[ie/youtube] Set tv_samsung as a default client (#17805)

Authored by: ruben1PvP

.github/actionlint.yml

@@ -22,3 +22,15 @@ paths:
     ignore:
       # https://github.com/rhysd/actionlint/issues/657
       - 'unexpected key "queue" for "concurrency" section.+'
+  .github/workflows/release-master.yml:
+    ignore:
+      # https://github.com/rhysd/actionlint/issues/711
+      - 'reusable workflow call .+ at "uses" is not following the format.+'
+  .github/workflows/release-nightly.yml:
+    ignore:
+      # https://github.com/rhysd/actionlint/issues/711
+      - 'reusable workflow call .+ at "uses" is not following the format.+'
+  .github/workflows/release.yml:
+    ignore:
+      # https://github.com/rhysd/actionlint/issues/711
+      - 'reusable workflow call .+ at "uses" is not following the format.+'

.github/workflows/build.yml

@@ -265,7 +265,7 @@ jobs:
 
       - name: Set up QEMU
         if: matrix.qemu_platform
-        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8  # v4.2.0
+        uses: docker/setup-qemu-action@99012661954931238ded8c8b007157a8430204e1  # v4.4.0
         with:
           image: tonistiigi/binfmt:qemu-v10.0.4-56@sha256:30cc9a4d03765acac9be2ed0afc23af1ad018aed2c28ea4be8c2eb9afe03fbd1
           cache-image: false

.github/workflows/codeql.yml

@@ -36,12 +36,12 @@ jobs:
         persist-credentials: false
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd  # v4.37.7
+      uses: github/codeql-action/init@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2  # v4.38.2
       with:
         languages: ${{ matrix.language }}
         build-mode: none
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@ff2f1c621b7f889edc0d3c761ac2e6a3f8cdb0dd  # v4.37.7
+      uses: github/codeql-action/analyze@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2  # v4.38.2
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/release-master.yml

@@ -24,7 +24,7 @@ jobs:
     permissions:
       contents: write  # May be needed to publish release
       id-token: write  # Needed for trusted publishing
-    uses: ./.github/workflows/release.yml
+    uses: $/.github/workflows/release.yml
     with:
       prerelease: true
       source: ${{ (github.repository != 'yt-dlp/yt-dlp' && vars.MASTER_ARCHIVE_REPO) || 'master' }}

.github/workflows/release-nightly.yml

@@ -77,7 +77,7 @@ jobs:
     permissions:
       contents: write  # May be needed to publish release
       id-token: write  # Needed for trusted publishing
-    uses: ./.github/workflows/release.yml
+    uses: $/.github/workflows/release.yml
     with:
       prerelease: true
       source: ${{ (github.repository != 'yt-dlp/yt-dlp' && vars.NIGHTLY_ARCHIVE_REPO) || 'nightly' }}

.github/workflows/release.yml

@@ -155,7 +155,7 @@ jobs:
     needs: [prepare]
     permissions:
       contents: read
-    uses: ./.github/workflows/build.yml
+    uses: $/.github/workflows/build.yml
     with:
       version: ${{ needs.prepare.outputs.version }}
       channel: ${{ needs.prepare.outputs.channel }}

.github/workflows/test-workflows.yml

@@ -83,7 +83,7 @@ jobs:
           persist-credentials: false
 
       - name: Run zizmor
-        uses: zizmorcore/zizmor-action@3dc1ecc9bcb9e94e9b2c709687979e1298497054  # v0.6.2
+        uses: zizmorcore/zizmor-action@cc914d7f3750a2d13d75c7f184a1060aa0e9d482  # v0.6.4
         with:
           advanced-security: false
           persona: pedantic

README.md

@@ -1859,7 +1859,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube/_base.py](https://github.com/yt-dlp/yt-dlp/blob/415b4c9f955b1a0391204bd24a7132590e7b3bdb/yt_dlp/extractor/youtube/_base.py#L402-L409) for the list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `visionos`, `android`, `android_vr`, `tv`, `tv_downgraded`, and `tv_simply`. By default, `visionos,web` is used. If no JavaScript runtime/engine is available, then `web` is omitted. If logged-in cookies are passed to yt-dlp, then `web_embedded,tv_downgraded,web` is used for free accounts and `web_creator,tv_downgraded,web` is used for premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only successfully works around the age-restriction sometimes (e.g. if the video is embeddable). The `tv_downgraded` and `web_embedded` clients may be added as a fallback if `android_vr` or `visionos` is unable to access a video. The `web_creator` client is added for age-restricted videos if account age-verification is required. Some clients, such as `web_creator` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-web`
+* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `visionos`, `android`, `android_vr`, `tv`, `tv_downgraded`, `tv_samsung`, and `tv_simply`. By default, `tv_samsung,visionos,web` is used. If no JavaScript runtime/engine is available, then `web` and `tv_samsung` are omitted. If logged-in cookies are passed to yt-dlp, then `web_embedded,tv_samsung,web` is used for free accounts and `web_creator,tv_samsung,web` is used for premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only successfully works around the age-restriction sometimes (e.g. if the video is embeddable). The `web_embedded` client may be added as a fallback if `android_vr` or `visionos` is unable to access a video. The `web_creator` client is added for age-restricted videos if account age-verification is required. Some clients, such as `web_creator` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-web`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `webpage_skip`: Skip extraction of embedded webpage data. One or both of `player_response`, `initial_data`. These options are for testing purposes and don't skip any network requests. Neither is skipped by default; however, if a `player_js_version` value other than `actual` is used, then `webpage_skip=player_response` is implied
 * `webpage_client`: Client to use for the video webpage request. One of `web` (default) or `web_safari`
@@ -1978,6 +1978,9 @@ The following extractors use this feature:
 * `client`: Client to extract video data from. The currently available clients are `android` and `web`. Only one client can be used. The `web` client is used by default, and it only works with account cookies or login credentials. The `android` client only works with previously cached OAuth tokens
 * `original_format_policy`: Policy for when to try extracting original formats. One of `always`, `never`, or `auto`. The default `auto` policy tries to avoid exceeding the web client's API rate-limit by only making an extra request when Vimeo publicizes the video's downloadability
 
+#### adn
+* `profile_id`: The numeric ID of the premium account profile that will be used to download videos (default: `1`)
+
 #### zan
 * `split_angles`: Split multi-angle streams into separate angle formats. Forces re-encoding of the video stream during download, and requires ffmpeg. Either `true` or `false` (default)
 

bundle/requirements/default.txt

@@ -240,6 +240,10 @@ mutagen==1.48.1 \
     --hash=sha256:4f077fe87d3fc7fba259aa63d8c026b18382ca6a42ef37c61e16f1b1b5b82fe7 \
     --hash=sha256:8f95637ab9f6f305cec6bd1294e197debe207998e3e068596563c74f86b0a173
     # via yt-dlp
+pycparser==3.0 ; implementation_name != 'PyPy' and implementation_name != 'cpython' \
+    --hash=sha256:600f49d217304a5902ac3c37e1281c9fe94e4d0489de643a9504c5cdfdfc6b29 \
+    --hash=sha256:b727414169a36b7d524c1c3e31839a521725078d7b2ff038656844266160a992
+    # via cffi
 pycryptodomex==3.23.0 \
     --hash=sha256:02d87b80778c171445d67e23d1caef279bf4b25c3597050ccd2e13970b57fd51 \
     --hash=sha256:06698f957fe1ab229a99ba2defeeae1c09af185baa909a31a5d1f9d42b1aaed6 \

devscripts/prepare_manpage.py

@@ -66,8 +66,7 @@ def convert_code_blocks(readme):
 
 def move_sections(readme):
     MOVE_TAG_TEMPLATE = '<!-- MANPAGE: MOVE "%s" SECTION HERE -->'
-    sections = re.findall(r'(?m)^%s$' % (
-        re.escape(MOVE_TAG_TEMPLATE).replace(r'\%', '%') % '(.+)'), readme)
+    sections = re.findall(r'(?m)^%s$' % (re.escape(MOVE_TAG_TEMPLATE) % '(.+)'), readme)
 
     for section_name in sections:
         move_tag = MOVE_TAG_TEMPLATE % section_name

devscripts/update_requirements.py

@@ -77,7 +77,7 @@ BUNDLE_TARGETS = {
     'default': Target(
         extras=['default'],
         # PyPy bundles cffi, which is a transitive dep of brotlicffi, which is only required for PyPy
-        prune_packages=['cffi'],
+        omit_packages=['cffi'],
     ),
     'curl-cffi': Target(
         extras=['default', 'curl-cffi'],
@@ -643,7 +643,7 @@ def update_requirements(
             extras=[extra_name],
             bare=True,
             # PyPy bundles cffi, which is a transitive dep of brotlicffi, which is only required for PyPy
-            prune_packages=['cffi'] if extra_name == 'default' else [],
+            omit_packages=['cffi'] if extra_name == 'default' else [],
         ).splitlines()
 
     # Write the finalized pyproject.toml

pyproject.toml

@@ -74,6 +74,7 @@ pin = [
     "charset-normalizer==3.5.0",
     "idna==3.18",
     "mutagen==1.48.1",
+    "pycparser==3.0 ; implementation_name != 'PyPy' and implementation_name != 'cpython'",
     "pycryptodomex==3.23.0",
     "requests==2.34.2",
     "urllib3==2.7.0",

test/helper.py

@@ -3,7 +3,6 @@ import hashlib
 import json
 import os.path
 import re
-import ssl
 import sys
 import types
 
@@ -318,36 +317,6 @@ def expect_info_dict(self, got_dict, expected_dict):
             'Missing keys in test definition: {}'.format(', '.join(sorted(missing_keys))))
 
 
-def assertRegexpMatches(self, text, regexp, msg=None):
-    if hasattr(self, 'assertRegexp'):
-        return self.assertRegexp(text, regexp, msg)
-    else:
-        m = re.match(regexp, text)
-        if not m:
-            note = f'Regexp didn\'t match: {regexp!r} not found'
-            if len(text) < 1000:
-                note += f' in {text!r}'
-            if msg is None:
-                msg = note
-            else:
-                msg = note + ', ' + msg
-            self.assertTrue(m, msg)
-
-
-def assertGreaterEqual(self, got, expected, msg=None):
-    if not (got >= expected):
-        if msg is None:
-            msg = f'{got!r} not greater than or equal to {expected!r}'
-        self.assertTrue(got >= expected, msg)
-
-
-def assertLessEqual(self, got, expected, msg=None):
-    if not (got <= expected):
-        if msg is None:
-            msg = f'{got!r} not less than or equal to {expected!r}'
-        self.assertTrue(got <= expected, msg)
-
-
 def assertEqual(self, got, expected, msg=None):
     if got != expected:
         if msg is None:
@@ -366,12 +335,7 @@ def expect_warnings(ydl, warnings_re):
 
 
 def http_server_port(httpd):
-    if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
-        # In Jython SSLSocket is not a subclass of socket.socket
-        sock = httpd.socket.sock
-    else:
-        sock = httpd.socket
-    return sock.getsockname()[1]
+    return httpd.server_address[1]
 
 
 def verify_address_availability(address):

test/test_YoutubeDL.py

@@ -15,7 +15,7 @@ import contextlib
 import copy
 import json
 
-from test.helper import FakeYDL, assertRegexpMatches, try_rm
+from test.helper import FakeYDL, try_rm
 from yt_dlp import YoutubeDL
 from yt_dlp.extractor.common import InfoExtractor
 from yt_dlp.postprocessor.common import PostProcessor
@@ -860,10 +860,10 @@ class TestYoutubeDL(unittest.TestCase):
     def test_format_note(self):
         ydl = YoutubeDL()
         self.assertEqual(ydl._format_note({}), '')
-        assertRegexpMatches(self, ydl._format_note({
+        self.assertRegex(ydl._format_note({
             'vbr': 10,
         }), r'^\s*10k$')
-        assertRegexpMatches(self, ydl._format_note({
+        self.assertRegex(ydl._format_note({
             'fps': 30,
         }), r'^30fps$')
 

test/test_devalue.py

@@ -7,10 +7,12 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
+import base64
 import datetime as dt
 import json
 import math
 import re
+import struct
 import unittest
 
 from yt_dlp.utils.jslib import devalue
@@ -84,10 +86,61 @@ TEST_CASES_EQUALS = [{
     'name': 'Uint8Array',
     'unparsed': [['Uint8Array', 'AQID']],
     'parsed': [1, 2, 3],
+}, {
+    'name': 'Uint8Array with ArrayBuffer reference',
+    'unparsed': [['Uint8Array', 1], ['ArrayBuffer', 'AQID']],
+    'parsed': [1, 2, 3],
+}, {
+    'name': 'Uint8Array with byte offset and element length',
+    'unparsed': [['Uint8Array', 1, 1, 2], ['ArrayBuffer', 'AQIDBAU=']],
+    'parsed': [2, 3],
+}, {
+    'name': 'Uint16Array with byte offset and element length',
+    'unparsed': [
+        ['Uint16Array', 1, 2, 2],
+        ['ArrayBuffer', base64.b64encode(struct.pack('=4H', 1, 2, 3, 4)).decode()],
+    ],
+    'parsed': [2, 3],
+}, {
+    'name': 'DataView with byte offset and byte length',
+    'unparsed': [['DataView', 1, 1, 2], ['ArrayBuffer', 'AQIDBAU=']],
+    'parsed': b'\x02\x03',
+}, {
+    'name': 'DataView with byte offset',
+    'unparsed': [['DataView', 1, 2], ['ArrayBuffer', 'AQIDBAU=']],
+    'parsed': b'\x03\x04\x05',
+}, {
+    'name': 'Float16Array',
+    'unparsed': [[
+        'Float16Array',
+        base64.b64encode(struct.pack('=2e', -2.0, 1.5)).decode(),
+    ]],
+    'parsed': [-2.0, 1.5],
+}, {
+    'name': 'Uint32Array',
+    'unparsed': [[
+        'Uint32Array',
+        base64.b64encode(struct.pack('=2I', 12345, 12345678)).decode(),
+    ]],
+    'parsed': [12345, 12345678],
+}, {
+    'name': 'BigInt64Array',
+    'unparsed': [[
+        'BigInt64Array',
+        base64.b64encode(struct.pack('=2q', -1, 2)).decode(),
+    ]],
+    'parsed': [-1, 2],
+}, {
+    'name': 'BigUint64Array',
+    'unparsed': [[
+        'BigUint64Array',
+        base64.b64encode(struct.pack('=2Q', 1, 2)).decode(),
+    ]],
+    'parsed': [1, 2],
 }, {
     'name': 'ArrayBuffer',
     'unparsed': [['ArrayBuffer', 'AQID']],
-    'parsed': [1, 2, 3],
+    'parsed': b'\x01\x02\x03',
 }, {
     'name': 'str (repetition)',
     'unparsed': [[1, 1], 'a string'],

test/test_download.py

@@ -13,8 +13,6 @@ import hashlib
 import json
 
 from test.helper import (
-    assertGreaterEqual,
-    assertLessEqual,
     expect_info_dict,
     expect_warnings,
     get_params,
@@ -201,8 +199,8 @@ def generator(test_case, tname):
             num_entries = len(res_dict.get('entries', []))
             if 'playlist_mincount' in test_case:
                 mincount = test_case['playlist_mincount']
-                assertGreaterEqual(
-                    self, num_entries, mincount,
+                self.assertGreaterEqual(
+                    num_entries, mincount,
                     f'Expected at least {mincount} entries in playlist {test_url}, but got only {num_entries}')
             if 'playlist_count' in test_case:
                 count = test_case['playlist_count']
@@ -212,8 +210,8 @@ def generator(test_case, tname):
                     f'Expected exactly {count} entries in playlist {test_url}, but got {got}')
             if 'playlist_maxcount' in test_case:
                 maxcount = test_case['playlist_maxcount']
-                assertLessEqual(
-                    self, num_entries, maxcount,
+                self.assertLessEqual(
+                    num_entries, maxcount,
                     f'Expected at most {maxcount} entries in playlist {test_url}, but got more')
             if 'playlist_duration_sum' in test_case:
                 got_duration = sum(e['duration'] for e in res_dict['entries'])
@@ -241,8 +239,8 @@ def generator(test_case, tname):
                         if params.get('test'):
                             expected_minsize = max(expected_minsize, 10000)
                         got_fsize = os.path.getsize(tc_filename)
-                        assertGreaterEqual(
-                            self, got_fsize, expected_minsize,
+                        self.assertGreaterEqual(
+                            got_fsize, expected_minsize,
                             f'Expected {tc_filename} to be at least {format_bytes(expected_minsize)}, '
                             f'but it\'s only {format_bytes(got_fsize)} ')
                     if 'md5' in tc:

test/test_networking.py

@@ -180,6 +180,11 @@ class HTTPTestRequestHandler(http.server.BaseHTTPRequestHandler):
             self.send_header('Location', '/a/b/./../../headers')
             self.send_header('Content-Length', '0')
             self.end_headers()
+        elif self.path == '/a/b/redirect_relative_dotsegments':
+            self.send_response(301)
+            self.send_header('Location', '../../headers')
+            self.send_header('Content-Length', '0')
+            self.end_headers()
         elif self.path == '/redirect_dotsegments_absolute':
             self.send_response(301)
             # redirect to /headers but with dot segments before - absolute url
@@ -338,7 +343,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
         https_server_thread.start()
 
         with handler(verify=False) as rh:
-            with pytest.raises(SSLError, match=r'(?i)ssl(?:v3|/tls).alert.handshake.failure') as exc_info:
+            with pytest.raises(SSLError, match=r'(?i)(?:sslv3|tls).alert.handshake.failure') as exc_info:
                 validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 
@@ -412,6 +417,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
     @pytest.mark.parametrize('path', [
         '/a/b/./../../headers',
         '/redirect_dotsegments',
+        '/a/b/redirect_relative_dotsegments',
         # https://github.com/yt-dlp/yt-dlp/issues/9020
         '/redirect_dotsegments_absolute',
     ])
@@ -984,28 +990,15 @@ class TestUrllibRequestHandler(TestRequestHandlerBase):
             ):
                 validate_and_send(rh, Request(f'https://127.0.0.1:{self.https_port}/headers'))
 
-    @pytest.mark.parametrize('req,match,version_check', [
+    @pytest.mark.parametrize('req,match', [
         # https://github.com/python/cpython/blob/987b712b4aeeece336eed24fcc87a950a756c3e2/Lib/http/client.py#L1256
-        # bpo-39603: Check implemented in 3.7.9+, 3.8.5+
-        (
-            Request('http://127.0.0.1', method='GET\n'),
-            'method can\'t contain control characters',
-            lambda v: v < (3, 7, 9) or (3, 8, 0) <= v < (3, 8, 5),
-        ),
+        (Request('http://127.0.0.1', method='GET\n'), 'method can\'t contain control characters'),
         # https://github.com/python/cpython/blob/987b712b4aeeece336eed24fcc87a950a756c3e2/Lib/http/client.py#L1265
-        # bpo-38576: Check implemented in 3.7.8+, 3.8.3+
-        (
-            Request('http://127.0.0. 1', method='GET'),
-            'URL can\'t contain control characters',
-            lambda v: v < (3, 7, 8) or (3, 8, 0) <= v < (3, 8, 3),
-        ),
+        (Request('http://127.0.0. 1', method='GET'), 'URL can\'t contain control characters'),
         # https://github.com/python/cpython/blob/987b712b4aeeece336eed24fcc87a950a756c3e2/Lib/http/client.py#L1288C31-L1288C50
-        (Request('http://127.0.0.1', headers={'foo\n': 'bar'}), 'Invalid header name', None),
+        (Request('http://127.0.0.1', headers={'foo\n': 'bar'}), 'Invalid header name'),
     ])
-    def test_httplib_validation_errors(self, handler, req, match, version_check):
-        if version_check and version_check(sys.version_info):
-            pytest.skip(f'Python {sys.version} version does not have the required validation for this test.')
-
+    def test_httplib_validation_errors(self, handler, req, match):
         with handler() as rh:
             with pytest.raises(RequestError, match=match) as exc_info:
                 validate_and_send(rh, req)

test/test_networking_utils.py

@@ -63,13 +63,13 @@ class TestNetworkingUtils:
             'username': 'user',
             'password': '',
         }),
-        ('socks4://u%40ser:pa%20ss@127.0.0.1:1080', {
+        ('socks4://u%40ser+name:pa%20ss+word@127.0.0.1:1080', {
             'proxytype': ProxyType.SOCKS4,
             'addr': '127.0.0.1',
             'port': 1080,
             'rdns': False,
-            'username': 'u@ser',
-            'password': 'pa ss',
+            'username': 'u@ser+name',
+            'password': 'pa ss+word',
         }),
         ('socks4a://:pa%20ss@127.0.0.1', {
             'proxytype': ProxyType.SOCKS4A,

test/test_traversal.py

@@ -546,6 +546,18 @@ class TestTraversalHelpers:
                 {'url': 'https://example.com/subs/de4'},
             ],
         }, 'non str types should be replaced by default id'
+        assert traverse_obj([
+            {'name': '', 'ext': '', 'url': 'https://example.com/subs/en'},
+        ], [..., {
+            'id': 'name',
+            'ext': 'ext',
+            'url': 'url',
+        }, all, {subs_list_to_dict(lang='en', ext='vtt')}]) == {
+            'en': [{
+                'ext': 'vtt',
+                'url': 'https://example.com/subs/en',
+            }],
+        }, 'empty id and ext should be replaced by defaults'
 
     def test_trim_str(self):
         with pytest.raises(TypeError):

test/test_utils.py

@@ -9,6 +9,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import contextlib
 import datetime as dt
+import email.message
 import io
 import itertools
 import json
@@ -48,6 +49,7 @@ from yt_dlp.utils import (
     determine_ext,
     determine_file_encoding,
     dfxp2srt,
+    disposition_filename,
     encode_base_n,
     encode_compat_str,
     expand_path,
@@ -107,6 +109,7 @@ from yt_dlp.utils import (
     sanitize_filename,
     sanitize_path,
     sanitize_url,
+    setproctitle,
     shell_quote,
     strftime_or_none,
     smuggle_url,
@@ -125,6 +128,7 @@ from yt_dlp.utils import (
     url_basename,
     url_or_none,
     urlencode_postdata,
+    urlhandle_detect_ext,
     urljoin,
     urshift,
     variadic,
@@ -613,6 +617,14 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(res_url, url)
         self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
 
+    @unittest.mock.patch('ctypes.cdll.LoadLibrary')
+    def test_setproctitle(self, load_library):
+        for title in ('yt-dlp', 'café'):
+            with self.subTest(title=title):
+                setproctitle(title)
+                buf = load_library.return_value.prctl.call_args.args[1]
+                self.assertEqual(bytes(buf), title.encode() + b'\0')
+
     def test_shell_quote(self):
         args = ['ffmpeg', '-i', 'ñ€ß\'.mp4']
         self.assertEqual(
@@ -1347,15 +1359,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
         self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
         self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
-        # "Narrow" Python builds don't support unicode code points outside BMP.
-        try:
-            chr(0x10000)
-            supports_outside_bmp = True
-        except ValueError:
-            supports_outside_bmp = False
-        if supports_outside_bmp:
         self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
-        # Malformed HTML should not break attributes extraction on older Python
+        # Malformed HTML should not break attribute extraction
         self.assertEqual(extract_attributes('<mal"formed/>'), {})
 
     def test_clean_html(self):
@@ -2121,6 +2126,32 @@ Line 1
         self.assertEqual(get_compatible_ext(
             vcodecs=['av1'], acodecs=['mp4a'], vexts=['webm'], aexts=['m4a'], preferences=('webm', 'mkv')), 'mkv')
 
+    def test_disposition_filename(self):
+        test_cases = (
+            (None, None),
+            ('attachment', None),
+            ('attachment; filename="video.mp4"', 'video.mp4'),
+            ('attachment; FILENAME="video.mp4"', 'video.mp4'),
+            ('inline; filename=video.mp4', 'video.mp4'),
+            ('attachment; filename=" video.mp4 "', 'video.mp4'),
+            ("attachment; filename*=UTF-8''r%C3%A9sum%C3%A9.mp4", 'résumé.mp4'),
+            ("attachment; filename=fallback.mp4; filename*=UTF-8''actual.webm", 'actual.webm'),
+            ("attachment; filename*=UTF-8''actual.webm; filename=fallback.mp4", 'actual.webm'),
+        )
+
+        for content_disposition, expected in test_cases:
+            headers = email.message.Message()
+            if content_disposition is not None:
+                headers['Content-Disposition'] = content_disposition
+            with self.subTest(content_disposition=content_disposition):
+                self.assertEqual(disposition_filename(headers), expected)
+
+    def test_urlhandle_detect_ext(self):
+        headers = email.message.Message()
+        headers['Content-Disposition'] = "attachment; filename=fallback.mp4; filename*=UTF-8''actual.webm"
+        headers['Content-Type'] = 'video/mp4'
+        self.assertEqual(urlhandle_detect_ext(unittest.mock.Mock(headers=headers)), 'webm')
+
     def test_try_call(self):
         def total(*x, **kwargs):
             return sum(x) + sum(kwargs.values())

test/test_websockets.py

@@ -130,7 +130,11 @@ def ws_validate_and_send(rh, req):
         try:
             return rh.send(req)
         except TransportError as e:
-            if i < (max_tries - 1) and 'connection closed during handshake' in str(e):
+            if i < (max_tries - 1) and (
+                'connection closed during handshake' in str(e)
+                or (isinstance(e.cause, websockets.exceptions.InvalidMessage)
+                    and isinstance(e.cause.__cause__, EOFError))
+            ):
                 # websockets server sometimes hangs on new connections
                 continue
             raise
@@ -186,7 +190,7 @@ class TestWebsSocketRequestHandlerConformance:
 
     def test_ssl_error(self, handler):
         with handler(verify=False) as rh:
-            with pytest.raises(SSLError, match=r'ssl(?:v3|/tls) alert handshake failure') as exc_info:
+            with pytest.raises(SSLError, match=r'(?:sslv3|tls) alert handshake failure') as exc_info:
                 ws_validate_and_send(rh, Request(self.bad_wss_host))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 

uv.lock

@@ -1447,6 +1447,7 @@ pin = [
     { name = "charset-normalizer" },
     { name = "idna" },
     { name = "mutagen" },
+    { name = "pycparser", marker = "implementation_name != 'PyPy' and implementation_name != 'cpython'" },
     { name = "pycryptodomex" },
     { name = "requests" },
     { name = "urllib3" },
@@ -1534,6 +1535,7 @@ requires-dist = [
     { name = "mutagen", marker = "extra == 'default'" },
     { name = "mutagen", marker = "extra == 'pin'", specifier = "==1.48.1" },
     { name = "pycparser", marker = "implementation_name != 'PyPy' and platform_python_implementation != 'PyPy' and extra == 'pin-secretstorage'", specifier = "==3.0" },
+    { name = "pycparser", marker = "implementation_name != 'PyPy' and implementation_name != 'cpython' and extra == 'pin'", specifier = "==3.0" },
     { name = "pycparser", marker = "implementation_name == 'cpython' and extra == 'pin-curl-cffi'", specifier = "==3.0" },
     { name = "pycryptodomex", marker = "extra == 'default'" },
     { name = "pycryptodomex", marker = "extra == 'pin'", specifier = "==3.23.0" },

yt_dlp/YoutubeDL.py

@@ -672,7 +672,6 @@ class YoutubeDL:
         except Exception as e:
             self.write_debug(f'Failed to enable VT mode: {e}')
 
-        # hehe "immutable" namespace
         self._out_files.console = next(filter(supports_terminal_sequences, (sys.stderr, sys.stdout)), None)
 
         if self.params.get('no_color'):
@@ -2398,8 +2397,7 @@ class YoutubeDL:
             selectors = []
             current_selector = None
             for type_, string_, start, _, _ in tokens:
-                # ENCODING is only defined in Python 3.x
-                if type_ == getattr(tokenize, 'ENCODING', None):
+                if type_ == tokenize.ENCODING:
                     continue
                 elif type_ in [tokenize.NAME, tokenize.NUMBER]:
                     current_selector = FormatSelector(SINGLE, string_, [])

yt_dlp/aes.py

@@ -293,7 +293,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
     - Mode of operation is 'counter'
 
     @param {str} data                    Base64 encoded string
-    @param {str,unicode} password        Password (will be encoded with utf-8)
+    @param {str} password                Password (will be encoded with UTF-8)
     @param {int} key_size_bytes          Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
     @returns {str}                       Decrypted data
     """

yt_dlp/compat/__init__.py

@@ -8,9 +8,8 @@ passthrough_module(__name__, '._deprecated')
 del passthrough_module
 
 
-# HTMLParseError has been deprecated in Python 3.3 and removed in
-# Python 3.5. Introducing dummy exception for Python >3.5 for compatible
-# and uniform cross-version exception handling
+# HTMLParseError was deprecated in Python 3.3 and removed in Python 3.5.
+# Keep a replacement for API compatibility and uniform exception handling.
 class compat_HTMLParseError(ValueError):
     pass
 

yt_dlp/downloader/ism.py

@@ -154,7 +154,7 @@ def write_piff_header(stream, params):
         sample_entry_payload += u16.pack(0x18)  # depth
         sample_entry_payload += s16.pack(-1)  # pre defined
 
-        codec_private_data = binascii.unhexlify(params['codec_private_data'].encode())
+        codec_private_data = binascii.unhexlify(params['codec_private_data'])
         if fourcc in ('H264', 'AVC1'):
             sps, pps = codec_private_data.split(u32.pack(1))[1:]
             avcc_payload = u8.pack(1)  # configuration version

yt_dlp/extractor/_extractors.py

@@ -1221,6 +1221,7 @@ from .nhk import (
 from .nhl import NHLIE
 from .nick import NickIE
 from .niconico import (
+    NiconicoChannelIE,
     NiconicoHistoryIE,
     NiconicoIE,
     NiconicoLiveIE,

yt_dlp/extractor/adn.py

@@ -50,14 +50,13 @@ class ADNIE(ADNBaseIE):
     _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://animationdigitalnetwork.com/video/558-fruits-basket/9841-episode-1-a-ce-soir',
-        'md5': '1c9ef066ceb302c86f80c2b371615261',
+        'md5': '3999b7b235ffb3591a385d1913cd3cd1',
         'info_dict': {
             'id': '9841',
             'ext': 'mp4',
             'title': 'Fruits Basket - Episode 1',
-            'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
             'series': 'Fruits Basket',
-            'duration': 1437,
+            'duration': 1436,
             'release_date': '20190405',
             'comment_count': int,
             'average_rating': float,
@@ -174,6 +173,8 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
     def _real_extract(self, url):
         lang, video_id = self._match_valid_url(url).group('lang', 'id')
         self._HEADERS['X-Target-Distribution'] = lang or 'fr'
+        if 'Authorization' in self._HEADERS:
+            self._HEADERS['X-Profile-ID'] = self._configuration_arg('profile_id', ['1'])[0]
         video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
         player = self._download_json(
             video_base_url + 'configuration', video_id,

yt_dlp/extractor/applepodcasts.py

@@ -28,7 +28,7 @@ class AppleBaseIE(InfoExtractor):
 
     def _get_token(self, webpage, episode_id):
         if self._jwt_cache.get(self._BASE_URL) and not self._jwt_is_expired(self._jwt_cache[self._BASE_URL]):
-            return self._jwt
+            return self._jwt_cache[self._BASE_URL]
 
         js_path = self._search_regex(
             r'<script [^>]*\bsrc="(/assets/index~[0-9a-f]+\.js)">', webpage, 'JS asset path')

yt_dlp/extractor/bandcamp.py

@@ -25,7 +25,35 @@ from ..utils import (
 from ..utils.traversal import find_element, find_elements, traverse_obj
 
 
-class BandcampIE(InfoExtractor):
+class BandcampBaseIE(InfoExtractor):
+    # Initially try without impersonation, retry with impersonation
+    def _download_webpage(self, *args, **kwargs):
+        impersonate = kwargs.pop('impersonate', None) or True
+        kwargs.pop('require_impersonation', None)
+        webpage = super()._download_webpage(*args, **kwargs)
+        if webpage:
+            if self._html_extract_title(webpage) == 'Client Challenge':
+                self.write_debug('Got client challenge webpage response')
+            else:
+                return webpage
+
+        res = self._download_webpage_handle(*args, impersonate=impersonate, require_impersonation=True, **kwargs)
+        if res is False:
+            return False
+
+        webpage, urlh = res
+        if self._html_extract_title(webpage) == 'Client Challenge':
+            raise ExtractorError(f'Got client challenge webpage response with {urlh.extensions.get("impersonate")}')
+
+        return webpage
+
+    def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
+        return self._parse_json(self._html_search_regex(
+            rf'data-{attr}=(["\'])({{.+?}})\1', webpage,
+            attr + ' data', group=2), video_id, fatal=fatal)
+
+
+class BandcampIE(BandcampBaseIE):
     _VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
     _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
     _TESTS = [{
@@ -149,14 +177,9 @@ class BandcampIE(InfoExtractor):
         'skip': 'embed detection is broken',
     }]
 
-    def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
-        return self._parse_json(self._html_search_regex(
-            rf'data-{attr}=(["\'])({{.+?}})\1', webpage,
-            attr + ' data', group=2), video_id, fatal=fatal)
-
     def _real_extract(self, url):
         title, uploader = self._match_valid_url(url).group('id', 'uploader')
-        webpage = self._download_webpage(url, title, impersonate=True)
+        webpage = self._download_webpage(url, title)
         tralbum = self._extract_data_attr(webpage, title)
         thumbnail = self._og_search_thumbnail(webpage)
 
@@ -202,7 +225,7 @@ class BandcampIE(InfoExtractor):
             track_id = str(tralbum['id'])
 
             download_webpage = self._download_webpage(
-                download_link, track_id, 'Downloading free downloads page', impersonate=True)
+                download_link, track_id, 'Downloading free downloads page')
 
             blob = self._extract_data_attr(download_webpage, track_id, 'blob')
 
@@ -284,7 +307,7 @@ class BandcampIE(InfoExtractor):
         }
 
 
-class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
+class BandcampAlbumIE(BandcampBaseIE):
     IE_NAME = 'Bandcamp:album'
     _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
 
@@ -389,7 +412,7 @@ class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
     def _real_extract(self, url):
         uploader_id, album_id = self._match_valid_url(url).groups()
         playlist_id = album_id or uploader_id
-        webpage = self._download_webpage(url, playlist_id, impersonate=True)
+        webpage = self._download_webpage(url, playlist_id)
         tralbum = self._extract_data_attr(webpage, playlist_id)
         track_info = tralbum.get('trackinfo')
         if not track_info:
@@ -414,7 +437,7 @@ class BandcampAlbumIE(BandcampIE):  # XXX: Do not subclass from concrete IE
         }
 
 
-class BandcampWeeklyIE(BandcampIE):  # XXX: Do not subclass from concrete IE
+class BandcampWeeklyIE(BandcampBaseIE):
     IE_NAME = 'Bandcamp:weekly'
     _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/radio/?\?(?:[^#]+&)?show=(?P<id>\d+)'
     _TESTS = [{
@@ -478,7 +501,7 @@ class BandcampWeeklyIE(BandcampIE):  # XXX: Do not subclass from concrete IE
         }
 
 
-class BandcampUserIE(InfoExtractor):
+class BandcampUserIE(BandcampBaseIE):
     IE_NAME = 'Bandcamp:user'
     _VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)'
 

yt_dlp/extractor/common.py

@@ -432,29 +432,28 @@ class InfoExtractor:
 
     chapter:        Name or title of the chapter the video belongs to.
     chapter_number: Number of the chapter the video belongs to, as an integer.
-    chapter_id:     Id of the chapter the video belongs to, as a unicode string.
+    chapter_id:     Id of the chapter the video belongs to.
 
     The following fields should only be used when the video is an episode of some
     series, programme or podcast:
 
     series:         Title of the series or programme the video episode belongs to.
-    series_id:      Id of the series or programme the video episode belongs to, as a unicode string.
+    series_id:      Id of the series or programme the video episode belongs to.
     season:         Title of the season the video episode belongs to.
     season_number:  Number of the season the video episode belongs to, as an integer.
-    season_id:      Id of the season the video episode belongs to, as a unicode string.
+    season_id:      Id of the season the video episode belongs to.
     episode:        Title of the video episode. Unlike mandatory video title field,
                     this field should denote the exact title of the video episode
                     without any kind of decoration.
     episode_number: Number of the video episode within a season, as an integer.
-    episode_id:     Id of the video episode, as a unicode string.
+    episode_id:     Id of the video episode.
 
     The following fields should only be used when the media is a track or a part of
     a music album:
 
     track:          Title of the track.
     track_number:   Number of the track within an album or a disc, as an integer.
-    track_id:       Id of the track (useful in case of custom indexing, e.g. 6.iii),
-                    as a unicode string.
+    track_id:       Id of the track (useful for custom indexing, e.g. 6.iii).
     artists:        List of artists of the track.
     composers:      List of composers of the piece.
     genres:         List of genres of the track.
@@ -487,7 +486,7 @@ class InfoExtractor:
     creator:        Use "creators" instead.
                     The creator of the video.
 
-    Unless mentioned otherwise, the fields should be Unicode strings.
+    Unless mentioned otherwise, the fields should be strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
 
@@ -1277,6 +1276,9 @@ class InfoExtractor:
         """Returns a URL that points to a page that should be processed"""
         if ie is not None:
             kwargs['ie_key'] = ie if isinstance(ie, str) else ie.ie_key()
+        # Silence fallback warning if this is an intentional generic result
+        if kwargs.get('ie_key') == 'Generic':
+            url = smuggle_url(url, {'to_generic': True})
         if video_id is not None:
             kwargs['id'] = video_id
         if video_title is not None:

yt_dlp/extractor/globalplayer.py

@@ -1,14 +1,6 @@
 from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    join_nonempty,
-    parse_duration,
-    str_or_none,
-    traverse_obj,
-    unified_strdate,
-    unified_timestamp,
-    urlhandle_detect_ext,
-)
+from ..utils import url_or_none
+from ..utils.traversal import require, traverse_obj
 
 
 class GlobalPlayerBaseIE(InfoExtractor):
@@ -16,29 +8,11 @@ class GlobalPlayerBaseIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         return self._search_nextjs_data(webpage, video_id)['props']['pageProps']
 
-    def _request_ext(self, url, video_id):
-        return urlhandle_detect_ext(self._request_webpage(  # Server rejects HEAD requests
-            url, video_id, note='Determining source extension'))
-
-    def _extract_audio(self, episode, series):
-        return {
-            'vcodec': 'none',
-            **traverse_obj(series, {
-                'series': 'title',
-                'series_id': 'id',
-                'thumbnail': 'imageUrl',
-                'uploader': 'itunesAuthor',  # podcasts only
-            }),
-            **traverse_obj(episode, {
-                'id': 'id',
-                'description': ('description', {clean_html}),
-                'duration': ('duration', {parse_duration}),
-                'thumbnail': 'imageUrl',
-                'url': 'streamUrl',
-                'timestamp': (('pubDate', 'startDate'), {unified_timestamp}),
-                'title': 'title',
-            }, get_all=False),
-        }
+    @staticmethod
+    def _get_playback_url(data):
+        return traverse_obj(data, (
+            'playback', lambda _, v: v['canUse'] == 'true',
+            'url', {url_or_none}, any, {require('playback URL')}))
 
 
 class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
@@ -48,11 +22,10 @@ class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
         'info_dict': {
             'id': '2mx1E',
             'ext': 'aac',
-            'display_id': 'smoothchill-uk',
-            'title': 're:^Smooth Chill.+$',
-            'thumbnail': 'https://herald.musicradio.com/media/f296ade8-50c9-4f60-911f-924e96873620.png',
-            'description': 'Music To Chill To',
             'live_status': 'is_live',
+            'thumbnail': 'md5:d5040f26c7c4061014a44866129b900e',
+            'description': 'md5:6e183929da9001778895f32ae85124bc',
+            'title': 're:^Smooth Chill.+$',
         },
     }, {
         # national station
@@ -60,11 +33,10 @@ class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
         'info_dict': {
             'id': '2mwx4',
             'ext': 'aac',
-            'description': 'turn up the feel good!',
-            'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
             'live_status': 'is_live',
+            'description': 'md5:492d07dfea8addadd15650ef40c10d02',
+            'thumbnail': 'md5:6f13378a53ce55bcf57365a654e1b490',
             'title': 're:^Heart UK.+$',
-            'display_id': 'heart-uk',
         },
     }, {
         # regional variation
@@ -72,110 +44,131 @@ class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
         'info_dict': {
             'id': 'AMqg',
             'ext': 'aac',
-            'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
-            'title': 're:^Heart London.+$',
             'live_status': 'is_live',
-            'display_id': 'heart-london',
-            'description': 'turn up the feel good!',
+            'description': 'md5:492d07dfea8addadd15650ef40c10d02',
+            'thumbnail': 'md5:6f13378a53ce55bcf57365a654e1b490',
+            'title': 're:^Heart London.+$',
         },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        station = self._get_page_props(url, video_id)['station']
-        stream_url = station['streamUrl']
+        meta = self._get_page_props(url, video_id)['station']
+        station_id = meta['id']
+
+        data = self._download_json(f'https://bff-web-guacamole.musicradio.com/playables/{station_id}', video_id)
 
         return {
-            'id': station['id'],
-            'display_id': join_nonempty('brandSlug', 'slug', from_dict=station) or station.get('legacyStationPrefix'),
-            'url': stream_url,
-            'ext': self._request_ext(stream_url, video_id),
+            'id': station_id,
+            'url': self._get_playback_url(data),
+            'ext': 'aac',
             'vcodec': 'none',
             'is_live': True,
-            **traverse_obj(station, {
-                'title': (('name', 'brandName'), {str_or_none}),
-                'description': 'tagline',
-                'thumbnail': 'brandLogo',
-            }, get_all=False),
+            **traverse_obj(meta, {
+                'thumbnail': ('brandLogo', {url_or_none}),
+                'description': ('tagline', {str}),
+                'title': ('name', {str}),
+            }),
         }
 
 
 class GlobalPlayerLivePlaylistIE(GlobalPlayerBaseIE):
     _VALID_URL = r'https?://www\.globalplayer\.com/playlists/(?P<id>\w+)'
     _TESTS = [{
-        # "live playlist"
+        # live playlist
         'url': 'https://www.globalplayer.com/playlists/8bLk/',
         'info_dict': {
             'id': '8bLk',
             'ext': 'aac',
             'live_status': 'is_live',
-            'description': 'md5:e10f5e10b01a7f2c14ba815509fbb38d',
-            'thumbnail': 'https://images.globalplayer.com/images/551379?width=450&signature=oMLPZIoi5_dBSHnTMREW0Xg76mA=',
+            'thumbnail': 'md5:391a13cc087b42f626e9e65bbeaf0a11',
+            'description': 'md5:f015f2f6c6f6a807669ebcc9a0ca147c',
             'title': 're:^Classic FM Hall of Fame.+$',
         },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        station = self._get_page_props(url, video_id)['playlistData']
-        stream_url = station['streamUrl']
+        meta = self._get_page_props(url, video_id)['playlistData']
 
         return {
-            'id': video_id,
-            'url': stream_url,
-            'ext': self._request_ext(stream_url, video_id),
+            'url': meta['streamUrl'],
+            'ext': 'aac',
             'vcodec': 'none',
+            'id': video_id,
             'is_live': True,
-            **traverse_obj(station, {
-                'title': 'title',
-                'description': 'description',
-                'thumbnail': 'image',
+            **traverse_obj(meta, {
+                'thumbnail': ('image', {url_or_none}),
+                'description': ('description', {str}),
+                'title': ('title', {str}),
             }),
         }
 
 
 class GlobalPlayerAudioIE(GlobalPlayerBaseIE):
-    _VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)/|catchup/\w+/\w+/)(?P<id>\w+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://www\.globalplayer\.com/(?P<path>(?P<podcast>podcasts)/|catchup/\w+/\w+/)(?P<id>\w+)/?(?:$|[?#])'
     _TESTS = [{
         # podcast
         'url': 'https://www.globalplayer.com/podcasts/42KuaM/',
-        'playlist_mincount': 5,
+        'playlist_mincount': 2,
         'info_dict': {
             'id': '42KuaM',
-            'title': 'Filthy Ritual',
             'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
-            'categories': ['Society & Culture', 'True Crime'],
-            'uploader': 'Global',
-            'description': 'md5:da5b918eac9ae319454a10a563afacf9',
+            'description': 'md5:17b7b9e3c76b2f4d9e31ccc4f0b66e32',
+            'title': 'Filthy Ritual',
         },
     }, {
         # radio catchup
         'url': 'https://www.globalplayer.com/catchup/lbc/uk/46vyD7z/',
-        'playlist_mincount': 3,
+        'playlist_mincount': 2,
         'info_dict': {
             'id': '46vyD7z',
-            'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
+            'thumbnail': 'md5:664ad62a8fb920a2b8e264ed780eee3d',
+            'description': 'md5:53b6fa5ef71a3cff6628551bcc416384',
             'title': 'Nick Ferrari',
-            'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
         },
     }]
 
     def _real_extract(self, url):
-        video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
+        video_id, path, podcast = self._match_valid_url(url).group('id', 'path', 'podcast')
         props = self._get_page_props(url, video_id)
-        series = props['podcastInfo'] if podcast else props['catchupInfo']
+        if podcast:
+            meta = props['podcastInfo']['metadata']
+            blocks = props['podcastInfo']['blocks'][1]['items']
+        else:
+            catchup = props['catchupShow'] if 'catchupShow' in props else props['catchupInfo']
+            meta = catchup['metadata']
+            blocks = catchup['blocks'][1]['items']
+
+        def _entries():
+            for block in blocks:
+                entry_id = block['id']
+                data = self._download_json(
+                    f'https://bff-web-guacamole.musicradio.com/playables/{entry_id}',
+                    video_id, f'Downloading metadata JSON for {entry_id}')
+
+                yield {
+                    'id': entry_id,
+                    'url': self._get_playback_url(data),
+                    'vcodec': 'none',
+                    'extractor': GlobalPlayerAudioEpisodeIE.IE_NAME,
+                    'extractor_key': GlobalPlayerAudioEpisodeIE.ie_key(),
+                    'webpage_url': f'https://www.globalplayer.com/{path}episodes/{entry_id}',
+                    **traverse_obj(block, {
+                        'thumbnail': ('image', 'url', {url_or_none}),
+                        'description': ('description', {str}),
+                        'title': ('title', {str}),
+                    }),
+                }
 
         return {
             '_type': 'playlist',
             'id': video_id,
-            'entries': [self._extract_audio(ep, series) for ep in traverse_obj(
-                        series, ('episodes', lambda _, v: v['id'] and v['streamUrl']))],
-            'categories': traverse_obj(series, ('categories', ..., 'name')) or None,
-            **traverse_obj(series, {
-                'description': 'description',
-                'thumbnail': 'imageUrl',
-                'title': 'title',
-                'uploader': 'itunesAuthor',  # podcasts only
+            'entries': _entries(),
+            **traverse_obj(meta, {
+                'thumbnail': ('image', 'url', {url_or_none}),
+                'description': ('description', {str}),
+                'title': ('title', {str}),
             }),
         }
 
@@ -184,44 +177,42 @@ class GlobalPlayerAudioEpisodeIE(GlobalPlayerBaseIE):
     _VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)|catchup/\w+/\w+)/episodes/(?P<id>\w+)/?(?:$|[?#])'
     _TESTS = [{
         # podcast
-        'url': 'https://www.globalplayer.com/podcasts/episodes/7DrfNnE/',
+        'url': 'https://www.globalplayer.com/podcasts/episodes/7DrorSc/',
         'info_dict': {
-            'id': '7DrfNnE',
+            'id': '7DrorSc',
             'ext': 'mp3',
-            'title': 'Filthy Ritual - Trailer',
-            'description': 'md5:1f1562fd0f01b4773b590984f94223e0',
             'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
-            'duration': 225.0,
-            'timestamp': 1681254900,
-            'series': 'Filthy Ritual',
-            'series_id': '42KuaM',
-            'upload_date': '20230411',
-            'uploader': 'Global',
+            'description': 'md5:372e5aa2b531f9eba863dfc67d007c1c',
+            'title': 'Filthy Ritual - Trailer',
         },
     }, {
-        # radio catchup
-        'url': 'https://www.globalplayer.com/catchup/lbc/uk/episodes/2zGq26Vcv1fCWhddC4JAwETXWe/',
+        # radio catchup - test urls are removed after 7 days
+        'url': 'https://www.globalplayer.com/catchup/lbc/uk/episodes/2zGmrV6DnvogKkNCXkwkQ8HQTA/',
         'info_dict': {
-            'id': '2zGq26Vcv1fCWhddC4JAwETXWe',
+            'id': '2zGmrV6DnvogKkNCXkwkQ8HQTA',
             'ext': 'm4a',
-            'timestamp': 1682056800,
-            'series': 'Nick Ferrari',
-            'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
-            'upload_date': '20230421',
-            'series_id': '46vyD7z',
-            'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
+            'thumbnail': 'md5:664ad62a8fb920a2b8e264ed780eee3d',
+            'description': 'md5:53b6fa5ef71a3cff6628551bcc416384',
             'title': 'Nick Ferrari',
-            'duration': 10800.0,
         },
     }]
 
     def _real_extract(self, url):
         video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
         props = self._get_page_props(url, video_id)
-        episode = props['podcastEpisode'] if podcast else props['catchupEpisode']
+        meta = props['podcastEpisode']['metadata'] if podcast else props['catchupEpisode']['metadata']
+        data = self._download_json(f'https://bff-web-guacamole.musicradio.com/playables/{video_id}', video_id)
 
-        return self._extract_audio(
-            episode, traverse_obj(episode, 'podcast', 'show', expected_type=dict) or {})
+        return {
+            'id': video_id,
+            'url': self._get_playback_url(data),
+            'vcodec': 'none',
+            **traverse_obj(meta, {
+                'thumbnail': ('image', 'url', {url_or_none}),
+                'description': ('description', {str}),
+                'title': ('title', {str}),
+            }),
+        }
 
 
 class GlobalPlayerVideoIE(GlobalPlayerBaseIE):
@@ -231,9 +222,8 @@ class GlobalPlayerVideoIE(GlobalPlayerBaseIE):
         'info_dict': {
             'id': '2JsSZ7Gm2uP',
             'ext': 'mp4',
-            'description': 'md5:6a9f063c67c42f218e42eee7d0298bfd',
             'thumbnail': 'md5:d4498af48e15aae4839ce77b97d39550',
-            'upload_date': '20230420',
+            'description': 'md5:6a9f063c67c42f218e42eee7d0298bfd',
             'title': 'Treble Malakai Bayoh sings a sublime Handel aria at Classic FM Live',
         },
     }]
@@ -245,10 +235,9 @@ class GlobalPlayerVideoIE(GlobalPlayerBaseIE):
         return {
             'id': video_id,
             **traverse_obj(meta, {
-                'url': 'url',
-                'thumbnail': ('image', 'url'),
-                'title': 'title',
-                'upload_date': ('publish_date', {unified_strdate}),
-                'description': 'description',
+                'url': ('url', {url_or_none}),
+                'thumbnail': ('image', 'url', {url_or_none}),
+                'description': ('description', {str}),
+                'title': ('title', {str}),
             }),
         }

yt_dlp/extractor/go.py

@@ -116,41 +116,41 @@ class GoIE(AdobePassIE):
         'params': {'skip_download': 'm3u8'},
         'skip': 'This video requires AdobePass MSO credentials',
     }, {
-        'url': 'https://www.freeform.com/episode/bda0eaf7-761a-4838-aa44-96f794000844/playlist/PL553044961',
+        'url': 'https://www.freeform.com/episode/235128d8-2609-4df4-9874-0b0b687fe9f9/playlist/PL5539647334',
         'info_dict': {
-            'id': 'VDKA39007340',
+            'id': 'VDKA39623200',
             'ext': 'mp4',
-            'title': 'Angel\'s Landing',
-            'description': 'md5:91bf084e785c968fab16734df7313446',
+            'title': 'New House / New Rules',
+            'description': 'md5:6f38b4b1649dc9f3a9e7acf911a70056',
             'age_limit': 14,
-            'duration': 2523,
+            'duration': 2733,
             'thumbnail': r're:https?://.+/.+\.jpg',
-            'series': 'How I Escaped My Cult',
-            'season': 'Season 1',
-            'season_number': 1,
-            'episode': 'Episode 2',
-            'episode_number': 2,
-            'timestamp': 1740038400.0,
-            'upload_date': '20250220',
+            'series': 'Project Runway',
+            'season': 'Season 21',
+            'season_number': 21,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'timestamp': 1754020800,
+            'upload_date': '20250801',
         },
         'params': {'skip_download': 'm3u8'},
     }, {
-        'url': 'https://www.nationalgeographic.com/tv/episode/ca694661-1186-41ae-8089-82f64d69b16d/playlist/PL554408064',
+        'url': 'https://www.nationalgeographic.com/tv/episode/df0e5bd8-f9bb-4c92-9f94-74dec4dad8a7/playlist/PL553044961',
         'info_dict': {
-            'id': 'VDKA39492078',
+            'id': 'VDKA35475602',
             'ext': 'mp4',
-            'title': 'Heart of the Emperors',
-            'description': 'md5:4fc50a2878f030bb3a7eac9124dca677',
+            'title': 'The Pol Shebang',
+            'description': 'md5:ccea1210c5ebcdc5c1a435f01bdb8b82',
             'age_limit': 0,
-            'duration': 2775,
+            'duration': 1323,
             'thumbnail': r're:https?://.+/.+\.jpg',
-            'series': 'Secrets of the Penguins',
+            'series': 'The Incredible Pol Farm',
             'season': 'Season 1',
             'season_number': 1,
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'timestamp': 1745204400.0,
-            'upload_date': '20250421',
+            'episode': 'Episode 14',
+            'episode_number': 14,
+            'timestamp': 1704614400,
+            'upload_date': '20240107',
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -190,7 +190,10 @@ class GoIE(AdobePassIE):
 
         site_info = self._SITE_INFO[site]
         brand = site_info['brand']
-        video_data = self._extract_videos(brand, video_id)[0]
+        videos = self._extract_videos(brand, video_id)
+        if not videos:
+            self.report_drm(video_id)
+        video_data = videos[0]
         video_id = video_data['id']
         title = video_data['title']
 

yt_dlp/extractor/googledrive.py

@@ -3,6 +3,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
+    disposition_filename,
     extract_attributes,
     filter_dict,
     get_element_by_class,
@@ -184,9 +185,7 @@ class GoogleDriveIE(InfoExtractor):
             def add_source_format(urlh):
                 nonlocal title
                 if not title:
-                    title = self._search_regex(
-                        r'\bfilename="([^"]+)"', urlh.headers.get('Content-Disposition'),
-                        'title', default=None)
+                    title = disposition_filename(urlh.headers) or None
                 formats.append({
                     # Use redirect URLs as download URLs in order to calculate
                     # correct cookies in _calc_cookies.
@@ -198,7 +197,7 @@ class GoogleDriveIE(InfoExtractor):
                     'format_id': 'source',
                     'quality': 1,
                 })
-            if urlh.headers.get('Content-Disposition'):
+            if urlh.headers.get_content_disposition():
                 add_source_format(urlh)
             else:
                 confirmation_webpage = self._webpage_read_content(
@@ -209,7 +208,7 @@ class GoogleDriveIE(InfoExtractor):
                         get_element_html_by_id('download-form', confirmation_webpage) or '').get('action')
                     if confirmed_source_url:
                         urlh = request_source_file(confirmed_source_url, 'confirmed source', data=b'')
-                        if urlh and urlh.headers.get('Content-Disposition'):
+                        if urlh and urlh.headers.get_content_disposition():
                             add_source_format(urlh)
                     else:
                         self.report_warning(

yt_dlp/extractor/itv.py

@@ -114,7 +114,7 @@ class ITVIE(InfoExtractor):
         # See: https://github.com/yt-dlp/yt-dlp/issues/986
         platform_tag_subs, featureset_subs = next(
             ((platform_tag, featureset)
-             for platform_tag, featuresets in reversed(list(variants.items())) for featureset in featuresets
+             for platform_tag, featuresets in reversed(variants.items()) for featureset in featuresets
              if try_get(featureset, lambda x: x[2]) == 'outband-webvtt'),
             (None, None))
 
@@ -143,7 +143,7 @@ class ITVIE(InfoExtractor):
         # See: https://github.com/yt-dlp/yt-dlp/issues/986
         platform_tag_video, featureset_video = next(
             ((platform_tag, featureset)
-             for platform_tag, featuresets in reversed(list(variants.items())) for featureset in featuresets
+             for platform_tag, featuresets in reversed(variants.items()) for featureset in featuresets
              if set(try_get(featureset, lambda x: x[:2]) or []) == {'aes', 'hls'}),
             (None, None))
         if not platform_tag_video or not featureset_video:

yt_dlp/extractor/niconico.py

@@ -3,6 +3,7 @@ import functools
 import itertools
 import json
 import re
+import urllib.parse
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..networking.exceptions import HTTPError
@@ -14,6 +15,7 @@ from ..utils import (
     extract_attributes,
     float_or_none,
     int_or_none,
+    join_nonempty,
     parse_bitrate,
     parse_iso8601,
     parse_qs,
@@ -31,8 +33,10 @@ from ..utils import (
 )
 from ..utils.traversal import (
     find_element,
+    find_elements,
     require,
     traverse_obj,
+    trim_str,
 )
 
 
@@ -1080,3 +1084,98 @@ class NiconicoLiveIE(NiconicoBaseIE):
             'thumbnails': thumbnails,
             'formats': formats,
         }
+
+
+class NiconicoChannelIE(NiconicoBaseIE):
+    IE_NAME = 'niconico:channel'
+
+    _PAGE_SIZE = 20
+    _SEARCH_PAGE_SIZE = 32
+    _VALID_URL = [
+        r'https?://ch\.nicovideo\.jp/(?P<id>[\w-]+)/(?P<type>video)/?(?P<slug>continuation|member|pay|so\d{8})?(?:[/?#]|$)',
+        r'https?://ch\.nicovideo\.jp/(?P<type>search)/(?P<id>[^/?#]+)',
+    ]
+    _TESTS = [{
+        'url': 'https://ch.nicovideo.jp/higurashianime/video',
+        'info_dict': {
+            'id': 'higurashianime',
+            'title': '「ひぐらしのなく頃に」オフィシャルチャンネル',
+        },
+        'playlist_mincount': 54,
+    }, {
+        'url': 'https://ch.nicovideo.jp/amiami-ssr/video?page=2',
+        'info_dict': {
+            'id': 'amiami-ssr',
+            'title': 'あみあみSSRチャンネル',
+        },
+        'playlist_count': 20,
+    }, {
+        'url': 'https://ch.nicovideo.jp/yukarisama/video/pay',
+        'info_dict': {
+            'id': 'yukarisama',
+            'title': '縁結びのゆかり様',
+        },
+        'playlist_mincount': 16,
+    }, {
+        'url': 'https://ch.nicovideo.jp/mokou1/video/member',
+        'info_dict': {
+            'id': 'mokou1',
+            'title': 'もこう。',
+        },
+        'playlist_mincount': 49,
+    }, {
+        'url': 'https://ch.nicovideo.jp/amiami-ch/video/continuation',
+        'info_dict': {
+            'id': 'amiami-ch',
+            'title': 'あみあみチャンネル',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://ch.nicovideo.jp/search/%E3%81%AF%E3%81%AA%E3%81%BE%E3%81%8D%E3%81%93%E3%82%82%E3%81%A1%E3%81%83?channel_id=ch2585696&type=video',
+        'info_dict': {
+            'id': 'secondshot',
+            'title': 'セカンドショットちゃんねる - はなまきこもちぃ',
+        },
+        'playlist_mincount': 115,
+    }, {
+        'url': 'https://ch.nicovideo.jp/amiami-ch/video/so44060088',
+        'only_matching': True,
+    }]
+
+    def _fetch_page(self, url, playlist_id, page):
+        page += 1
+        webpage = self._download_webpage(
+            url, playlist_id, f'Downloading page {page}', query={'page': page})
+        for url in traverse_obj(webpage, (
+            {find_elements(cls='watchLink', html=True)},
+            ..., {extract_attributes}, 'href', {url_or_none},
+        )):
+            yield self.url_result(url, NiconicoIE)
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        display_id = urllib.parse.unquote(mobj.group('id'))
+        playlist_type = mobj.group('type')
+
+        if playlist_type == 'search':
+            keyword = display_id
+            page_size = self._SEARCH_PAGE_SIZE
+        else:
+            if (slug := mobj.group('slug')) and slug.startswith('so'):
+                return self.url_result(
+                    f'{self._BASE_URL}/watch/{slug}', NiconicoIE)
+            keyword = None
+            page_size = self._PAGE_SIZE
+
+        webpage = self._download_webpage(url, display_id)
+        channel_name = traverse_obj(webpage, (
+            {find_element(cls='channel_name')}, {find_element(tag='a', html=True)},
+            {extract_attributes}, 'href', {str}, {trim_str(start='/')}, filter))
+        site_name = self._og_search_property('site_name', webpage, default=None)
+
+        fetch_page = functools.partial(self._fetch_page, url, display_id)
+        page = traverse_obj(parse_qs(url), ('page', -1, {int_or_none}))
+        entries = fetch_page(page - 1) if page else OnDemandPagedList(fetch_page, page_size)
+
+        return self.playlist_result(
+            entries, channel_name, join_nonempty(site_name, keyword, delim=' - '))

yt_dlp/extractor/odnoklassniki.py

@@ -2,10 +2,8 @@ import urllib.parse
 
 from .common import InfoExtractor
 from ..compat import compat_etree_fromstring
-from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
     qualities,
     smuggle_url,
@@ -21,7 +19,7 @@ from ..utils.traversal import find_element, traverse_obj
 class OdnoklassnikiIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 https?://
-                    (?:(?:www|m|mobile)\.)?
+                    (?:www\.)?
                     (?:odnoklassniki|ok)\.ru/
                     (?:
                         video(?P<embed>embed)?/|
@@ -34,21 +32,21 @@ class OdnoklassnikiIE(InfoExtractor):
     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1']
     _TESTS = [{
         'note': 'Coub embedded',
-        'url': 'http://ok.ru/video/1484130554189',
+        'url': 'https://ok.ru/video/1484130554189',
         'info_dict': {
             'id': '1keok9',
             'ext': 'mp4',
-            'timestamp': 1545580896,
-            'view_count': int,
-            'thumbnail': r're:^https?://.*\.jpg$',
             'title': 'Народная забава',
             'uploader': 'Nevata',
-            'upload_date': '20181223',
-            'age_limit': 0,
             'uploader_id': 'nevata.s',
+            'view_count': int,
             'like_count': int,
-            'duration': 8.08,
             'repost_count': int,
+            'age_limit': 0,
+            'duration': 8.08,
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1545580896,
+            'upload_date': '20181223',
         },
     }, {
         'note': 'vk.com embedded',
@@ -66,28 +64,25 @@ class OdnoklassnikiIE(InfoExtractor):
         },
         'skip': 'vk extractor error',
     }, {
-        # metadata in JSON, webm_dash with Firefox UA
-        'url': 'http://ok.ru/video/20079905452',
+        # metadataWebmUrl
+        'url': 'https://ok.ru/video/20079905452',
         'md5': '8f477d8931c531374a3e36daec617b2c',
         'info_dict': {
             'id': '20079905452',
             'ext': 'webm',
             'title': 'Культура меняет нас (прекрасный ролик!))',
-            'thumbnail': str,
-            'duration': 100,
-            'upload_date': '20141207',
-            'uploader_id': '330537914540',
-            'uploader': 'Виталий Добровольский',
             'like_count': int,
             'age_limit': 0,
+            'duration': 100,
+            'thumbnail': 'https://iv.okcdn.ru/videoPreview?id=50132290220&type=37&idx=13&tkn=pYXx7IXsAq2kUf1W0PpYHMMAnF8&fn=external_8',
+            'upload_date': '20141207',
         },
         'params': {
             'format': 'bv[ext=webm]',
-            'http_headers': {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:102.0) Gecko/20100101 Firefox/102.0'},
         },
     }, {
         # metadataUrl
-        'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
+        'url': 'https://ok.ru/video/63567059965189-0?fromTime=5',
         'md5': '2bae2f58eefe1b3d26f3926c4a64d2f3',
         'info_dict': {
             'id': '63567059965189-0',
@@ -103,6 +98,7 @@ class OdnoklassnikiIE(InfoExtractor):
             'start_time': 5,
         },
         'params': {'skip_download': 'm3u8'},
+        'skip': 'Redirects to homepage',
     }, {
         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
         'url': 'https://ok.ru/video/3952212382174',
@@ -132,9 +128,10 @@ class OdnoklassnikiIE(InfoExtractor):
             'playable_in_embed': True,
             'channel': 'BornToReact',
         },
+        'skip': 'This video has been removed for violating YouTube\'s Community Guidelines',
     }, {
         # YouTube embed (metadata, provider == USER_YOUTUBE, no metadata.movie.title field)
-        'url': 'http://ok.ru/video/62036049272859-0',
+        'url': 'https://ok.ru/video/62036049272859-0',
         'info_dict': {
             'id': '62036049272859-0',
             'ext': 'mp4',
@@ -149,16 +146,6 @@ class OdnoklassnikiIE(InfoExtractor):
             'skip_download': True,
         },
         'skip': 'Video has not been found',
-    }, {
-        'note': 'Only available in mobile webpage',
-        'url': 'https://m.ok.ru/video/2361249957145',
-        'info_dict': {
-            'id': '2361249957145',
-            'ext': 'mp4',
-            'title': 'Быковское крещение',
-            'duration': 3038.181,
-            'thumbnail': r're:^https?://i\.mycdn\.me/videoPreview\?.+',
-        },
     }, {
         'note': 'subtitles',
         'url': 'https://ok.ru/video/4249587550747',
@@ -178,56 +165,47 @@ class OdnoklassnikiIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'Video has not been found',
     }, {
-        'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
+        'url': 'https://ok.ru/videoembed/9178551814752',
+        'md5': 'cf97450124817f122136ba09819a60c3',
+        'info_dict': {
+            'id': '9178551814752',
+            'ext': 'mp4',
+            'title': 'В ПАРКЕ ЧАИР - РЕТРО ХИТЫ - СОВЕТСКИЕ ПЕСНИ',
+            'like_count': int,
+            'duration': 3260,
+            'thumbnail': 'https://iv.okcdn.ru/videoPreview?id=8382455220832&type=32&idx=12&tkn=FpC95WqL8aCthA4GNKSHpoEMgg4&fn=external_8',
+        },
+    }, {
+        'url': 'https://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,
     }, {
-        'url': 'http://www.ok.ru/video/20648036891',
+        'url': 'https://www.ok.ru/video/20648036891',
         'only_matching': True,
     }, {
-        'url': 'http://www.ok.ru/videoembed/20648036891',
-        'only_matching': True,
-    }, {
-        'url': 'http://m.ok.ru/video/20079905452',
-        'only_matching': True,
-    }, {
-        'url': 'http://mobile.ok.ru/video/20079905452',
+        'url': 'https://www.ok.ru/videoembed/20648036891',
         'only_matching': True,
     }, {
         'url': 'https://www.ok.ru/live/484531969818',
         'only_matching': True,
-    }, {
-        'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#',
-        'only_matching': True,
     }, {
         # Paid video
         'url': 'https://ok.ru/video/954886983203',
         'only_matching': True,
-    }, {
-        'url': 'https://ok.ru/videoembed/2932705602075',
-        'info_dict': {
-            'id': '2932705602075',
-            'ext': 'mp4',
-            'thumbnail': 'https://i.mycdn.me/videoPreview?id=1369902483995&type=37&idx=2&tkn=fqlnoQD_xwq5ovIlKfgNyU08qmM&fn=external_8',
-            'title': 'Boosty для тебя!',
-            'uploader_id': '597811038747',
-            'like_count': 0,
-            'duration': 35,
-        },
     }]
 
     _WEBPAGE_TESTS = [{
-        'url': 'https://boosty.to/ikakprosto/posts/56cedaca-b56a-4dfd-b3ed-98c79cfa0167',
+        'url': 'https://www.liveinternet.ru/users/5932706/post515277341/',
+        'md5': 'cf97450124817f122136ba09819a60c3',
         'info_dict': {
-            'id': '3950343629563',
+            'id': '9178551814752',
             'ext': 'mp4',
-            'thumbnail': 'https://i.mycdn.me/videoPreview?id=2776238394107&type=37&idx=11&tkn=F3ejkUFcpuI4DnMRxrDGcH5YcmM&fn=external_8',
-            'title': 'Заяц Бусти.mp4',
-            'uploader_id': '571368965883',
-            'like_count': 0,
-            'duration': 10444,
+            'title': 'В ПАРКЕ ЧАИР - РЕТРО ХИТЫ - СОВЕТСКИЕ ПЕСНИ',
+            'like_count': int,
+            'duration': 3260,
+            'thumbnail': 'https://iv.okcdn.ru/videoPreview?id=8382455220832&type=32&idx=12&tkn=FpC95WqL8aCthA4GNKSHpoEMgg4&fn=external_8',
         },
-        'skip': 'Site no longer embeds',
     }]
 
     def _clear_cookies(self, cdn_url):
@@ -242,16 +220,6 @@ class OdnoklassnikiIE(InfoExtractor):
             yield smuggle_url(x, {'referrer': url})
 
     def _real_extract(self, url):
-        try:
-            return self._extract_desktop(url)
-        except ExtractorError as e:
-            try:
-                return self._extract_mobile(url)
-            except ExtractorError:
-                # error message of desktop webpage is in English
-                raise e
-
-    def _extract_desktop(self, url):
         start_time = int_or_none(urllib.parse.parse_qs(
             urllib.parse.urlparse(url).query).get('fromTime', [None])[0])
 
@@ -261,7 +229,6 @@ class OdnoklassnikiIE(InfoExtractor):
 
         webpage = self._download_webpage(
             f'https://ok.ru/{mode}/{video_id}', video_id,
-            note='Downloading desktop webpage',
             headers={'Referer': smuggled['referrer']} if smuggled.get('referrer') else {})
 
         error = traverse_obj(webpage, {find_element(cls='vp_video_stub_txt')})
@@ -287,9 +254,7 @@ class OdnoklassnikiIE(InfoExtractor):
         flashvars = player['flashvars']
 
         metadata = flashvars.get('metadata')
-        if metadata:
-            metadata = self._parse_json(metadata, video_id)
-        else:
+        if not metadata:
             data = {}
             st_location = flashvars.get('location')
             if st_location:
@@ -302,7 +267,7 @@ class OdnoklassnikiIE(InfoExtractor):
         movie = metadata['movie']
 
         # Some embedded videos may not contain title in movie dict (e.g.
-        # http://ok.ru/video/62036049272859-0) thus we allow missing title
+        # https://ok.ru/video/62036049272859-0) thus we allow missing title
         # here and it's going to be extracted later by an extractor that
         # will process the actual embed.
         provider = metadata.get('provider')
@@ -416,36 +381,3 @@ class OdnoklassnikiIE(InfoExtractor):
 
         info['formats'] = formats
         return info
-
-    def _extract_mobile(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(
-            f'https://m.ok.ru/video/{video_id}', video_id,
-            note='Downloading mobile webpage')
-
-        error = self._search_regex(
-            r'видео</a>\s*<div\s+class="empty">(.+?)</div>',
-            webpage, 'error', default=None)
-        if error:
-            raise ExtractorError(error, expected=True)
-
-        json_data = self._search_regex(
-            r'data-video="(.+?)"', webpage, 'json data')
-        json_data = self._parse_json(unescapeHTML(json_data), video_id) or {}
-
-        redirect_url = self._request_webpage(HEADRequest(
-            json_data['videoSrc']), video_id, 'Requesting download URL').url
-        self._clear_cookies(redirect_url)
-
-        return {
-            'id': video_id,
-            'title': json_data.get('videoName'),
-            'duration': float_or_none(json_data.get('videoDuration'), scale=1000),
-            'thumbnail': json_data.get('videoPosterSrc'),
-            'formats': [{
-                'format_id': 'mobile',
-                'url': redirect_url,
-                'ext': 'mp4',
-            }],
-        }

yt_dlp/extractor/showroomlive.py

@@ -17,7 +17,11 @@ from ..utils.traversal import (
 )
 
 
-class ShowRoomLiveIE(InfoExtractor):
+class ShowRoomBaseIE(InfoExtractor):
+    _API_BASE = 'https://www.showroom-live.com/api'
+
+
+class ShowRoomLiveIE(ShowRoomBaseIE):
     IE_NAME = 'showroom:live'
     IE_DESC = 'SHOWROOM'
 
@@ -29,19 +33,11 @@ class ShowRoomLiveIE(InfoExtractor):
 
     def _real_extract(self, url):
         broadcaster_id = self._match_id(url)
-        webpage = self._download_webpage(
-            url, broadcaster_id, headers={'Accept-Language': 'ja'})
-        nuxt_data = self._search_nuxt_json(webpage, broadcaster_id)['data']
-
-        cookies = self._get_cookies(url)
-        sr_id = traverse_obj(cookies, ('sr_id', 'value', {str}, filter))
-        if not sr_id:
-            self.raise_login_required()
-
-        room_profile = traverse_obj(nuxt_data, (
-            f'roomProfile-{broadcaster_id}-{sr_id}', {dict}))
-        start_timestamp = traverse_obj(room_profile, ('current_live_started_at', {int_or_none}))
-        is_live = traverse_obj(room_profile, ('is_onlive', {bool}))
+        room_status = self._download_json(
+            f'{self._API_BASE}/room/status', broadcaster_id,
+            query={'room_url_key': broadcaster_id})
+        start_timestamp = traverse_obj(room_status, ('started_at', {int_or_none}))
+        is_live = traverse_obj(room_status, ('is_live', {bool}))
 
         if not is_live:
             if start_timestamp:
@@ -59,12 +55,15 @@ class ShowRoomLiveIE(InfoExtractor):
                 }
             raise UserNotLive(video_id=broadcaster_id)
 
-        room_id = traverse_obj(room_profile, ('room_id', {str_or_none}))
+        room_id = traverse_obj(room_status, ('room_id', {str_or_none}))
+        room_profile = self._download_json(
+            f'{self._API_BASE}/room/profile',
+            broadcaster_id, query={'room_id': room_id})
         room_name = traverse_obj(room_profile, (
             ('room_name', 'main_name'), {clean_html}, filter, any))
 
         streaming_url_list = self._download_json(
-            'https://www.showroom-live.com/api/live/streaming_url',
+            f'{self._API_BASE}/live/streaming_url',
             broadcaster_id, query={'room_id': room_id})
         m3u8_url = traverse_obj(streaming_url_list, (
             'streaming_url_list', lambda _, v: v['type'] == 'hls_all',
@@ -84,13 +83,13 @@ class ShowRoomLiveIE(InfoExtractor):
                 'description': ('description', {clean_html}, filter),
                 'genres': ('genre_name', {clean_html}, filter, all, filter),
                 'tags': ('live_tags', ..., 'name', {clean_html}, filter, all, filter),
-                'thumbnail': ('image_square', {url_or_none}),
+                'thumbnail': (('image_square', 'image'), {url_or_none}, any),
                 'view_count': ('view_num', {int_or_none}),
             }),
         }
 
 
-class ShowRoomVodIE(InfoExtractor):
+class ShowRoomVodIE(ShowRoomBaseIE):
     IE_NAME = 'showroom:vod'
 
     _VALID_URL = r'https?://(?:www\.)?showroom-live\.com/episode/watch\?(?:[^#]+&)?id=(?P<id>\w+)'
@@ -111,7 +110,7 @@ class ShowRoomVodIE(InfoExtractor):
             {extract_attributes}, 'data-episode', {json.loads}, {dict}))
 
         streaming_url_list = self._download_json(
-            'https://www.showroom-live.com/api/episode/streaming_url',
+            f'{self._API_BASE}/episode/streaming_url',
             episode_id, query={'episode_id': episode_id})
         m3u8_url = traverse_obj(streaming_url_list, (
             'streaming_url_list', 'hls_all',

yt_dlp/extractor/ted.py

@@ -46,7 +46,7 @@ class TedTalkIE(TedBaseIE):
         webpage = self._download_webpage(url, display_id)
         talk_info = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['videoData']
         video_id = talk_info['id']
-        player_data = self._parse_json(talk_info.get('playerData'), video_id)
+        player_data = talk_info.get('videoPlayerData') or {}
 
         http_url = None
         formats, subtitles = [], {}
@@ -193,8 +193,8 @@ class TedPlaylistIE(TedBaseIE):
         'url': 'https://www.ted.com/playlists/171/the_most_popular_talks_of_all',
         'info_dict': {
             'id': '171',
-            'title': 'The most popular talks of all time',
-            'description': 'md5:d2f22831dc86c7040e733a3cb3993d78',
+            'title': 'The most popular TED Talks of all time',
+            'description': 'md5:5346ef094754d2edd7e1a4cd3a166168',
         },
         'playlist_mincount': 25,
     }]

yt_dlp/extractor/tubitv.py

@@ -1,23 +1,17 @@
-import re
-
 from .common import InfoExtractor
-from ..networking import Request
 from ..utils import (
     ExtractorError,
     int_or_none,
     js_to_json,
     strip_or_none,
-    traverse_obj,
     url_or_none,
-    urlencode_postdata,
 )
+from ..utils.traversal import require, traverse_obj
 
 
 class TubiTvIE(InfoExtractor):
     IE_NAME = 'tubitv'
     _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:[a-z]{2}-[a-z]{2}/)?(?P<type>video|movies|tv-shows)/(?P<id>\d+)'
-    _LOGIN_URL = 'http://tubitv.com/login'
-    _NETRC_MACHINE = 'tubitv'
     _TESTS = [{
         'url': 'https://tubitv.com/movies/100004539/the-39-steps',
         'info_dict': {
@@ -27,7 +21,7 @@ class TubiTvIE(InfoExtractor):
             'description': 'md5:bb2f2dd337f0dc58c06cb509943f54c8',
             'uploader_id': 'abc2558d54505d4f0f32be94f2e7108c',
             'release_year': 1935,
-            'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
+            'thumbnail': r're:^https?://canvas-lb\.tubitv\.com/.+',
             'duration': 5187,
         },
         'params': {'skip_download': 'm3u8'},
@@ -44,7 +38,7 @@ class TubiTvIE(InfoExtractor):
             'season_number': 1,
             'uploader_id': '2a9273e728c510d22aa5c57d0646810b',
             'release_year': 2011,
-            'thumbnail': r're:^https?://.+\.(jpe?g|png)$',
+            'thumbnail': r're:^https?://canvas-lb\.tubitv\.com/.+',
             'duration': 1376,
         },
         'params': {'skip_download': 'm3u8'},
@@ -82,24 +76,11 @@ class TubiTvIE(InfoExtractor):
     _UNPLAYABLE_FORMATS = ('hlsv6_widevine', 'hlsv6_widevine_nonclearlead', 'hlsv6_playready_psshv0',
                            'hlsv6_fairplay', 'dash_widevine', 'dash_widevine_nonclearlead')
 
-    def _perform_login(self, username, password):
-        self.report_login()
-        form_data = {
-            'username': username,
-            'password': password,
-        }
-        payload = urlencode_postdata(form_data)
-        request = Request(self._LOGIN_URL, payload)
-        request.headers['Content-Type'] = 'application/x-www-form-urlencoded'
-        login_page = self._download_webpage(
-            request, None, False, 'Wrong login info')
-        if not re.search(r'id="tubi-logout"', login_page):
-            raise ExtractorError(
-                'Login failed (invalid username/password)', expected=True)
-
     def _real_extract(self, url):
         video_id, video_type = self._match_valid_url(url).group('id', 'type')
-        webpage = self._download_webpage(f'https://tubitv.com/{video_type}/{video_id}/', video_id)
+        webpage = self._download_webpage(
+            f'https://tubitv.com/{video_type}/{video_id}/', video_id,
+            headers=self.geo_verification_headers())
         video_data = self._search_json(
             r'window\.__data\s*=', webpage, 'data', video_id,
             transform_source=js_to_json)['video']['byId'][video_id]
@@ -113,7 +94,11 @@ class TubiTvIE(InfoExtractor):
             if resource_type == 'dash':
                 formats.extend(self._extract_mpd_formats(manifest_url, video_id, mpd_id=resource_type, fatal=False))
             elif resource_type in ('hlsv3', 'hlsv6'):
-                formats.extend(self._extract_m3u8_formats(manifest_url, video_id, 'mp4', m3u8_id=resource_type, fatal=False))
+                fmts = self._extract_m3u8_formats(manifest_url, video_id, 'mp4', m3u8_id=resource_type, fatal=False)
+                for fmt in fmts:
+                    if 'Audio Description' in fmt.get('format_note', ''):
+                        fmt['language_preference'] = -10
+                formats.extend(fmts)
             elif resource_type in self._UNPLAYABLE_FORMATS:
                 drm_formats = True
             else:
@@ -162,31 +147,34 @@ class TubiTvShowIE(InfoExtractor):
             'id': 'the-joy-of-painting-with-bob-ross',
         },
     }, {
-        'url': 'https://tubitv.com/series/2311/the-saddle-club/season-1',
+        'url': 'https://tubitv.com/series/300000435/the-saddle-club/season-1',
         'playlist_count': 26,
         'info_dict': {
             'id': 'the-saddle-club-season-1',
         },
     }, {
-        'url': 'https://tubitv.com/series/2311/the-saddle-club/season-3',
-        'playlist_count': 19,
+        'url': 'https://tubitv.com/series/300000435/the-saddle-club/season-2',
+        'playlist_count': 26,
         'info_dict': {
-            'id': 'the-saddle-club-season-3',
+            'id': 'the-saddle-club-season-2',
         },
     }, {
-        'url': 'https://tubitv.com/series/2311/the-saddle-club/',
-        'playlist_mincount': 71,
+        'url': 'https://tubitv.com/series/300000435/the-saddle-club/',
+        'playlist_mincount': 52,
         'info_dict': {
             'id': 'the-saddle-club',
         },
     }]
 
     def _entries(self, show_url, playlist_id, selected_season):
-        webpage = self._download_webpage(show_url, playlist_id)
+        webpage = self._download_webpage(show_url, playlist_id, headers=self.geo_verification_headers())
 
-        data = self._search_json(
-            r'window\.__REACT_QUERY_STATE__\s*=', webpage, 'data', playlist_id,
-            transform_source=js_to_json)['queries'][0]['state']['data']
+        react_query_state = self._search_json(
+            r'window\.__REACT_QUERY_STATE__\s*=', webpage,
+            'react query state', playlist_id, transform_source=js_to_json)
+        data = traverse_obj(react_query_state, (
+            'queries', lambda _, v: v['state']['data']['seasons'][0],
+            'state', 'data', any, {require('season data')}))
 
         # v['number'] is already a decimal string, but stringify to protect against API changes
         path = [lambda _, v: str(v['number']) == selected_season] if selected_season else [..., {dict}]

yt_dlp/extractor/twitch.py

@@ -44,7 +44,7 @@ class TwitchBaseIE(InfoExtractor):
         'CollectionSideBar': '016e1e4ccee0eb4698eb3bf1a04dc1c077fb746c78c82bac9a8f0289658fbd1a',
         'FilterableVideoTower_Videos': '67004f7881e65c297936f32c75246470629557a393788fb5a69d6d9a25a8fd5f',
         'ClipsCards__User': '1cd671bfa12cec480499c087319f26d21925e9695d1f80225aae6a4354f23088',
-        'ShareClipRenderStatus': '0a02bb974443b576f5579aab0fef1d4b7f44e58a8a256f0c5adfead0db70640f',
+        'ShareClipRenderStatus': '2db6a3b20eabf510bd3cf465ae2408834b59eb6b8af89ca73ab1486cacecfb63',
         'ChannelCollectionsContent': '5247910a19b1cd2b760939bf4cba4dcbd3d13bdf8c266decd16956f6ef814077',
         'StreamMetadata': 'ad022ca32220d5523d03a23cbcb5beaa1e0999889c1f8f78f9f2520dafb5cae6',
         'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',

yt_dlp/extractor/youtube/_base.py

@@ -125,6 +125,7 @@ INNERTUBE_CLIENTS = {
             'client': {
                 'clientName': 'WEB_EMBEDDED_PLAYER',
                 'clientVersion': '2.20260708.00.00',
+                'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)',
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 56,
@@ -363,6 +364,21 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
         'SUPPORTS_COOKIES': True,
     },
+    'tv_samsung': {
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'clientName': 'TVHTML5',
+                'clientVersion': '5.20260707',
+                'deviceMake': 'Samsung',
+                'deviceModel': 'UKS9800',
+                'userAgent': 'Mozilla/5.0 (SMART-TV; Linux; Tizen 2.4.0) AppleWebKit/538.1 (KHTML, like Gecko) Version/2.4.0 TV Safari/538.1',
+                'osName': 'Tizen',
+                'osVersion': '2.4.0',
+            },
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
+        'SUPPORTS_COOKIES': True,
+    },
     'tv_simply': {
         'INNERTUBE_CONTEXT': {
             'client': {

yt_dlp/extractor/youtube/_video.py

@@ -140,11 +140,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     _RETURN_TYPE = 'video'  # XXX: How to handle multifeed?
 
     _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
-    _DEFAULT_CLIENTS = ('visionos', 'web')
+    _DEFAULT_CLIENTS = ('tv_samsung', 'visionos', 'web')
     _DEFAULT_JSLESS_CLIENTS = ('visionos',)
-    _DEFAULT_AUTHED_CLIENTS = ('web_embedded', 'tv_downgraded', 'web')
+    _DEFAULT_AUTHED_CLIENTS = ('web_embedded', 'tv_samsung', 'web')
     # Premium does not require POT (except for subtitles)
-    _DEFAULT_PREMIUM_CLIENTS = ('web_creator', 'tv_downgraded', 'web')
+    _DEFAULT_PREMIUM_CLIENTS = ('web_creator', 'tv_samsung', 'web')
     _WEBPAGE_CLIENTS = ('web', 'web_safari')
     _DEFAULT_WEBPAGE_CLIENT = 'web'
 
@@ -3151,7 +3151,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 and any(p.is_available() for p in self._jsc_director.providers.values())
             ):
                 append_client('web_embedded')
-                append_client('tv_downgraded')
 
             # web_embedded can work around age-gate and age-verification for some embeddable videos
             if self._is_agegated(pr) and variant != 'web_embedded':
@@ -3640,7 +3639,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     f['source_preference'] = -1
 
                 # Deprioritize since its pre-merged m3u8 formats may have lower quality audio streams
-                if client_name == 'web_safari' and proto == 'hls' and live_status != 'is_live':
+                if client_name in ('web_safari', 'web_embedded') and proto == 'hls' and live_status != 'is_live':
                     f['source_preference'] -= 1
 
                 if missing_pot:

yt_dlp/extractor/youtube/pot/_director.py

@@ -76,7 +76,7 @@ class YoutubeIEContentProviderLogger(IEContentProviderLogger):
         if self.log_level <= self.LogLevel.ERROR:
             self.__ie._downloader.report_error(
                 self._format_msg(message), is_error=False,
-                tb=''.join(traceback.format_exception(None, cause, cause.__traceback__)) if cause else None)
+                tb=''.join(traceback.format_exception(cause)) if cause else None)
 
 
 class PoTokenCache:

yt_dlp/networking/_helper.py

@@ -52,25 +52,27 @@ def ssl_load_windows_store_certs(ssl_context, storename):
 
 def make_socks_proxy_opts(socks_proxy):
     url_components = urllib.parse.urlparse(socks_proxy)
-    if url_components.scheme.lower() == 'socks5':
+    scheme = url_components.scheme.lower()
+
+    if scheme == 'socks5':
         socks_type = ProxyType.SOCKS5
         rdns = False
-    elif url_components.scheme.lower() == 'socks5h':
+    elif scheme == 'socks5h':
         socks_type = ProxyType.SOCKS5
         rdns = True
-    elif url_components.scheme.lower() == 'socks4':
+    elif scheme == 'socks4':
         socks_type = ProxyType.SOCKS4
         rdns = False
-    elif url_components.scheme.lower() == 'socks4a':
+    elif scheme == 'socks4a':
         socks_type = ProxyType.SOCKS4A
         rdns = True
     else:
-        raise ValueError(f'Unknown SOCKS proxy version: {url_components.scheme.lower()}')
+        raise ValueError(f'Unknown SOCKS proxy version: {scheme}')
 
     def unquote_if_non_empty(s):
         if not s:
             return s
-        return urllib.parse.unquote_plus(s)
+        return urllib.parse.unquote(s)
     return {
         'proxytype': socks_type,
         'addr': url_components.hostname,
@@ -108,8 +110,6 @@ def make_ssl_context(
     context = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT)
     context.check_hostname = verify
     context.verify_mode = ssl.CERT_REQUIRED if verify else ssl.CERT_NONE
-    # OpenSSL 1.1.1+ Python 3.8+ keylog file
-    if hasattr(context, 'keylog_filename'):
     context.keylog_filename = os.environ.get('SSLKEYLOGFILE') or None
 
     # Some servers may reject requests if ALPN extension is not sent. See:

yt_dlp/networking/_requests.py

@@ -123,7 +123,7 @@ class RequestsResponseAdapter(Response):
         # Work around issue with `.read(amt)` then `.read()`
         # See: https://github.com/urllib3/urllib3/issues/3636
         if amt is None:
-            # compat: py3.9: Python 3.9 preallocates the whole read buffer, read in chunks
+            # Read in chunks to avoid preallocating a large buffer
             read_chunk = functools.partial(self.fp.read, 1 << 20, decode_content=True)
             return b''.join(iter(read_chunk, b''))
         # Interact with urllib3 response directly.

yt_dlp/networking/_urllib.py

@@ -161,17 +161,7 @@ class HTTPHandler(urllib.request.AbstractHTTPHandler):
         if decoded_response is not None:
             resp = urllib.request.addinfourl(io.BytesIO(decoded_response), old_resp.headers, old_resp.url, old_resp.code)
             resp.msg = old_resp.msg
-        # Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
-        # https://github.com/ytdl-org/youtube-dl/issues/6457).
-        if 300 <= resp.code < 400:
-            location = resp.headers.get('Location')
-            if location:
-                # As of RFC 2616 default charset is iso-8859-1 that is respected by Python 3
-                location = location.encode('iso-8859-1').decode()
-                location_escaped = normalize_url(location)
-                if location != location_escaped:
-                    del resp.headers['Location']
-                    resp.headers['Location'] = location_escaped
+
         return resp
 
     https_request = http_request
@@ -296,13 +286,9 @@ class UrllibResponseAdapter(Response):
     """
 
     def __init__(self, res: http.client.HTTPResponse | urllib.response.addinfourl):
-        # addinfourl: In Python 3.9+, .status was introduced and .getcode() was deprecated [1]
-        # HTTPResponse: .getcode() was deprecated, .status always existed [2]
-        # 1. https://docs.python.org/3/library/urllib.request.html#urllib.response.addinfourl.getcode
-        # 2. https://docs.python.org/3.10/library/http.client.html#http.client.HTTPResponse.status
         super().__init__(
             fp=res, headers=res.headers, url=res.url,
-            status=getattr(res, 'status', None) or res.getcode(), reason=getattr(res, 'reason', None))
+            status=res.status, reason=getattr(res, 'reason', None))
 
     def read(self, amt=None):
         if self.closed:
@@ -317,7 +303,9 @@ class UrllibResponseAdapter(Response):
                 # urllib's addinfourl does not close the underlying fp automatically when fully read
                 if isinstance(underlying, io.BytesIO):
                     # data URLs or in-memory responses (e.g. gzip/deflate/brotli decoded)
-                    if underlying.tell() >= len(underlying.getbuffer()):
+                    with underlying.getbuffer() as view:
+                        fully_read = underlying.tell() >= len(view)
+                    if fully_read:
                         self.close()
                 elif isinstance(underlying, io.BufferedReader) and amt is None:
                     # file URLs.

yt_dlp/networking/_websockets.py

@@ -164,6 +164,11 @@ class WebsocketsRH(WebSocketRequestHandler):
                 user_agent_header=None,
                 ssl=ssl_ctx if wsuri.secure else None,
                 close_timeout=0,  # not ideal, but prevents yt-dlp hanging
+                # Workaround for websockets>=17.1 support:
+                # connect() is intended to be used as a context manager and other usage has been deprecated.
+                # The `legacy` flag was added in 17.1 for backwards compat and has not yet been deprecated.
+                # Ref: https://github.com/python-websockets/websockets/commit/1f7f0e537233ac82e4ca51921678963c696c8c08
+                **({'legacy': True} if websockets_version >= (17, 1) else {}),
             )
             return WebsocketsResponseAdapter(conn, url=request.url)
 

yt_dlp/update.py

@@ -227,6 +227,10 @@ def _make_label(origin, tag, version=None):
     return f'{origin}@{tag}'
 
 
+class _GitHubError(Exception):
+    pass
+
+
 @dataclass
 class UpdateInfo:
     """
@@ -319,7 +323,14 @@ class Updater:
         path = 'latest/download' if tag == 'latest' else f'download/{tag}'
         url = f'https://github.com/{self.requested_repo}/releases/{path}/{name}'
         self.ydl.write_debug(f'Downloading {name} from {url}')
-        return self.ydl.urlopen(url).read()
+        response = self.ydl.urlopen(url)
+        # GitHub may send an error webpage response with HTTP status 200
+        # See https://github.com/yt-dlp/yt-dlp/issues/17550
+        prefix = response.read(512)
+        if b'<!DOCTYPE html>' in prefix:
+            raise _GitHubError('got error webpage instead of release asset')
+
+        return prefix + response.read()
 
     def _call_api(self, tag):
         tag = f'tags/{tag}' if tag != 'latest' else tag
@@ -358,7 +369,7 @@ class Updater:
         for tag in source_tags:
             try:
                 return self._download_asset('_update_spec', tag=tag).decode()
-            except network_exceptions as error:
+            except (_GitHubError, *network_exceptions) as error:
                 if isinstance(error, HTTPError) and error.status == 404:
                     continue
                 self._report_network_error(f'fetch update spec: {error}')
@@ -462,7 +473,7 @@ class Updater:
         if not is_non_updateable():
             try:
                 hashes = self._download_asset('SHA2-256SUMS', result_tag)
-            except network_exceptions as error:
+            except (_GitHubError, *network_exceptions) as error:
                 if not isinstance(error, HTTPError) or error.status != 404:
                     self._report_network_error(f'fetch checksums: {error}')
                     return None
@@ -525,7 +536,7 @@ class Updater:
 
         try:
             newcontent = self._download_asset(update_info.binary_name, update_info.tag)
-        except network_exceptions as e:
+        except (_GitHubError, *network_exceptions) as e:
             if isinstance(e, HTTPError) and e.status == 404:
                 return self._report_error(
                     f'The requested tag {self.requested_repo}@{update_info.tag} does not exist', True)
@@ -609,7 +620,7 @@ class Updater:
         self.ydl._download_retcode = 100
 
     def _report_permission_error(self, file):
-        self._report_error(f'Unable to write to {file}; try running as administrator', True)
+        self._report_error(f'Insufficient permissions to write to {file}', True)
 
     def _report_network_error(self, action, delim=';', tag=None):
         if not tag:

yt_dlp/utils/_utils.py

@@ -238,11 +238,9 @@ def find_xpath_attr(node, xpath, key, val=None):
     expr = xpath + (f'[@{key}]' if val is None else f"[@{key}='{val}']")
     return node.find(expr)
 
-# On python2.6 the xml.etree.ElementTree.Element methods don't support
-# the namespace parameter
-
 
 def xpath_with_ns(path, ns_map):
+    """Expand namespace-prefixed names to Clark notation."""
     components = [c.split(':') for c in path.split('/')]
     replaced = []
     for c in components:
@@ -876,7 +874,7 @@ class Popen(subprocess.Popen):
 
         self.__text_mode = kwargs.get('encoding') or kwargs.get('errors') or text or kwargs.get('universal_newlines')
         if text is True:
-            kwargs['universal_newlines'] = True  # For 3.6 compatibility
+            kwargs['text'] = True
             kwargs.setdefault('encoding', 'utf-8')
             kwargs.setdefault('errors', 'replace')
 
@@ -1012,7 +1010,7 @@ class ExtractorError(YoutubeDLError):
     def format_traceback(self):
         return join_nonempty(
             self.traceback and ''.join(traceback.format_tb(self.traceback)),
-            self.cause and ''.join(traceback.format_exception(None, self.cause, self.cause.__traceback__)[1:]),
+            self.cause and ''.join(traceback.format_exception(self.cause)[1:]),
             delim='\n') or None
 
     def __setattr__(self, name, value):
@@ -1960,14 +1958,8 @@ def setproctitle(title):
         libc = ctypes.cdll.LoadLibrary('libc.so.6')
     except OSError:
         return
-    except TypeError:
-        # LoadLibrary in Windows Python 2.7.13 only expects
-        # a bytestring, but since unicode_literals turns
-        # every string into a unicode string, it fails.
-        return
-    title_bytes = title.encode()
-    buf = ctypes.create_string_buffer(len(title_bytes))
-    buf.value = title_bytes
+
+    buf = ctypes.create_string_buffer(title.encode())
     try:
         # PR_SET_NAME = 15      Ref: /usr/include/linux/prctl.h
         libc.prctl(15, buf, 0, 0, 0)
@@ -2655,11 +2647,10 @@ def multipart_encode(data, boundary=None):
     Encode a dict to RFC 7578-compliant form-data
 
     data:
-        A dict where keys and values can be either Unicode or bytes-like
-        objects.
+        A dict where keys and values can be either str or bytes-like objects.
     boundary:
-        If specified a Unicode object, it's used as the boundary. Otherwise
-        a random boundary is generated.
+        An ASCII string to use as the boundary. If omitted, a random boundary
+        is generated.
 
     Reference: https://tools.ietf.org/html/rfc7578
     """
@@ -3138,18 +3129,26 @@ def get_compatible_ext(*, vcodecs, acodecs, vexts, aexts, preferences=None):
     return 'mkv' if allow_mkv else preferences[-1]
 
 
-def urlhandle_detect_ext(url_handle, default=NO_DEFAULT):
-    getheader = url_handle.headers.get
+def disposition_filename(headers):
+    filename = None
+    for name, value in headers.get_params(header='Content-Disposition') or ():
+        if name.lower() != 'filename':
+            continue
+        filename = value
+        if isinstance(value, tuple):  # Prefer filename* over filename
+            break
 
-    if cd := getheader('Content-Disposition'):
-        if m := re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd):
-            if ext := determine_ext(m.group('filename'), default_ext=None):
-                return ext
+    return email.utils.collapse_rfc2231_value(filename).strip() if filename is not None else None
+
+
+def urlhandle_detect_ext(url_handle, default=NO_DEFAULT):
+    headers = url_handle.headers
 
     return (
-        determine_ext(getheader('x-amz-meta-name'), default_ext=None)
-        or getheader('x-amz-meta-file-type')
-        or mimetype2ext(getheader('Content-Type'), default=default))
+        determine_ext(disposition_filename(headers), default_ext=None)
+        or determine_ext(headers.get('x-amz-meta-name'), default_ext=None)
+        or headers.get('x-amz-meta-file-type')
+        or mimetype2ext(headers.get('Content-Type'), default=default))
 
 
 def encode_data_uri(data, mime_type):
@@ -3391,10 +3390,15 @@ class download_range_func:
 
     def __eq__(self, other):
         return (isinstance(other, download_range_func)
-                and self.chapters == other.chapters and self.ranges == other.ranges)
+                and self.chapters == other.chapters
+                and self.ranges == other.ranges
+                and self.from_info == other.from_info)
 
     def __repr__(self):
-        return f'{__name__}.{type(self).__name__}({self.chapters}, {self.ranges})'
+        args = [repr(self.chapters), repr(self.ranges)]
+        if self.from_info:
+            args.append('from_info=True')
+        return f'{__name__}.{type(self).__name__}({", ".join(args)})'
 
 
 def parse_dfxp_time_expr(time_expr):
@@ -3422,7 +3426,7 @@ def ass_subtitles_timecode(seconds):
 def dfxp2srt(dfxp_data):
     """
     @param dfxp_data A bytes-like object containing DFXP data
-    @returns A unicode object containing converted SRT data
+    @returns A string containing the converted SRT data
     """
     LEGACY_NAMESPACES = (
         (b'http://www.w3.org/ns/ttml', [
@@ -5090,7 +5094,7 @@ class function_with_repr:
 
 
 class Namespace(types.SimpleNamespace):
-    """Immutable namespace"""
+    """SimpleNamespace iterable over attribute values"""
 
     def __iter__(self):
         return iter(self.__dict__.values())

yt_dlp/utils/jslib/devalue.py

@@ -1,10 +1,10 @@
 from __future__ import annotations
 
-import array
 import base64
 import datetime as dt
 import math
 import re
+import struct
 
 from .._utils import parse_iso8601
 
@@ -22,13 +22,13 @@ _ARRAY_TYPE_LOOKUP = {
     'Uint8ClampedArray': 'B',
     'Int16Array': 'h',
     'Uint16Array': 'H',
+    'Float16Array': 'e',
     'Int32Array': 'i',
     'Uint32Array': 'I',
     'Float32Array': 'f',
     'Float64Array': 'd',
-    'BigInt64Array': 'l',
-    'BigUint64Array': 'L',
-    'ArrayBuffer': 'B',
+    'BigInt64Array': 'q',
+    'BigUint64Array': 'Q',
 }
 
 
@@ -85,30 +85,31 @@ def parse_iter(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Cal
 
         if isinstance(value, list):
             if value and isinstance(value[0], str):
+                type_name = value[0]
                 # TODO: implement zips `strict=True`
-                if reviver := revivers.get(value[0]):
+                if reviver := revivers.get(type_name):
                     if value[1] == source:
                         # XXX: avoid infinite loop
-                        yield IndexError(f'{value[0]!r} cannot point to itself (index: {source})')
+                        yield IndexError(f'{type_name!r} cannot point to itself (index: {source})')
                         continue
                     # inverse order: resolve index, revive value
-                    stack.append((target, index, (value[0], value[1], reviver)))
+                    stack.append((target, index, (type_name, value[1], reviver)))
                     stack.append((target, index, value[1]))
                     continue
 
-                elif value[0] == 'Date':
+                elif type_name == 'Date':
                     try:
                         result = dt.datetime.fromtimestamp(parse_iso8601(value[1]), tz=dt.timezone.utc)
                     except Exception:
                         yield ValueError(f'invalid date: {value[1]!r}')
                         result = None
 
-                elif value[0] == 'Set':
+                elif type_name == 'Set':
                     result = [None] * (len(value) - 1)
                     for offset, new_source in enumerate(value[1:]):
                         stack.append((result, offset, new_source))
 
-                elif value[0] == 'Map':
+                elif type_name == 'Map':
                     result = []
                     for key, new_source in zip(*(iter(value[1:]),) * 2, strict=True):
                         pair = [None, None]
@@ -116,29 +117,101 @@ def parse_iter(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Cal
                         stack.append((pair, 1, new_source))
                         result.append(pair)
 
-                elif value[0] == 'RegExp':
+                elif type_name == 'RegExp':
                     # XXX: use jsinterp to translate regex flags
                     #      currently ignores `value[2]`
                     result = re.compile(value[1])
 
-                elif value[0] == 'Object':
+                elif type_name == 'Object':
                     result = value[1]
 
-                elif value[0] == 'BigInt':
+                elif type_name == 'BigInt':
                     result = int(value[1])
 
-                elif value[0] == 'null':
+                elif type_name == 'null':
                     result = {}
                     for key, new_source in zip(*(iter(value[1:]),) * 2, strict=True):
                         stack.append((result, key, new_source))
 
-                elif value[0] in _ARRAY_TYPE_LOOKUP:
-                    typecode = _ARRAY_TYPE_LOOKUP[value[0]]
+                elif type_name == 'ArrayBuffer':
+                    try:
+                        if len(value) < 2 or not isinstance(value[1], str):
+                            raise TypeError(f'Invalid ArrayBuffer encoding: {value[1:]!r}')
+                        result = base64.b64decode(value[1])
+                    except Exception as error:
+                        yield ValueError(f'Invalid ArrayBuffer at {source}: {error}')
+                        result = None
+
+                elif type_name in _ARRAY_TYPE_LOOKUP or type_name == 'DataView':
+                    try:
+                        if len(value) < 2:
+                            raise TypeError('Missing ArrayBuffer reference')
+                        if isinstance(value[1], str):
                             data = base64.b64decode(value[1])
-                    result = array.array(typecode, data).tolist()
+                        else:
+                            buffer_index = value[1]
+                            if (
+                                not isinstance(buffer_index, int)
+                                or isinstance(buffer_index, bool)
+                                or not 0 <= buffer_index < len(parsed)
+                            ):
+                                raise IndexError(f'Invalid ArrayBuffer index: {buffer_index!r}')
+
+                            if buffer_index in resolved:
+                                data = resolved[buffer_index]
+                                if not isinstance(data, bytes):
+                                    raise TypeError(f'Invalid ArrayBuffer reference: {buffer_index!r}')
+                            else:
+                                buffer = parsed[buffer_index]
+                                if not (
+                                    isinstance(buffer, list)
+                                    and len(buffer) >= 2
+                                    and buffer[0] == 'ArrayBuffer'
+                                    and isinstance(buffer[1], str)
+                                ):
+                                    raise TypeError(f'Invalid ArrayBuffer reference: {buffer_index!r}')
+                                data = resolved[buffer_index] = base64.b64decode(buffer[1])
+
+                        offset = value[2] if len(value) > 2 else 0
+                        if not isinstance(offset, int) or isinstance(offset, bool) or offset < 0:
+                            raise ValueError(f'Invalid byte offset: {offset!r}')
+
+                        length = value[3] if len(value) > 3 else None
+                        if length is not None and (
+                            not isinstance(length, int) or isinstance(length, bool) or length < 0
+                        ):
+                            raise ValueError(f'Invalid length: {length!r}')
+
+                        if type_name == 'DataView':
+                            end = len(data) if length is None else offset + length
+                            if offset > len(data) or end > len(data):
+                                raise ValueError('View exceeds ArrayBuffer length')
+                            result = data[offset:end]
+                        else:
+                            typecode = _ARRAY_TYPE_LOOKUP[type_name]
+                            itemsize = struct.calcsize(f'={typecode}')
+                            if offset % itemsize:
+                                raise ValueError(f'Byte offset {offset} is not aligned to {itemsize}-byte elements')
+                            if offset > len(data):
+                                raise ValueError('View exceeds ArrayBuffer length')
+
+                            if length is None:
+                                view = data[offset:]
+                                if len(view) % itemsize:
+                                    raise ValueError(f'Byte length is not a multiple of {itemsize}')
+                            else:
+                                end = offset + length * itemsize
+                                if end > len(data):
+                                    raise ValueError('View exceeds ArrayBuffer length')
+                                view = data[offset:end]
+
+                            result = [item[0] for item in struct.iter_unpack(f'={typecode}', view)]
+                    except Exception as error:
+                        yield ValueError(f'Invalid {type_name} at {source}: {error}')
+                        result = None
 
                 else:
-                    yield TypeError(f'invalid type at {source}: {value[0]!r}')
+                    yield TypeError(f'Invalid type at {source}: {type_name!r}')
                     result = None
             else:
                 result = len(value) * [None]

yt_dlp/utils/traversal.py

@@ -360,12 +360,12 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
         if not url_or_none(sub.get('url')) and not sub.get('data'):
             continue
         sub_id = sub.pop('id', None)
-        if not isinstance(sub_id, str):
+        if not isinstance(sub_id, str) or not sub_id:
             if not lang:
                 continue
             sub_id = lang
         sub_ext = sub.get('ext')
-        if not isinstance(sub_ext, str):
+        if not isinstance(sub_ext, str) or not sub_ext:
             if not ext:
                 sub.pop('ext', None)
             else: