note='Downloading %s ISM manifest' % vid_format,
-                    errnote='Failed to download %s ISM manifest' % vid_format,
-                    fatal=False))
-            elif ext == 'mp4':
-                formats.append({
-                    'ext': ext,
-                    'url': video_url,
-                    'format_id': vid_format,
-                })
+            elif ext == "mpd":
+                formats.extend(
+                    self._extract_mpd_formats(
+                        video_url,
+                        video_id,
+                        mpd_id=vid_format,
+                        note="Downloading %s MPD manifest" % vid_format,
+                        errnote="Failed to download %s MPD manifest" % vid_format,
+                        fatal=False,
+                    )
+                )
+            elif ext == "ism":
+                formats.extend(
+                    self._extract_ism_formats(
+                        video_url,
+                        video_id,
+                        ism_id=vid_format,
+                        note="Downloading %s ISM manifest" % vid_format,
+                        errnote="Failed to download %s ISM manifest" % vid_format,
+                        fatal=False,
+                    )
+                )
+            elif ext == "mp4":
+                formats.append(
+                    {
+                        "ext": ext,
+                        "url": video_url,
+                        "format_id": vid_format,
+                    }
+                )
         if not formats:
-            for meta in (info.get('Metas') or []):
-                if meta.get('Key') == 'Encryption' and meta.get('Value') == '1':
-                    raise ExtractorError(
-                        'This video is DRM protected.', expected=True)
-            # Most likely because geo-blocked
-            raise ExtractorError('No downloadable videos found', expected=True)
-        self._sort_formats(formats)
+            for meta in info.get("Metas") or []:
+                if (
+                    not self.get_param("allow_unplayable_formats")
+                    and meta.get("Key") == "Encryption"
+                    and meta.get("Value") == "1"
+                ):
+                    self.report_drm(video_id)
+            # Most likely because geo-blocked if no formats and no DRM
 
         thumbnails = []
-        for picture in info.get('Pictures', []):
+        for picture in info.get("images", []):
             if not isinstance(picture, dict):
                 continue
-            pic_url = picture.get('URL')
+            pic_url = picture.get("tile")
             if not pic_url:
                 continue
             thumbnail = {
-                'url': pic_url,
+                "url": pic_url,
             }
-            pic_size = picture.get('PicSize', '')
-            m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
+            pic_size = picture.get("PicSize", "")
+            m = re.search(r"(?P<width>\d+)[xX](?P<height>\d+)", pic_size)
             if m:
-                thumbnail.update({
-                    'width': int(m.group('width')),
-                    'height': int(m.group('height')),
-                })
+                thumbnail.update(
+                    {
+                        "width": int(m.group("width")),
+                        "height": int(m.group("height")),
+                    }
+                )
             thumbnails.append(thumbnail)
 
         def counter(prefix):
             return int_or_none(
-                info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))
+                info.get(prefix + "Counter") or info.get(prefix.lower() + "_counter")
+            )
 
         return {
-            'id': video_id,
-            'title': title,
-            'description': strip_or_none(info.get('Description')),
-            'duration': int_or_none(info.get('Duration')),
-            'timestamp': parse_iso8601(info.get('CreationDate') or None),
-            'average_rating': float_or_none(info.get('Rating')),
-            'view_count': counter('View'),
-            'like_count': counter('Like'),
-            'thumbnails': thumbnails,
-            'formats': formats,
+            "id": video_id,
+            "title": title,
+            "description": strip_or_none(info.get("Description")),
+            "duration": int_or_none(info.get("Duration")),
+            "timestamp": parse_iso8601(info.get("CreationDate") or None),
+            "average_rating": float_or_none(info.get("Rating")),
+            "view_count": counter("View"),
+            "like_count": counter("Like"),
+            "thumbnails": thumbnails,
+            "formats": formats,
         }
 
 
 class MeWatchIE(InfoExtractor):
-    IE_NAME = 'mewatch'
-    _VALID_URL = r'https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
-        'info_dict': {
-            'id': '1008625',
-            'ext': 'mp4',
-            'title': 'Recipe Of Life 味之道',
-            'timestamp': 1603306526,
-            'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
-            'upload_date': '20201021',
+    IE_NAME = "mewatch"
+    _VALID_URL = (
+        r"https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)"
+    )
+    _TESTS = [
+        {
+            "url": "https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371",
+            "info_dict": {
+                "id": "1008625",
+                "ext": "mp4",
+                "title": "Recipe Of Life 味之道",
+                "timestamp": 1603306526,
+                "description": "md5:6e88cde8af2068444fc8e1bc3ebf257c",
+                "upload_date": "20201021",
+            },
+            "params": {
+                "skip_download": "m3u8 download",
+            },
         },
-        'params': {
-            'skip_download': 'm3u8 download',
+        {
+            "url": "https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232",
+            "only_matching": True,
         },
-    }, {
-        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
-        'only_matching': True,
-    }, {
-        'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
-        'only_matching': True,
-    }]
+        {
+            "url": "https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232",
+            "only_matching": True,
+        },
+        {
+            "url": "https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759",
+            "only_matching": True,
+        },
+    ]
 
     def _real_extract(self, url):
         item_id = self._match_id(url)
-        custom_id = self._download_json(
-            'https://cdn.mewatch.sg/api/items/' + item_id,
-            item_id, query={'segments': 'all'})['customId']
-        return self.url_result(
-            'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)
+        return self.url_result("toggle:" + item_id, ToggleIE.ie_key(), item_id)
+
+        print(f"[debug]{item_id}")
+        xdata = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + item_id,
+            item_id,
+            query={"segments": "all", "lang": "en", "ff": "idp,ldp,rpt,cd"},
+        )
+        from pprint import pprint
+
+        pprint(xdata)
+        custom_id = xdata["customId"]
+        print(f"[debug]{custom_id}")
+        return self.url_result("toggle:" + custom_id, ToggleIE.ie_key(), custom_id)

youtube_dl/extractor/youtube.py

@@ -692,9 +692,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         'invidious': '|'.join(_INVIDIOUS_SITES),
     }
     _PLAYER_INFO_RE = (
-        r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})//(?:tv-)?player',
-        r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
-        r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
+        r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/(?:tv-)?player',
+        r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias(?:_tce)?\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
+        r'\b(?P<id>vfl[a-zA-Z0-9_-]{6,})\b.*?\.js$',
     )
     _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
 
@@ -1626,15 +1626,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         """ Return a string representation of a signature """
         return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
 
-    @classmethod
-    def _extract_player_info(cls, player_url):
-        for player_re in cls._PLAYER_INFO_RE:
-            id_m = re.search(player_re, player_url)
-            if id_m:
-                break
-        else:
-            raise ExtractorError('Cannot identify player %r' % player_url)
-        return id_m.group('id')
+    def _extract_player_info(self, player_url):
+        try:
+            return self._search_regex(
+                self._PLAYER_INFO_RE, player_url, 'player info', group='id')
+        except ExtractorError as e:
+            raise ExtractorError(
+                'Cannot identify player %r' % (player_url,), cause=e)
 
     def _load_player(self, video_id, player_url, fatal=True, player_id=None):
         if not player_id:
@@ -1711,6 +1709,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 '    return %s\n') % (signature_id_tuple, expr_code)
         self.to_screen('Extracted signature function:\n' + code)
 
+    def _extract_sig_fn(self, jsi, funcname):
+        var_ay = self._search_regex(
+            r'''(?x)
+                (?:\*/|\{|\n|^)\s*(?:'[^']+'\s*;\s*)
+                    (var\s*[\w$]+\s*=\s*(?:
+                        ('|")(?:\\\2|(?!\2).)+\2\s*\.\s*split\(\s*('|")\W+\3\s*\)|
+                        \[\s*(?:('|")(?:\\\4|(?!\4).)*\4\s*(?:(?=\])|,\s*))+\]
+                    ))(?=\s*[,;])
+            ''', jsi.code, 'useful values', default='')
+
+        sig_fn = jsi.extract_function_code(funcname)
+
+        if var_ay:
+            sig_fn = (sig_fn[0], ';\n'.join((var_ay, sig_fn[1])))
+
+        return sig_fn
+
     def _parse_sig_js(self, jscode):
         # Examples where `sig` is funcname:
         # sig=function(a){a=a.split(""); ... ;return a.join("")};
@@ -1736,8 +1751,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
-        initial_function = jsi.extract_function(funcname)
-        return lambda s: initial_function([s])
+
+        initial_function = self._extract_sig_fn(jsi, funcname)
+
+        func = jsi.extract_function_from_code(*initial_function)
+
+        return lambda s: func([s])
 
     def _cached(self, func, *cache_id):
         def inner(*args, **kwargs):
@@ -1856,15 +1875,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
 
-        var_ay = self._search_regex(
-            r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"(?:\\"|[^"])+"\s*\.\s*split\("\W+"\))(?=\s*[,;])',
-            jsi.code, 'useful values', default='')
-
         func_name = self._extract_n_function_name(jsi.code)
 
-        func_code = jsi.extract_function_code(func_name)
-        if var_ay:
-            func_code = (func_code[0], ';\n'.join((var_ay, func_code[1])))
+        func_code = self._extract_sig_fn(jsi, func_name)
 
         if player_id:
             self.cache.store('youtube-nsig', player_id, func_code)
@@ -2136,7 +2149,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     video_details = merge_dicts(*traverse_obj(
                         (player_response, api_player_response),
                         (Ellipsis, 'videoDetails', T(dict))))
-                    player_response.update(api_player_response or {})
+                    player_response.update(filter_dict(
+                        api_player_response or {}, cndn=lambda k, _: k != 'captions'))
                     player_response['videoDetails'] = video_details
 
         def is_agegated(playability):
@@ -2566,8 +2580,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         }
 
         pctr = traverse_obj(
-            player_response,
-            ('captions', 'playerCaptionsTracklistRenderer', T(dict)))
+            (player_response, api_player_response),
+            (Ellipsis, 'captions', 'playerCaptionsTracklistRenderer', T(dict)))
         if pctr:
             def process_language(container, base_url, lang_code, query):
                 lang_subs = []
@@ -2584,20 +2598,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             def process_subtitles():
                 subtitles = {}
                 for caption_track in traverse_obj(pctr, (
-                        'captionTracks', lambda _, v: v.get('baseUrl'))):
+                        Ellipsis, 'captionTracks', lambda _, v: (
+                            v.get('baseUrl') and v.get('languageCode')))):
                     base_url = self._yt_urljoin(caption_track['baseUrl'])
                     if not base_url:
                         continue
+                    lang_code = caption_track['languageCode']
                     if caption_track.get('kind') != 'asr':
-                        lang_code = caption_track.get('languageCode')
-                        if not lang_code:
-                            continue
                         process_language(
                             subtitles, base_url, lang_code, {})
                         continue
                     automatic_captions = {}
+                    process_language(
+                        automatic_captions, base_url, lang_code, {})
                     for translation_language in traverse_obj(pctr, (
-                            'translationLanguages', lambda _, v: v.get('languageCode'))):
+                            Ellipsis, 'translationLanguages', lambda _, v: v.get('languageCode'))):
                         translation_language_code = translation_language['languageCode']
                         process_language(
                             automatic_captions, base_url, translation_language_code,

youtube_dl/jsinterp.py

@@ -678,7 +678,7 @@ class JSInterpreter(object):
             return len(obj)
         try:
             return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
-        except (TypeError, KeyError, IndexError) as e:
+        except (TypeError, KeyError, IndexError, ValueError) as e:
             # allow_undefined is None gives correct behaviour
             if allow_undefined or (
                     allow_undefined is None and not isinstance(e, TypeError)):
@@ -1038,6 +1038,10 @@ class JSInterpreter(object):
                     left_val = self._index(left_val, idx)
             if isinstance(idx, float):
                 idx = int(idx)
+            if isinstance(left_val, list) and len(left_val) <= int_or_none(idx, default=-1):
+                # JS Array is a sparsely assignable list
+                # TODO: handle extreme sparsity without memory bloat, eg using auxiliary dict
+                left_val.extend((idx - len(left_val) + 1) * [JS_Undefined])
             left_val[idx] = self._operator(
                 m.group('op'), self._index(left_val, idx) if m.group('op') else None,
                 m.group('expr'), expr, local_vars, allow_recursion)
@@ -1204,9 +1208,10 @@ class JSInterpreter(object):
                 elif member == 'join':
                     assertion(isinstance(obj, list), 'must be applied on a list')
                     assertion(len(argvals) <= 1, 'takes at most one argument')
-                    return (',' if len(argvals) == 0 else argvals[0]).join(
-                        ('' if x in (None, JS_Undefined) else _js_toString(x))
-                        for x in obj)
+                    return (',' if len(argvals) == 0 or argvals[0] in (None, JS_Undefined)
+                            else argvals[0]).join(
+                                ('' if x in (None, JS_Undefined) else _js_toString(x))
+                                for x in obj)
                 elif member == 'reverse':
                     assertion(not argvals, 'does not take any arguments')
                     obj.reverse()
@@ -1364,19 +1369,21 @@ class JSInterpreter(object):
         code, _ = self._separate_at_paren(func_m.group('code'))  # refine the match
         return self.build_arglist(func_m.group('args')), code
 
-    def extract_function(self, funcname):
+    def extract_function(self, funcname, *global_stack):
         return function_with_repr(
-            self.extract_function_from_code(*self.extract_function_code(funcname)),
+            self.extract_function_from_code(*itertools.chain(
+                self.extract_function_code(funcname), global_stack)),
             'F<%s>' % (funcname,))
 
     def extract_function_from_code(self, argnames, code, *global_stack):
         local_vars = {}
 
+        start = None
         while True:
-            mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code)
+            mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code[start:])
             if mobj is None:
                 break
-            start, body_start = mobj.span()
+            start, body_start = ((start or 0) + x for x in mobj.span())
             body, remaining = self._separate_at_paren(code[body_start - 1:])
             name = self._named_object(local_vars, self.extract_function_from_code(
                 [x.strip() for x in mobj.group('args').split(',')],