Merge 2730e55b36d299e17beacc4aaa8fa9441932c8aa into da7223d4aa42ff9fc680b0951d043dd03cec2d30

* improve extraction of global "useful data" Array from player JS
* also handle tv-player and add tests: thx seproDev (yt-dlp/yt-dlp#12684)

Co-Authored-By: sepro <sepro@sepr0.com>

test/test_youtube_signature.py

@@ -232,8 +232,32 @@ _NSIG_TESTS = [
         'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
     ),
     (
-        'https://www.youtube.com/s/player/91201489/player_ias_tce.vflset/en_US/base.js',
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'U48vOZHaeYS6vO',
+        'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
+    ),
+    (
+        'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
+        'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
+    ),
+    (
+        'https://www.youtube.com/s/player/d50f54ef/player_ias_tce.vflset/en_US/base.js',
+        'Ha7507LzRmH3Utygtj', 'XFTb2HoeOE5MHg',
+    ),
+    (
+        'https://www.youtube.com/s/player/074a8365/player_ias_tce.vflset/en_US/base.js',
+        'Ha7507LzRmH3Utygtj', 'ufTsrE0IVYrkl8v',
+    ),
+    (
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+        'N5uAlLqm0eg1GyHO', 'dCBQOejdq5s-ww',
+    ),
+    (
+        'https://www.youtube.com/s/player/69f581a5/tv-player-ias.vflset/tv-player-ias.js',
+        '-qIP447rVlTTwaZjY', 'KNcGOksBAvwqQg',
+    ),
+    (
+        'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
+        'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
     ),
 ]
 

youtube_dl/extractor/extractors.py

@@ -810,6 +810,10 @@ from .nhk import (
     NhkVodIE,
     NhkVodProgramIE,
 )
+from .nhkRadio import (
+    NhkRadioIE,
+    NhkRadioProgramIE
+)
 from .nhl import NHLIE
 from .nick import (
     NickIE,

youtube_dl/extractor/nhkRadio.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+from .common import InfoExtractor
+from ..utils import ExtractorError, parse_iso8601
+from ..compat import compat_HTTPError
+import re
+
+
+class NhkRadioBase(InfoExtractor):
+    def _get_json_meta(self, program_id, corner_id):
+        program_corner_id = program_id + "_" + corner_id
+        try:
+            data = self._download_json(
+                "https://www.nhk.or.jp/radioondemand/json/"
+                + program_id
+                + "/bangumi_"
+                + program_corner_id
+                + ".json",
+                program_corner_id,
+            )
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+                raise ExtractorError("The invalid url", expected=True)
+        return data
+
+    def _extract_program(self, info, program_corner_id):
+        id = program_corner_id + "_" + info.get("headline_id")
+        file = info.get("file_list")[0]
+        formats = self._extract_m3u8_formats(file.get("file_name", None), id, "m4a", entry_protocol="m3u8_native", m3u8_id="hls")
+        self._sort_formats(formats)
+        return {
+            "id": id,
+            "title": file.get("file_title"),
+            "formats": formats,
+            "timestamp": parse_iso8601(file.get("close_time")),
+        }
+
+
+class NhkRadioIE(NhkRadioBase):
+    _VALID_URL = r"https?://www\.nhk\.or\.jp/radio/player/ondemand\.html\?p=(?P<program_id>\d+)_(?P<corner_id>\d+)_(?P<headline_id>\d+)"
+
+    _TESTS = [
+        {
+            "url": "https://www.nhk.or.jp/radio/player/ondemand.html?p=4812_01_2898188",
+            "info_dict": {
+                "id": "4812_01_2898188",
+                "ext": "m4a",
+                "title": "世界へ発信！ニュースで英語術　＃２０９▽“首相長男から接待”　総務省１１人を処分",
+                "upload_date": str,
+                "timestamp": int,
+            },
+        },
+        {
+            "url": "https://www.nhk.or.jp/radio/player/ondemand.html?p=0444_01_2890944",
+            "info_dict": {
+                "ext": "m4a",
+                "id": "0444_01_2890944",
+                "title": "歌謡スクランブル　春色コレクション（３）　▽尾崎亜美",
+                "upload_date": str,
+                "timestamp": int,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        program_id, corner_id, headline_id = re.match(self._VALID_URL, url).groups()
+        program_corner_id = program_id + "_" + corner_id
+        data = self._download_json(
+            "https://www.nhk.or.jp/radioondemand/json/"
+            + program_id
+            + "/bangumi_"
+            + program_corner_id
+            + ".json",
+            program_corner_id,
+        )
+        for detail in data["main"]["detail_list"]:
+            if headline_id == detail.get("headline_id"):
+                return self._extract_program(detail, program_corner_id)
+        raise ExtractorError("The program not found", expected=True)
+
+
+class NhkRadioProgramIE(NhkRadioBase):
+    _VALID_URL = r"https?://www\.nhk\.or\.jp/radio/ondemand/detail\.html\?p=(?P<program_id>\d+)_(?P<corner_id>\d+)"
+
+    _TESTS = [
+        {
+            "url": "https://www.nhk.or.jp/radio/ondemand/detail.html?p=0164_01",
+            "info_dict": {"title": "青春アドベンチャー", "id": "0164_01"},
+            "playlist_mincount": 5,
+        },
+        {
+            "url": "https://www.nhk.or.jp/radio/ondemand/detail.html?p=0455_01",
+            "info_dict": {"id": "0455_01", "title": "弾き語りフォーユー"},
+            "playlist_mincount": 5,
+        },
+    ]
+
+    def _real_extract(self, url):
+        program_id, corner_id = re.match(self._VALID_URL, url).groups()
+        data = self._get_json_meta(program_id, corner_id)
+        entries = []
+        for detail in data["main"]["detail_list"]:
+            entries.append(self._extract_program(detail, program_id + "_" + corner_id))
+        return self.playlist_result(
+            entries, program_id + "_" + corner_id, data["main"]["program_name"]
+        )

youtube_dl/extractor/youtube.py

@@ -91,12 +91,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'IOS',
-                    'clientVersion': '19.45.4',
+                    'clientVersion': '20.10.4',
                     'deviceMake': 'Apple',
                     'deviceModel': 'iPhone16,2',
-                    'userAgent': 'com.google.ios.youtube/19.45.4 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
+                    'userAgent': 'com.google.ios.youtube/20.10.4 (iPhone16,2; U; CPU iOS 18_3_2 like Mac OS X;)',
                     'osName': 'iPhone',
-                    'osVersion': '18.1.0.22B83',
+                    'osVersion': '18.3.2.22D82',
                 },
             },
             'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
@@ -109,7 +109,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'MWEB',
-                    'clientVersion': '2.20241202.07.00',
+                    'clientVersion': '2.20250311.03.00',
                     # mweb previously did not require PO Token with this UA
                     'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)',
                 },
@@ -122,7 +122,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'TVHTML5',
-                    'clientVersion': '7.20250120.19.00',
+                    'clientVersion': '7.20250312.16.00',
                     'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
                 },
             },
@@ -133,7 +133,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'WEB',
-                    'clientVersion': '2.20241126.01.00',
+                    'clientVersion': '2.20250312.04.00',
                 },
             },
             'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
@@ -692,7 +692,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         'invidious': '|'.join(_INVIDIOUS_SITES),
     }
     _PLAYER_INFO_RE = (
-        r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
+        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$',
         r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
     )
@@ -1857,7 +1857,7 @@ 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\("\{"\))(?=\s*[,;])',
+            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)