Oops

Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com>

.github/workflows/release.yml

@@ -282,6 +282,7 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           verbose: true
+          attestations: false  # Currently doesn't work w/ reusable workflows (breaks nightly)
 
   publish:
     needs: [prepare, build]

README.md

@@ -1791,7 +1791,7 @@ The following extractors use this feature:
 * `key_query`: Passthrough the master m3u8 URL query to its HLS AES-128 decryption key URI if no value is provided, or else apply the query string given as `key_query=VALUE`. Note that this will have no effect if the key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg
 * `hls_key`: An HLS AES-128 key URI *or* key (as hex), and optionally the IV (as hex), in the form of `(URI|KEY)[,IV]`; e.g. `generic:hls_key=ABCDEF1234567980,0xFEDCBA0987654321`. Passing any of these values will force usage of the native HLS downloader and override the corresponding values found in the m3u8 playlist
 * `is_live`: Bypass live HLS detection and manually set `live_status` - a value of `false` will set `not_live`, any other value (or no value) will set `is_live`
-* `impersonate`: Target(s) to try and impersonate with the initial webpage request; e.g. `safari,chrome-110`. By default any available target will be used. Use `false` to disable impersonation
+* `impersonate`: Target(s) to try and impersonate with the initial webpage request; e.g. `generic:impersonate=safari,chrome-110`. Use `generic:impersonate` to impersonate any available target, and use `generic:impersonate=false` to disable impersonation (default)
 
 #### funimation
 * `language`: Audio languages to extract, e.g. `funimation:language=english,japanese`

devscripts/changelog_override.json

@@ -216,5 +216,23 @@
         "action": "add",
         "when": "d784464399b600ba9516bbcec6286f11d68974dd",
         "short": "[priority] **The minimum *required* Python version has been raised to 3.9**\nPython 3.8 reached its end-of-life on 2024.10.07, and yt-dlp has now removed support for it. As an unfortunate side effect, the official `yt-dlp.exe` and `yt-dlp_x86.exe` binaries are no longer supported on Windows 7. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)"
+    },
+    {
+        "action": "change",
+        "when": "914af9a0cf51c9a3f74aa88d952bee8334c67511",
+        "short": "Expand paths in `--plugin-dirs` (#11334)",
+        "authors": ["bashonly"]
+    },
+    {
+        "action": "change",
+        "when": "c29f5a7fae93a08f3cfbb6127b2faa75145b06a0",
+        "short": "[ie/generic] Do not impersonate by default (#11336)",
+        "authors": ["bashonly"]
+    },
+    {
+        "action": "change",
+        "when": "57212a5f97ce367590aaa5c3e9a135eead8f81f7",
+        "short": "[ie/vimeo] Fix API retries (#11351)",
+        "authors": ["bashonly"]
     }
 ]

devscripts/make_changelog.py

@@ -71,14 +71,13 @@ class CommitGroup(enum.Enum):
     def get(cls, value: str) -> tuple[CommitGroup | None, str | None]:
         group, _, subgroup = (group.strip().lower() for group in value.partition('/'))
 
-        result = cls.group_lookup().get(group)
-        if not result:
-            if subgroup:
-                return None, value
-            subgroup = group
-            result = cls.subgroup_lookup().get(subgroup)
+        if result := cls.group_lookup().get(group):
+            return result, subgroup or None
 
-        return result, subgroup or None
+        if subgroup:
+            return None, value
+
+        return cls.subgroup_lookup().get(group), group or None
 
 
 @dataclass
@@ -136,8 +135,7 @@ class Changelog:
                 first = False
                 yield '\n<details><summary><h3>Changelog</h3></summary>\n'
 
-            group = groups[item]
-            if group:
+            if group := groups[item]:
                 yield self.format_module(item.value, group)
 
         if self._collapsible:
@@ -253,7 +251,7 @@ class CommitRange:
         ''', re.VERBOSE | re.DOTALL)
     EXTRACTOR_INDICATOR_RE = re.compile(r'(?:Fix|Add)\s+Extractors?', re.IGNORECASE)
     REVERT_RE = re.compile(r'(?:\[[^\]]+\]\s+)?(?i:Revert)\s+([\da-f]{40})')
-    FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert|Improve)\s+([\da-f]{40})')
+    FIXES_RE = re.compile(r'(?i:(?:bug\s*)?fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Improve)\s+([\da-f]{40})')
     UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
 
     def __init__(self, start, end, default_author=None):
@@ -287,11 +285,16 @@ class CommitRange:
             short = next(lines)
             skip = short.startswith('Release ') or short == '[version] update'
 
+            fix_commitish = None
+            if match := self.FIXES_RE.search(short):
+                fix_commitish = match.group(1)
+
             authors = [default_author] if default_author else []
             for line in iter(lambda: next(lines), self.COMMIT_SEPARATOR):
-                match = self.AUTHOR_INDICATOR_RE.match(line)
-                if match:
+                if match := self.AUTHOR_INDICATOR_RE.match(line):
                     authors = sorted(map(str.strip, line[match.end():].split(',')), key=str.casefold)
+                if not fix_commitish and (match := self.FIXES_RE.fullmatch(line)):
+                    fix_commitish = match.group(1)
 
             commit = Commit(commit_hash, short, authors)
             if skip and (self._start or not i):
@@ -301,21 +304,17 @@ class CommitRange:
                 logger.debug(f'Reached Release commit, breaking: {commit}')
                 break
 
-            revert_match = self.REVERT_RE.fullmatch(commit.short)
-            if revert_match:
-                reverts[revert_match.group(1)] = commit
+            if match := self.REVERT_RE.fullmatch(commit.short):
+                reverts[match.group(1)] = commit
                 continue
 
-            fix_match = self.FIXES_RE.search(commit.short)
-            if fix_match:
-                commitish = fix_match.group(1)
-                fixes[commitish].append(commit)
+            if fix_commitish:
+                fixes[fix_commitish].append(commit)
 
             commits[commit.hash] = commit
 
         for commitish, revert_commit in reverts.items():
-            reverted = commits.pop(commitish, None)
-            if reverted:
+            if reverted := commits.pop(commitish, None):
                 logger.debug(f'{commitish} fully reverted {reverted}')
             else:
                 commits[revert_commit.hash] = revert_commit
@@ -461,8 +460,7 @@ def create_changelog(args):
 
     logger.info(f'Loaded {len(commits)} commits')
 
-    new_contributors = get_new_contributors(args.contributors_path, commits)
-    if new_contributors:
+    if new_contributors := get_new_contributors(args.contributors_path, commits):
         if args.contributors:
             write_file(args.contributors_path, '\n'.join(new_contributors) + '\n', mode='a')
         logger.info(f'New contributors: {", ".join(new_contributors)}')

test/test_InfoExtractor.py

@@ -53,6 +53,18 @@ class TestInfoExtractor(unittest.TestCase):
     def test_ie_key(self):
         self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
 
+    def test_get_netrc_login_info(self):
+        for params in [
+            {'usenetrc': True, 'netrc_location': './test/testdata/netrc/netrc'},
+            {'netrc_cmd': f'{sys.executable} ./test/testdata/netrc/print_netrc.py'},
+        ]:
+            ie = DummyIE(FakeYDL(params))
+            self.assertEqual(ie._get_netrc_login_info(netrc_machine='normal_use'), ('user', 'pass'))
+            self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_user'), ('', 'pass'))
+            self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_pass'), ('user', ''))
+            self.assertEqual(ie._get_netrc_login_info(netrc_machine='both_empty'), ('', ''))
+            self.assertEqual(ie._get_netrc_login_info(netrc_machine='nonexistent'), (None, None))
+
     def test_html_search_regex(self):
         html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
         search = lambda re, *args: self.ie._html_search_regex(re, html, *args)

test/test_traversal.py

@@ -12,9 +12,10 @@ from yt_dlp.utils import (
     str_or_none,
 )
 from yt_dlp.utils.traversal import (
-    traverse_obj,
     require,
     subs_list_to_dict,
+    traverse_obj,
+    trim_str,
 )
 
 _TEST_DATA = {
@@ -495,6 +496,20 @@ class TestTraversalHelpers:
             {'url': 'https://example.com/subs/en2', 'ext': 'ext'},
         ]}, '`quality` key should sort subtitle list accordingly'
 
+    def test_trim_str(self):
+        with pytest.raises(TypeError):
+            trim_str('positional')
+
+        assert callable(trim_str(start='a'))
+        assert trim_str(start='ab')('abc') == 'c'
+        assert trim_str(end='bc')('abc') == 'a'
+        assert trim_str(start='a', end='c')('abc') == 'b'
+        assert trim_str(start='ab', end='c')('abc') == ''
+        assert trim_str(start='a', end='bc')('abc') == ''
+        assert trim_str(start='ab', end='bc')('abc') == ''
+        assert trim_str(start='abc', end='abc')('abc') == ''
+        assert trim_str(start='', end='')('abc') == 'abc'
+
 
 class TestDictGet:
     def test_dict_get(self):

test/test_utils.py

@@ -4,6 +4,7 @@
 import os
 import sys
 import unittest
+import unittest.mock
 import warnings
 import datetime as dt
 
@@ -71,6 +72,7 @@ from yt_dlp.utils import (
     intlist_to_bytes,
     iri_to_uri,
     is_html,
+    join_nonempty,
     js_to_json,
     limit_length,
     locked_file,
@@ -343,11 +345,13 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(remove_start(None, 'A - '), None)
         self.assertEqual(remove_start('A - B', 'A - '), 'B')
         self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
+        self.assertEqual(remove_start('non-empty', ''), 'non-empty')
 
     def test_remove_end(self):
         self.assertEqual(remove_end(None, ' - B'), None)
         self.assertEqual(remove_end('A - B', ' - B'), 'A')
         self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
+        self.assertEqual(remove_end('non-empty', ''), 'non-empty')
 
     def test_remove_quotes(self):
         self.assertEqual(remove_quotes(None), None)
@@ -2148,6 +2152,16 @@ Line 1
             assert run_shell(args) == expected
             assert run_shell(shell_quote(args, shell=True)) == expected
 
+    def test_partial_application(self):
+        assert callable(int_or_none(scale=10)), 'missing positional parameter should apply partially'
+        assert int_or_none(10, scale=0.1) == 100, 'positionally passed argument should call function'
+        assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
+        assert int_or_none(scale=0.1)(10) == 100, 'call after partial applicatino should call the function'
+
+        assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially'
+        assert callable(join_nonempty()), 'varargs positional should apply partially'
+        assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function'
+
 
 if __name__ == '__main__':
     unittest.main()

test/testdata/netrc/netrc

@@ -0,0 +1,4 @@
+machine normal_use login user password pass
+machine empty_user login "" password pass
+machine empty_pass login user password ""
+machine both_empty login "" password ""

test/testdata/netrc/print_netrc.py

@@ -0,0 +1,2 @@
+with open('./test/testdata/netrc/netrc', encoding='utf-8') as fp:
+    print(fp.read())

yt_dlp/YoutubeDL.py

@@ -2849,13 +2849,10 @@ class YoutubeDL:
             sanitize_string_field(fmt, 'format_id')
             sanitize_numeric_fields(fmt)
             fmt['url'] = sanitize_url(fmt['url'])
-            if fmt.get('ext') is None:
-                fmt['ext'] = determine_ext(fmt['url']).lower()
+            FormatSorter._fill_sorting_fields(fmt)
             if fmt['ext'] in ('aac', 'opus', 'mp3', 'flac', 'vorbis'):
                 if fmt.get('acodec') is None:
                     fmt['acodec'] = fmt['ext']
-            if fmt.get('protocol') is None:
-                fmt['protocol'] = determine_protocol(fmt)
             if fmt.get('resolution') is None:
                 fmt['resolution'] = self.format_resolution(fmt, default=None)
             if fmt.get('dynamic_range') is None and fmt.get('vcodec') != 'none':

yt_dlp/extractor/_extractors.py

@@ -401,8 +401,6 @@ from .cmt import CMTIE
 from .cnbc import CNBCVideoIE
 from .cnn import (
     CNNIE,
-    CNNArticleIE,
-    CNNBlogsIE,
     CNNIndonesiaIE,
 )
 from .comedycentral import (

yt_dlp/extractor/ccma.py

@@ -12,53 +12,86 @@ from ..utils import (
 
 
 class CCMAIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ccma\.cat/(?:[^/]+/)*?(?P<type>video|audio)/(?P<id>\d+)'
+    IE_DESC = '3Cat, TV3 and Catalunya Ràdio'
+    _VALID_URL = r'https?://(?:www\.)?3cat\.cat/(?:3cat|tv3/sx3)/[^/?#]+/(?P<type>video|audio)/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://www.ccma.cat/tv3/alacarta/lespot-de-la-marato-de-tv3/lespot-de-la-marato-de-tv3/video/5630208/',
+        # ccma.cat/tv3/alacarta/ URLs redirect to 3cat.cat/3cat/
+        'url': 'https://www.3cat.cat/3cat/lespot-de-la-marato-de-tv3/video/5630208/',
         'md5': '7296ca43977c8ea4469e719c609b0871',
         'info_dict': {
             'id': '5630208',
             'ext': 'mp4',
-            'title': 'L\'espot de La Marató de TV3',
+            'title': 'L\'espot de La Marató 2016: Ictus i les lesions medul·lars i cerebrals traumàtiques',
             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
             'timestamp': 1478608140,
             'upload_date': '20161108',
             'age_limit': 0,
+            'alt_title': 'EsportMarató2016WEB_PerPublicar',
+            'duration': 79,
+            'thumbnail': 'https://img.3cat.cat/multimedia/jpg/4/6/1478536106664.jpg',
+            'series': 'Dedicada a l\'ictus i les lesions medul·lars i cerebrals traumàtiques',
+            'categories': ['Divulgació'],
         },
     }, {
-        'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
+        # ccma.cat/catradio/alacarta/ URLs redirect to 3cat.cat/3cat/
+        'url': 'https://www.3cat.cat/3cat/el-consell-de-savis-analitza-el-derbi/audio/943685/',
         'md5': 'fa3e38f269329a278271276330261425',
         'info_dict': {
             'id': '943685',
             'ext': 'mp3',
             'title': 'El Consell de Savis analitza el derbi',
             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
-            'upload_date': '20170512',
-            'timestamp': 1494622500,
+            'upload_date': '20161217',
+            'timestamp': 1482011700,
             'vcodec': 'none',
             'categories': ['Esports'],
+            'series': 'Tot gira',
+            'duration': 821,
+            'thumbnail': 'https://img.3cat.cat/multimedia/jpg/8/9/1482002602598.jpg',
         },
     }, {
-        'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
-        'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
+        'url': 'https://www.3cat.cat/3cat/crims-josep-tallada-lespereu-me-part-1/video/6031387/',
+        'md5': '27493513d08a3e5605814aee9bb778d2',
         'info_dict': {
             'id': '6031387',
             'ext': 'mp4',
-            'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
+            'title': 'T1xC5 - Josep Talleda, l\'"Espereu-me" (part 1)',
             'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
-            'timestamp': 1582577700,
+            'timestamp': 1582577919,
             'upload_date': '20200224',
-            'subtitles': 'mincount:4',
-            'age_limit': 16,
+            'subtitles': 'mincount:1',
+            'age_limit': 13,
             'series': 'Crims',
+            'thumbnail': 'https://img.3cat.cat/multimedia/jpg/1/9/1582564376991.jpg',
+            'duration': 3203,
+            'categories': ['Divulgació'],
+            'alt_title': 'Crims - 5 - Josep Talleda, l\'"Espereu-me" (1a part) - Josep Talleda, l\'"Espereu-me" (part 1)',
+            'episode_number': 5,
+            'episode': 'Episode 5',
+        },
+    }, {
+        'url': 'https://www.3cat.cat/tv3/sx3/una-mosca-volava-per-la-llum/video/5759227/',
+        'info_dict': {
+            'id': '5759227',
+            'ext': 'mp4',
+            'title': 'Una mosca volava per la llum',
+            'alt_title': '17Z004Ç UNA MOSCA VOLAVA PER LA LLUM',
+            'description': 'md5:9ab64276944b0825336f4147f13f7854',
+            'series': 'Mic',
+            'upload_date': '20180411',
+            'timestamp': 1523440105,
+            'duration': 160,
+            'age_limit': 0,
+            'thumbnail': 'https://img.3cat.cat/multimedia/jpg/6/1/1524071667216.jpg',
+            'categories': ['Música'],
         },
     }]
 
     def _real_extract(self, url):
-        media_type, media_id = self._match_valid_url(url).groups()
+        media_type, media_id = self._match_valid_url(url).group('type', 'id')
 
         media = self._download_json(
-            'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
+            'http://api-media.3cat.cat/pvideo/media.jsp', media_id, query={
                 'media': media_type,
                 'idint': media_id,
                 'format': 'dm',

yt_dlp/extractor/cnn.py

@@ -1,146 +1,226 @@
+import functools
+import json
+import re
+
 from .common import InfoExtractor
-from .turner import TurnerBaseIE
-from ..utils import merge_dicts, try_call, url_basename
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    int_or_none,
+    merge_dicts,
+    parse_duration,
+    parse_iso8601,
+    parse_resolution,
+    try_call,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import find_elements, traverse_obj
 
 
-class CNNIE(TurnerBaseIE):
-    _VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
+class CNNIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:edition|www|money|cnnespanol)\.)?cnn\.com/(?!audio/)(?P<display_id>[^?#]+?)(?:[?#]|$|/index\.html)'
 
     _TESTS = [{
-        'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
-        'md5': '3e6121ea48df7e2259fe73a0628605c4',
+        'url': 'https://www.cnn.com/2024/05/31/sport/video/jadon-sancho-borussia-dortmund-champions-league-exclusive-spt-intl',
         'info_dict': {
-            'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
+            'id': 'med0e97ad0d154f56e29aa96e57192a14226734b6b',
+            'display_id': '2024/05/31/sport/video/jadon-sancho-borussia-dortmund-champions-league-exclusive-spt-intl',
             'ext': 'mp4',
-            'title': 'Nadal wins 8th French Open title',
-            'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
-            'duration': 135,
-            'upload_date': '20130609',
+            'upload_date': '20240531',
+            'description': 'md5:844bcdb0629e1877a7a466c913f4c19c',
+            'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/gettyimages-2151936122.jpg?c=original',
+            'duration': 373.0,
+            'timestamp': 1717148586,
+            'title': 'Borussia Dortmund star Jadon Sancho seeks Wembley redemption after 2020 Euros hurt',
+            'modified_date': '20240531',
+            'modified_timestamp': 1717150140,
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
-        'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29',
-        'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
+        'url': 'https://edition.cnn.com/2024/06/11/politics/video/inmates-vote-jail-nevada-murray-dnt-ac360-digvid',
         'info_dict': {
-            'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
+            'id': 'me522945c4709b299e5cb8657900a7a21ad3b559f9',
+            'display_id': '2024/06/11/politics/video/inmates-vote-jail-nevada-murray-dnt-ac360-digvid',
             'ext': 'mp4',
-            'title': "Student's epic speech stuns new freshmen",
-            'description': 'A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from "2001: A Space Odyssey."',
-            'upload_date': '20130821',
+            'description': 'md5:e0120fe5da9ad8259fd707c1cbb64a60',
+            'title': 'Here’s how some inmates in closely divided state are now able to vote from jail',
+            'timestamp': 1718158269,
+            'upload_date': '20240612',
+            'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/still-20701554-13565-571-still.jpg?c=original',
+            'duration': 202.0,
+            'modified_date': '20240612',
+            'modified_timestamp': 1718158509,
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
-        'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
-        'md5': 'f14d02ebd264df951feb2400e2c25a1b',
+        'url': 'https://edition.cnn.com/2024/06/11/style/king-charles-portrait-vandalized/index.html',
         'info_dict': {
-            'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
+            'id': 'mef5f52b9e1fe28b1ad192afcbc9206ae984894b68',
+            'display_id': '2024/06/11/style/king-charles-portrait-vandalized',
             'ext': 'mp4',
-            'title': 'Nashville Ep. 1: Hand crafted skateboards',
-            'description': 'md5:e7223a503315c9f150acac52e76de086',
-            'upload_date': '20141222',
+            'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/still-20701257-8846-816-still.jpg?c=original',
+            'description': 'md5:19f78338ccec533db0fa8a4511012dae',
+            'title': 'Video shows King Charles\' portrait being vandalized by activists',
+            'timestamp': 1718113852,
+            'upload_date': '20240611',
+            'duration': 51.0,
+            'modified_timestamp': 1718116193,
+            'modified_date': '20240611',
         },
-        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
-        'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
-        'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
+        'url': 'https://edition.cnn.com/videos/media/2022/12/05/robin-meade-final-sign-off-broadcast-hln-mxp-contd-vpx.hln',
         'info_dict': {
-            'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
+            'id': 'mefba13799201b084ea3b1d0f7ca820ae94d4bb5b2',
+            'display_id': 'videos/media/2022/12/05/robin-meade-final-sign-off-broadcast-hln-mxp-contd-vpx.hln',
             'ext': 'mp4',
-            'title': '5 stunning stats about Netflix',
-            'description': 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn\'t know.',
-            'upload_date': '20160819',
+            'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/221205163510-robin-meade-sign-off.jpg?c=original',
+            'duration': 158.0,
+            'title': 'Robin Meade signs off after HLN\'s last broadcast',
+            'description': 'md5:cff3c62d18d2fbc6c5c75cb029b7353b',
+            'upload_date': '20221205',
+            'timestamp': 1670284296,
+            'modified_timestamp': 1670332404,
+            'modified_date': '20221206',
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+        'params': {'format': 'direct'},
+    }, {
+        'url': 'https://cnnespanol.cnn.com/video/ataque-misil-israel-beirut-libano-octubre-trax',
+        'info_dict': {
+            'id': 'me484a43722642aa00627b812fe928f2e99c6e2997',
+            'ext': 'mp4',
+            'display_id': 'video/ataque-misil-israel-beirut-libano-octubre-trax',
+            'timestamp': 1729501452,
+            'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/ataqeubeirut-1.jpg?c=original',
+            'description': 'md5:256ee7137d161f776cda429654135e52',
+            'upload_date': '20241021',
+            'duration': 31.0,
+            'title': 'VIDEO | Israel lanza un nuevo ataque sobre Beirut',
+            'modified_date': '20241021',
+            'modified_timestamp': 1729501530,
         },
     }, {
-        'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
-        'only_matching': True,
-    }, {
-        'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
-        'only_matching': True,
-    }, {
-        'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
-        'only_matching': True,
+        'url': 'https://edition.cnn.com/2024/10/16/politics/kamala-harris-fox-news-interview/index.html',
+        'info_dict': {
+            'id': '2024/10/16/politics/kamala-harris-fox-news-interview',
+        },
+        'playlist_count': 2,
+        'playlist': [{
+            'md5': '073ffab87b8bef97c9913e71cc18ef9e',
+            'info_dict': {
+                'id': 'me19d548fdd54df0924087039283128ef473ab397d',
+                'ext': 'mp4',
+                'title': '\'I\'m not finished\': Harris interview with Fox News gets heated',
+                'display_id': 'kamala-harris-fox-news-interview-ebof-digvid',
+                'description': 'md5:e7dd3d1a04df916062230b60ca419a0a',
+                'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/harris-20241016234916617.jpg?c=original',
+                'duration': 173.0,
+                'timestamp': 1729122182,
+                'upload_date': '20241016',
+                'modified_timestamp': 1729194706,
+                'modified_date': '20241017',
+            },
+            'params': {'format': 'direct'},
+        }, {
+            'md5': '11604ab4af83b650826753f1ccb8ecff',
+            'info_dict': {
+                'id': 'med04507d8ca3da827001f63d22af321ec29c7d97b',
+                'ext': 'mp4',
+                'title': '\'Wise\': Buttigieg on Harris\' handling of interview question about gender transition surgery',
+                'display_id': 'pete-buttigieg-harris-fox-newssrc-digvid',
+                'description': 'md5:602a8a7e853ed5e574acd3159428c98e',
+                'thumbnail': 'https://media.cnn.com/api/v1/images/stellar/prod/buttigieg-20241017040412074.jpg?c=original',
+                'duration': 145.0,
+                'timestamp': 1729137765,
+                'upload_date': '20241017',
+                'modified_timestamp': 1729138184,
+                'modified_date': '20241017',
+            },
+            'params': {'format': 'direct'},
+        }],
     }]
 
-    _CONFIG = {
-        # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
-        'edition': {
-            'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
-            'media_src': 'http://pmd.cdn.turner.com/cnn/big',
-        },
-        # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
-        'money': {
-            'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
-            'media_src': 'http://ht3.cdn.turner.com/money/big',
-        },
-    }
-
-    def _extract_timestamp(self, video_data):
-        # TODO: fix timestamp extraction
-        return None
-
     def _real_extract(self, url):
-        sub_domain, path, page_title = self._match_valid_url(url).groups()
-        if sub_domain not in ('money', 'edition'):
-            sub_domain = 'edition'
-        config = self._CONFIG[sub_domain]
-        return self._extract_cvp_info(
-            config['data_src'] % path, page_title, {
-                'default': {
-                    'media_src': config['media_src'],
-                },
-                'f4m': {
-                    'host': 'cnn-vh.akamaihd.net',
-                },
+        display_id = self._match_valid_url(url).group('display_id')
+        webpage = self._download_webpage(url, display_id)
+        app_id = traverse_obj(
+            self._search_json(r'window\.env\s*=', webpage, 'window env', display_id, default={}),
+            ('TOP_AUTH_SERVICE_APP_ID', {str}))
+
+        entries = []
+        for player_data in traverse_obj(webpage, (
+                {find_elements(tag='div', attr='data-component-name', value='video-player', html=True)},
+                ..., {extract_attributes}, all, lambda _, v: v['data-media-id'])):
+            media_id = player_data['data-media-id']
+            parent_uri = player_data.get('data-video-resource-parent-uri')
+            formats, subtitles = [], {}
+
+            video_data = {}
+            if parent_uri:
+                video_data = self._download_json(
+                    'https://fave.api.cnn.io/v1/video', media_id, fatal=False,
+                    query={
+                        'id': media_id,
+                        'stellarUri': parent_uri,
+                    })
+                for direct_url in traverse_obj(video_data, ('files', ..., 'fileUri', {url_or_none})):
+                    resolution, bitrate = None, None
+                    if mobj := re.search(r'-(?P<res>\d+x\d+)_(?P<tbr>\d+)k\.mp4', direct_url):
+                        resolution, bitrate = mobj.group('res', 'tbr')
+                    formats.append({
+                        'url': direct_url,
+                        'format_id': 'direct',
+                        'quality': 1,
+                        'tbr': int_or_none(bitrate),
+                        **parse_resolution(resolution),
+                    })
+                for sub_data in traverse_obj(video_data, (
+                        'closedCaptions', 'types', lambda _, v: url_or_none(v['track']['url']), 'track')):
+                    subtitles.setdefault(sub_data.get('lang') or 'en', []).append({
+                        'url': sub_data['url'],
+                        'name': sub_data.get('label'),
+                    })
+
+            if app_id:
+                media_data = self._download_json(
+                    f'https://medium.ngtv.io/v2/media/{media_id}/desktop', media_id, fatal=False,
+                    query={'appId': app_id})
+                m3u8_url = traverse_obj(media_data, (
+                    'media', 'desktop', 'unprotected', 'unencrypted', 'url', {url_or_none}))
+                if m3u8_url:
+                    fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                        m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)
+                    formats.extend(fmts)
+                    self._merge_subtitles(subs, target=subtitles)
+
+            entries.append({
+                **traverse_obj(player_data, {
+                    'title': ('data-headline', {clean_html}),
+                    'description': ('data-description', {clean_html}),
+                    'duration': ('data-duration', {parse_duration}),
+                    'timestamp': ('data-publish-date', {parse_iso8601}),
+                    'thumbnail': (
+                        'data-poster-image-override', {json.loads}, 'big', 'uri', {url_or_none},
+                        {functools.partial(update_url, query='c=original')}),
+                    'display_id': 'data-video-slug',
+                }),
+                **traverse_obj(video_data, {
+                    'timestamp': ('dateCreated', 'uts', {int_or_none(scale=1000)}),
+                    'description': ('description', {clean_html}),
+                    'title': ('headline', {str}),
+                    'modified_timestamp': ('lastModified', 'uts', {int_or_none(scale=1000)}),
+                    'duration': ('trt', {int_or_none}),
+                }),
+                'id': media_id,
+                'formats': formats,
+                'subtitles': subtitles,
             })
 
+        if len(entries) == 1:
+            return {
+                **entries[0],
+                'display_id': display_id,
+            }
 
-class CNNBlogsIE(InfoExtractor):
-    _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
-    _TEST = {
-        'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
-        'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
-        'info_dict': {
-            'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
-            'ext': 'mp4',
-            'title': 'Criminalizing journalism?',
-            'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
-            'upload_date': '20140209',
-        },
-        'expected_warnings': ['Failed to download m3u8 information'],
-        'add_ie': ['CNN'],
-    }
-
-    def _real_extract(self, url):
-        webpage = self._download_webpage(url, url_basename(url))
-        cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
-        return self.url_result(cnn_url, CNNIE.ie_key())
-
-
-class CNNArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
-    _TEST = {
-        'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
-        'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
-        'info_dict': {
-            'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
-            'ext': 'mp4',
-            'title': 'Obama: Cyberattack not an act of war',
-            'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',
-            'upload_date': '20141221',
-        },
-        'expected_warnings': ['Failed to download m3u8 information'],
-        'add_ie': ['CNN'],
-    }
-
-    def _real_extract(self, url):
-        webpage = self._download_webpage(url, url_basename(url))
-        cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
-        return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key())
+        return self.playlist_result(entries, display_id)
 
 
 class CNNIndonesiaIE(InfoExtractor):

yt_dlp/extractor/common.py

@@ -47,6 +47,7 @@ from ..utils import (
     FormatSorter,
     GeoRestrictedError,
     GeoUtils,
+    ISO639Utils,
     LenientJSONDecoder,
     Popen,
     RegexNotFoundError,
@@ -1408,6 +1409,13 @@ class InfoExtractor:
             return None, None
 
         self.write_debug(f'Using netrc for {netrc_machine} authentication')
+
+        # compat: <=py3.10: netrc cannot parse tokens as empty strings, will return `""` instead
+        # Ref: https://github.com/yt-dlp/yt-dlp/issues/11413
+        #      https://github.com/python/cpython/commit/15409c720be0503131713e3d3abc1acd0da07378
+        if sys.version_info < (3, 11):
+            return tuple(x if x != '""' else '' for x in info[::2])
+
         return info[0], info[2]
 
     def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None):
@@ -3071,7 +3079,11 @@ class InfoExtractor:
             url_pattern = stream.attrib['Url']
             stream_timescale = int_or_none(stream.get('TimeScale')) or timescale
             stream_name = stream.get('Name')
-            stream_language = stream.get('Language', 'und')
+            # IsmFD expects ISO 639 Set 2 language codes (3-character length)
+            # See: https://github.com/yt-dlp/yt-dlp/issues/11356
+            stream_language = stream.get('Language') or 'und'
+            if len(stream_language) != 3:
+                stream_language = ISO639Utils.short2long(stream_language) or 'und'
             for track in stream.findall('QualityLevel'):
                 KNOWN_TAGS = {'255': 'AACL', '65534': 'EC-3'}
                 fourcc = track.get('FourCC') or KNOWN_TAGS.get(track.get('AudioTag'))

yt_dlp/extractor/generic.py

@@ -8,6 +8,8 @@ from .common import InfoExtractor
 from .commonprotocols import RtmpIE
 from .youtube import YoutubeIE
 from ..compat import compat_etree_fromstring
+from ..cookies import LenientSimpleCookie
+from ..networking.exceptions import HTTPError
 from ..networking.impersonate import ImpersonateTarget
 from ..utils import (
     KNOWN_EXTENSIONS,
@@ -2374,10 +2376,9 @@ class GenericIE(InfoExtractor):
         else:
             video_id = self._generic_id(url)
 
-        # Try to impersonate a web-browser by default if possible
-        # Skip impersonation if not available to omit the warning
-        impersonate = self._configuration_arg('impersonate', [''])
-        if 'false' in impersonate or not self._downloader._impersonate_target_available(ImpersonateTarget()):
+        # Do not impersonate by default; see https://github.com/yt-dlp/yt-dlp/issues/11335
+        impersonate = self._configuration_arg('impersonate', ['false'])
+        if 'false' in impersonate:
             impersonate = None
 
         # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
@@ -2388,10 +2389,29 @@ class GenericIE(InfoExtractor):
         # to accept raw bytes and being able to download only a chunk.
         # It may probably better to solve this by checking Content-Type for application/octet-stream
         # after a HEAD request, but not sure if we can rely on this.
-        full_response = self._request_webpage(url, video_id, headers=filter_dict({
-            'Accept-Encoding': 'identity',
-            'Referer': smuggled_data.get('referer'),
-        }), impersonate=impersonate)
+        try:
+            full_response = self._request_webpage(url, video_id, headers=filter_dict({
+                'Accept-Encoding': 'identity',
+                'Referer': smuggled_data.get('referer'),
+            }), impersonate=impersonate)
+        except ExtractorError as e:
+            if not (isinstance(e.cause, HTTPError) and e.cause.status == 403
+                    and e.cause.response.get_header('cf-mitigated') == 'challenge'
+                    and e.cause.response.extensions.get('impersonate') is None):
+                raise
+            cf_cookie_domain = traverse_obj(
+                LenientSimpleCookie(e.cause.response.get_header('set-cookie')),
+                ('__cf_bm', 'domain'))
+            if cf_cookie_domain:
+                self.write_debug(f'Clearing __cf_bm cookie for {cf_cookie_domain}')
+                self.cookiejar.clear(domain=cf_cookie_domain, path='/', name='__cf_bm')
+            msg = 'Got HTTP Error 403 caused by Cloudflare anti-bot challenge; '
+            if not self._downloader._impersonate_target_available(ImpersonateTarget()):
+                msg += ('see  https://github.com/yt-dlp/yt-dlp#impersonation  for '
+                        'how to install the required impersonation dependency, and ')
+            raise ExtractorError(
+                f'{msg}try again with  --extractor-args "generic:impersonate"', expected=True)
+
         new_url = full_response.url
         if new_url != extract_basic_auth(url)[0]:
             self.report_following_redirect(new_url)

yt_dlp/extractor/niconico.py

@@ -869,7 +869,7 @@ class NicovideoTagURLIE(NicovideoSearchBaseIE):
 
 
 class NiconicoUserIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)(?:/video)?/?(?:$|[#?])'
     _TEST = {
         'url': 'https://www.nicovideo.jp/user/419948',
         'info_dict': {
@@ -877,7 +877,7 @@ class NiconicoUserIE(InfoExtractor):
         },
         'playlist_mincount': 101,
     }
-    _API_URL = 'https://nvapi.nicovideo.jp/v1/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s'
+    _API_URL = 'https://nvapi.nicovideo.jp/v2/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s'
     _PAGE_SIZE = 100
 
     _API_HEADERS = {
@@ -897,12 +897,13 @@ class NiconicoUserIE(InfoExtractor):
                 total_count = int_or_none(json_parsed['data'].get('totalCount'))
             for entry in json_parsed['data']['items']:
                 count += 1
-                yield self.url_result('https://www.nicovideo.jp/watch/{}'.format(entry['id']))
+                yield self.url_result(
+                    f'https://www.nicovideo.jp/watch/{entry["essential"]["id"]}', ie=NiconicoIE)
             page_num += 1
 
     def _real_extract(self, url):
         list_id = self._match_id(url)
-        return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())
+        return self.playlist_result(self._entries(list_id), list_id)
 
 
 class NiconicoLiveIE(InfoExtractor):

yt_dlp/extractor/radioradicale.py

@@ -7,49 +7,99 @@ class RadioRadicaleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://www.radioradicale.it/scheda/471591',
+        'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
         'info_dict': {
             'id': '471591',
             'ext': 'mp4',
             'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
+            'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
             'location': 'Napoli',
+            'duration': 2852.0,
             'timestamp': 1459987200,
             'upload_date': '20160407',
-            'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
             'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
         },
-        'params': {
-            'skip_download': True,
+    }, {
+        'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
+        'info_dict': {
+            'id': '742783',
+            'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
+            'location': 'CAMERA',
+            'duration': 5868.0,
+            'timestamp': 1730246400,
+            'upload_date': '20241030',
         },
+        'playlist': [{
+            'md5': 'aa48de55dcc45478e4cd200f299aab7d',
+            'info_dict': {
+                'id': '742783-0',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'be915c189c70ad2920e5810f32260ff5',
+            'info_dict': {
+                'id': '742783-1',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }, {
+            'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
+            'info_dict': {
+                'id': '742783-2',
+                'ext': 'mp4',
+                'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
+            },
+        }],
     }]
 
+    def _entries(self, videos_info, page_id):
+        for idx, video in enumerate(traverse_obj(
+                videos_info, ('playlist', lambda _, v: v['sources']))):
+            video_id = f'{page_id}-{idx}'
+            formats = []
+            subtitles = {}
+
+            for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
+                self._merge_subtitles({sub.get('srclang') or 'und': [{
+                    'url': sub['src'],
+                    'name': sub.get('label'),
+                }]}, target=subtitles)
+
+            yield {
+                'id': video_id,
+                'title': video.get('title'),
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
 
-        video_info = self._search_json(
+        videos_info = self._search_json(
             r'jQuery\.extend\(Drupal\.settings\s*,',
-            webpage, 'video_info', video_id)['RRscheda']
-        json_ld = self._search_json_ld(webpage, video_id)
+            webpage, 'videos_info', page_id)['RRscheda']
 
-        formats = []
-        for source in traverse_obj(video_info, ('playlist', 0, 'sources')):
-            formats.extend(
-                self._extract_m3u8_formats(source.get('src'), video_id))
+        entries = list(self._entries(videos_info, page_id))
 
-        subtitles = {}
-        for sub in traverse_obj(video_info, ('playlist', 0, 'subtitles')):
-            self._merge_subtitles({sub.get('srclang') or 'und': [{
-                'url': sub.get('src'),
-                'name': sub.get('label'),
-            }]}, target=subtitles)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-            'title': json_ld.get('title') or self._og_search_title(webpage),
-            'location': video_info.get('luogo'),
-            'timestamp': json_ld.get('timestamp'),
-            'thumbnail': traverse_obj(json_ld, ('thumbnails', 0, 'url', {url_or_none})),
-            'description': json_ld.get('description') or self._og_search_description(webpage),
+        common_info = {
+            'id': page_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'location': videos_info.get('luogo'),
+            **self._search_json_ld(webpage, page_id),
         }
+
+        if len(entries) == 1:
+            return {
+                **entries[0],
+                **common_info,
+            }
+
+        return self.playlist_result(entries, multi_video=True, **common_info)

yt_dlp/extractor/soundcloud.py

@@ -208,7 +208,6 @@ class SoundcloudBaseIE(InfoExtractor):
 
     def _extract_info_dict(self, info, full_title=None, secret_token=None, extract_flat=False):
         track_id = str(info['id'])
-        title = info['title']
 
         format_urls = set()
         formats = []
@@ -367,7 +366,7 @@ class SoundcloudBaseIE(InfoExtractor):
             'uploader_id': str_or_none(user.get('id')) or user.get('permalink'),
             'uploader_url': user.get('permalink_url'),
             'timestamp': unified_timestamp(info.get('created_at')),
-            'title': title,
+            'title': info.get('title'),
             'description': info.get('description'),
             'thumbnails': thumbnails,
             'duration': float_or_none(info.get('duration'), 1000),
@@ -377,7 +376,8 @@ class SoundcloudBaseIE(InfoExtractor):
             'like_count': extract_count('favoritings') or extract_count('likes'),
             'comment_count': extract_count('comment'),
             'repost_count': extract_count('reposts'),
-            'genres': traverse_obj(info, ('genre', {str}, {lambda x: x or None}, all)),
+            'genres': traverse_obj(info, ('genre', {str}, filter, all, filter)),
+            'artists': traverse_obj(info, ('publisher_metadata', 'artist', {str}, filter, all, filter)),
             'formats': formats if not extract_flat else None,
         }
 
@@ -429,7 +429,6 @@ class SoundcloudIE(SoundcloudBaseIE):
                 'repost_count': int,
                 'thumbnail': 'https://i1.sndcdn.com/artworks-000031955188-rwb18x-original.jpg',
                 'uploader_url': 'https://soundcloud.com/ethmusic',
-                'genres': [],
             },
         },
         # geo-restricted
@@ -453,6 +452,7 @@ class SoundcloudIE(SoundcloudBaseIE):
                 'uploader_url': 'https://soundcloud.com/the-concept-band',
                 'thumbnail': 'https://i1.sndcdn.com/artworks-v8bFHhXm7Au6-0-original.jpg',
                 'genres': ['Alternative'],
+                'artists': ['The Royal Concept'],
             },
         },
         # private link
@@ -525,6 +525,7 @@ class SoundcloudIE(SoundcloudBaseIE):
                 'repost_count': int,
                 'view_count': int,
                 'genres': ['Dance & EDM'],
+                'artists': ['80M'],
             },
         },
         # private link, downloadable format
@@ -549,6 +550,7 @@ class SoundcloudIE(SoundcloudBaseIE):
                 'thumbnail': 'https://i1.sndcdn.com/artworks-000240712245-kedn4p-original.jpg',
                 'uploader_url': 'https://soundcloud.com/oriuplift',
                 'genres': ['Trance'],
+                'artists': ['Ori Uplift'],
             },
         },
         # no album art, use avatar pic for thumbnail
@@ -572,7 +574,7 @@ class SoundcloudIE(SoundcloudBaseIE):
                 'comment_count': int,
                 'repost_count': int,
                 'uploader_url': 'https://soundcloud.com/garyvee',
-                'genres': [],
+                'artists': ['MadReal'],
             },
             'params': {
                 'skip_download': True,

yt_dlp/extractor/twitter.py

@@ -150,14 +150,6 @@ class TwitterBaseIE(InfoExtractor):
     def is_logged_in(self):
         return bool(self._get_cookies(self._API_BASE).get('auth_token'))
 
-    # XXX: Temporary workaround until twitter.com => x.com migration is completed
-    def _real_initialize(self):
-        if self.is_logged_in or not self._get_cookies('https://twitter.com/').get('auth_token'):
-            return
-        # User has not yet been migrated to x.com and has passed twitter.com cookies
-        TwitterBaseIE._API_BASE = 'https://api.twitter.com/1.1/'
-        TwitterBaseIE._GRAPHQL_API_BASE = 'https://twitter.com/i/api/graphql/'
-
     @functools.cached_property
     def _selected_api(self):
         return self._configuration_arg('api', ['graphql'], ie_key='Twitter')[0]

yt_dlp/extractor/vimeo.py

@@ -869,11 +869,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
         for retry in (False, True):
             try:
                 video = self._call_videos_api(video_id, viewer['jwt'], unlisted_hash)
+                break
             except ExtractorError as e:
                 if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
                     and 'password' in traverse_obj(
-                        e.cause.response.read(),
-                        ({bytes.decode}, {json.loads}, 'invalid_parameters', ..., 'field'),
+                        self._webpage_read_content(e.cause.response, e.cause.response.url, video_id, fatal=False),
+                        ({json.loads}, 'invalid_parameters', ..., 'field'),
                 )):
                     self._verify_video_password(
                         video_id, self._get_video_password(), viewer['xsrft'])

yt_dlp/extractor/yle_areena.py

@@ -1,12 +1,13 @@
 from .common import InfoExtractor
 from .kaltura import KalturaIE
 from ..utils import (
+    ExtractorError,
     int_or_none,
+    parse_iso8601,
     smuggle_url,
-    traverse_obj,
-    unified_strdate,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class YleAreenaIE(InfoExtractor):
@@ -15,9 +16,9 @@ class YleAreenaIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'https://areena.yle.fi/1-4371942',
-            'md5': '932edda0ecf5dfd6423804182d32f8ac',
+            'md5': 'd87e9a1e74e67e009990ddd413e426b4',
             'info_dict': {
-                'id': '0_a3tjk92c',
+                'id': '1-4371942',
                 'ext': 'mp4',
                 'title': 'Pouchit',
                 'description': 'md5:01071d7056ceec375f63960f90c35366',
@@ -26,37 +27,27 @@ class YleAreenaIE(InfoExtractor):
                 'season_number': 1,
                 'episode': 'Episode 2',
                 'episode_number': 2,
-                'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/0_a3tjk92c/version/100061',
-                'uploader_id': 'ovp@yle.fi',
-                'duration': 1435,
-                'view_count': int,
-                'upload_date': '20181204',
-                'release_date': '20190106',
-                'timestamp': 1543916210,
-                'subtitles': {'fin': [{'url': r're:^https?://', 'ext': 'srt'}]},
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
                 'age_limit': 7,
-                'webpage_url': 'https://areena.yle.fi/1-4371942',
+                'release_date': '20190105',
+                'release_timestamp': 1546725660,
+                'duration': 1435,
             },
         },
         {
             'url': 'https://areena.yle.fi/1-2158940',
-            'md5': 'cecb603661004e36af8c5188b5212b12',
+            'md5': '6369ddc5e07b5fdaeda27a495184143c',
             'info_dict': {
-                'id': '1_l38iz9ur',
+                'id': '1-2158940',
                 'ext': 'mp4',
                 'title': 'Albi haluaa vessan',
-                'description': 'md5:15236d810c837bed861fae0e88663c33',
+                'description': 'Albi haluaa vessan.',
                 'series': 'Albi Lumiukko',
-                'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/1_l38iz9ur/version/100021',
-                'uploader_id': 'ovp@yle.fi',
-                'duration': 319,
-                'view_count': int,
-                'upload_date': '20211202',
-                'release_date': '20211215',
-                'timestamp': 1638448202,
-                'subtitles': {},
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
                 'age_limit': 0,
-                'webpage_url': 'https://areena.yle.fi/1-2158940',
+                'release_date': '20211215',
+                'release_timestamp': 1639555200,
+                'duration': 319,
             },
         },
         {
@@ -67,72 +58,125 @@ class YleAreenaIE(InfoExtractor):
                 'title': 'HKO & Mälkki & Tanner',
                 'description': 'md5:b4f1b1af2c6569b33f75179a86eea156',
                 'series': 'Helsingin kaupunginorkesterin konsertteja',
-                'thumbnail': r're:^https?://.+\.jpg$',
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
                 'release_date': '20230120',
+                'release_timestamp': 1674242079,
+                'duration': 8004,
             },
             'params': {
                 'skip_download': 'm3u8',
             },
         },
+        {
+            'url': 'https://areena.yle.fi/1-72251830',
+            'info_dict': {
+                'id': '1-72251830',
+                'ext': 'mp4',
+                'title': r're:Pentulive 2024 | Pentulive \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+                'description': 'md5:1f118707d9093bf894a34fbbc865397b',
+                'series': 'Pentulive',
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
+                'live_status': 'is_live',
+                'release_date': '20241025',
+                'release_timestamp': 1729875600,
+            },
+            'params': {
+                'skip_download': 'livestream',
+            },
+        },
+        {
+            'url': 'https://areena.yle.fi/podcastit/1-71022852',
+            'info_dict': {
+                'id': '1-71022852',
+                'ext': 'mp3',
+                'title': 'Värityspäivä',
+                'description': 'md5:c3a02b0455ec71d32cbe09d32ec161e2',
+                'series': 'Murun ja Paukun ikioma kaupunki',
+                'episode': 'Episode 1',
+                'episode_number': 1,
+                'release_date': '20240607',
+                'release_timestamp': 1717736400,
+                'duration': 442,
+            },
+        },
     ]
 
     def _real_extract(self, url):
         video_id, is_podcast = self._match_valid_url(url).group('id', 'podcast')
-        info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
+        json_ld = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
         video_data = self._download_json(
             f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
             video_id, headers={
                 'origin': 'https://areena.yle.fi',
                 'referer': 'https://areena.yle.fi/',
                 'content-type': 'application/json',
-            })
+            })['data']
 
         # Example title: 'K1, J2: Pouchit | Modernit miehet'
         season_number, episode_number, episode, series = self._search_regex(
             r'K(?P<season_no>\d+),\s*J(?P<episode_no>\d+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
-            info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
+            json_ld.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
             default=(None, None, None, None))
-        description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
+        description = traverse_obj(video_data, ('ongoing_ondemand', 'description', 'fin', {str}))
 
         subtitles = {}
-        for sub in traverse_obj(video_data, ('data', 'ongoing_ondemand', 'subtitles', ...)):
-            if url_or_none(sub.get('uri')):
-                subtitles.setdefault(sub.get('language') or 'und', []).append({
-                    'url': sub['uri'],
-                    'ext': 'srt',
-                    'name': sub.get('kind'),
-                })
+        for sub in traverse_obj(video_data, ('ongoing_ondemand', 'subtitles', lambda _, v: url_or_none(v['uri']))):
+            subtitles.setdefault(sub.get('language') or 'und', []).append({
+                'url': sub['uri'],
+                'ext': 'srt',
+                'name': sub.get('kind'),
+            })
 
-        if is_podcast:
-            info_dict = {
-                'url': video_data['data']['ongoing_ondemand']['media_url'],
-            }
-        elif kaltura_id := traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id', {str})):
-            info_dict = {
+        info_dict, metadata = {}, {}
+        if is_podcast and traverse_obj(video_data, ('ongoing_ondemand', 'media_url', {url_or_none})):
+            metadata = video_data['ongoing_ondemand']
+            info_dict['url'] = metadata['media_url']
+        elif traverse_obj(video_data, ('ongoing_event', 'manifest_url', {url_or_none})):
+            metadata = video_data['ongoing_event']
+            metadata.pop('duration', None)  # Duration is not accurate for livestreams
+            info_dict['live_status'] = 'is_live'
+        elif traverse_obj(video_data, ('ongoing_ondemand', 'manifest_url', {url_or_none})):
+            metadata = video_data['ongoing_ondemand']
+        # XXX: Has all externally-hosted Kaltura content been moved to native hosting?
+        elif kaltura_id := traverse_obj(video_data, ('ongoing_ondemand', 'kaltura', 'id', {str})):
+            metadata = video_data['ongoing_ondemand']
+            info_dict.update({
                 '_type': 'url_transparent',
                 'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}),
                 'ie_key': KalturaIE.ie_key(),
-            }
+            })
+        elif traverse_obj(video_data, ('gone', {dict})):
+            self.raise_no_formats('The content is no longer available', expected=True, video_id=video_id)
+            metadata = video_data['gone']
         else:
-            formats, subs = self._extract_m3u8_formats_and_subtitles(
-                video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls')
+            raise ExtractorError('Unable to extract content')
+
+        if not info_dict.get('url') and metadata.get('manifest_url'):
+            info_dict['formats'], subs = self._extract_m3u8_formats_and_subtitles(
+                metadata['manifest_url'], video_id, 'mp4', m3u8_id='hls')
             self._merge_subtitles(subs, target=subtitles)
-            info_dict = {'formats': formats}
 
         return {
-            **info_dict,
+            **traverse_obj(json_ld, {
+                'title': 'title',
+                'thumbnails': ('thumbnails', ..., {'url': 'url'}),
+            }),
             'id': video_id,
-            'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str)
-                      or episode or info.get('title')),
+            'title': episode,
             'description': description,
-            'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
-                       or series),
+            'series': series,
             'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
                               or int_or_none(season_number)),
-            'episode_number': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'episode_number'), expected_type=int_or_none)
-                               or int_or_none(episode_number)),
-            'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
-            'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
+            'episode_number': int_or_none(episode_number),
             'subtitles': subtitles or None,
-            'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
+            **traverse_obj(metadata, {
+                'title': ('title', 'fin', {str}),
+                'description': ('description', 'fin', {str}),
+                'series': ('series', 'title', 'fin', {str}),
+                'episode_number': ('episode_number', {int_or_none}),
+                'age_limit': ('content_rating', 'age_restriction', {int_or_none}),
+                'release_timestamp': ('start_time', {parse_iso8601}),
+                'duration': ('duration', 'duration_in_seconds', {int_or_none}),
+            }),
+            **info_dict,
         }

yt_dlp/extractor/youtube.py

@@ -644,13 +644,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE] = {}
 
         if refresh_token:
-            refresh_token = refresh_token.strip('\'') or None
-
-        # Allow refresh token passed to initialize cache
-        if refresh_token:
+            msg = f'{self._OAUTH_DISPLAY_ID}: Using password input as refresh token'
+            if self.get_param('cachedir') is not False:
+                msg += ' and caching token to disk; you should supply an empty password next time'
+            self.to_screen(msg)
             self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, refresh_token)
+        else:
+            refresh_token = self.cache.load(self._NETRC_MACHINE, self._oauth_cache_key)
 
-        refresh_token = refresh_token or self.cache.load(self._NETRC_MACHINE, self._oauth_cache_key)
         if refresh_token:
             YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE]['refresh_token'] = refresh_token
             try:

yt_dlp/utils/_utils.py

@@ -212,6 +212,23 @@ def write_json_file(obj, fn):
         raise
 
 
+def partial_application(func):
+    sig = inspect.signature(func)
+    required_args = [
+        param.name for param in sig.parameters.values()
+        if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL)
+        if param.default is inspect.Parameter.empty
+    ]
+
+    @functools.wraps(func)
+    def wrapped(*args, **kwargs):
+        if set(required_args[len(args):]).difference(kwargs):
+            return functools.partial(func, *args, **kwargs)
+        return func(*args, **kwargs)
+
+    return wrapped
+
+
 def find_xpath_attr(node, xpath, key, val=None):
     """ Find the xpath xpath[@key=val] """
     assert re.match(r'^[a-zA-Z_-]+$', key)
@@ -1192,6 +1209,7 @@ def extract_timezone(date_str, default=None):
     return timezone, date_str
 
 
+@partial_application
 def parse_iso8601(date_str, delimiter='T', timezone=None):
     """ Return a UNIX timestamp from the given date """
 
@@ -1269,6 +1287,7 @@ def unified_timestamp(date_str, day_first=True):
         return calendar.timegm(timetuple) + pm_delta * 3600 - timezone.total_seconds()
 
 
+@partial_application
 def determine_ext(url, default_ext='unknown_video'):
     if url is None or '.' not in url:
         return default_ext
@@ -1944,7 +1963,7 @@ def remove_start(s, start):
 
 
 def remove_end(s, end):
-    return s[:-len(end)] if s is not None and s.endswith(end) else s
+    return s[:-len(end)] if s is not None and end and s.endswith(end) else s
 
 
 def remove_quotes(s):
@@ -1973,6 +1992,7 @@ def base_url(url):
     return re.match(r'https?://[^?#]+/', url).group()
 
 
+@partial_application
 def urljoin(base, path):
     if isinstance(path, bytes):
         path = path.decode()
@@ -1988,21 +2008,6 @@ def urljoin(base, path):
     return urllib.parse.urljoin(base, path)
 
 
-def partial_application(func):
-    sig = inspect.signature(func)
-
-    @functools.wraps(func)
-    def wrapped(*args, **kwargs):
-        try:
-            sig.bind(*args, **kwargs)
-        except TypeError:
-            return functools.partial(func, *args, **kwargs)
-        else:
-            return func(*args, **kwargs)
-
-    return wrapped
-
-
 @partial_application
 def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1, base=None):
     if get_attr and v is not None:
@@ -2583,6 +2588,7 @@ def urlencode_postdata(*args, **kargs):
     return urllib.parse.urlencode(*args, **kargs).encode('ascii')
 
 
+@partial_application
 def update_url(url, *, query_update=None, **kwargs):
     """Replace URL components specified by kwargs
        @param url           str or parse url tuple
@@ -2603,6 +2609,7 @@ def update_url(url, *, query_update=None, **kwargs):
     return urllib.parse.urlunparse(url._replace(**kwargs))
 
 
+@partial_application
 def update_url_query(url, query):
     return update_url(url, query_update=query)
 
@@ -2924,6 +2931,7 @@ def error_to_str(err):
     return f'{type(err).__name__}: {err}'
 
 
+@partial_application
 def mimetype2ext(mt, default=NO_DEFAULT):
     if not isinstance(mt, str):
         if default is not NO_DEFAULT:
@@ -4664,6 +4672,7 @@ def to_high_limit_path(path):
     return path
 
 
+@partial_application
 def format_field(obj, field=None, template='%s', ignore=NO_DEFAULT, default='', func=IDENTITY):
     val = traversal.traverse_obj(obj, *variadic(field))
     if not val if ignore is NO_DEFAULT else val in variadic(ignore):
@@ -4828,6 +4837,7 @@ def number_of_digits(number):
     return len('%d' % number)
 
 
+@partial_application
 def join_nonempty(*values, delim='-', from_dict=None):
     if from_dict is not None:
         values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values)
@@ -5165,6 +5175,7 @@ class _UnsafeExtensionError(Exception):
         'ico',
         'image',
         'jng',
+        'jpe',
         'jpeg',
         'jxl',
         'svg',
@@ -5277,6 +5288,7 @@ class RetryManager:
             time.sleep(delay)
 
 
+@partial_application
 def make_archive_id(ie, video_id):
     ie_key = ie if isinstance(ie, str) else ie.ie_key()
     return f'{ie_key.lower()} {video_id}'
@@ -5578,14 +5590,15 @@ class FormatSorter:
             value = get_value(field)
         return self._calculate_field_preference_from_value(format_, field, type_, value)
 
-    def calculate_preference(self, format):
+    @staticmethod
+    def _fill_sorting_fields(format):
         # Determine missing protocol
         if not format.get('protocol'):
             format['protocol'] = determine_protocol(format)
 
         # Determine missing ext
         if not format.get('ext') and 'url' in format:
-            format['ext'] = determine_ext(format['url'])
+            format['ext'] = determine_ext(format['url']).lower()
         if format.get('vcodec') == 'none':
             format['audio_ext'] = format['ext'] if format.get('acodec') != 'none' else 'none'
             format['video_ext'] = 'none'
@@ -5613,6 +5626,8 @@ class FormatSorter:
         if not format.get('tbr'):
             format['tbr'] = try_call(lambda: format['vbr'] + format['abr']) or None
 
+    def calculate_preference(self, format):
+        self._fill_sorting_fields(format)
         return tuple(self._calculate_field_preference(format, field) for field in self._order)
 
 

yt_dlp/utils/traversal.py

@@ -391,14 +391,13 @@ def find_element(*, tag: str, html=False): ...
 def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=False):
     # deliberately using `id=` and `cls=` for ease of readability
     assert tag or id or cls or (attr and value), 'One of tag, id, cls or (attr AND value) is required'
-    if not tag:
-        tag = r'[\w:.-]+'
+    ANY_TAG = r'[\w:.-]+'
 
     if attr and value:
         assert not cls, 'Cannot match both attr and cls'
         assert not id, 'Cannot match both attr and id'
         func = get_element_html_by_attribute if html else get_element_by_attribute
-        return functools.partial(func, attr, value, tag=tag)
+        return functools.partial(func, attr, value, tag=tag or ANY_TAG)
 
     elif cls:
         assert not id, 'Cannot match both cls and id'
@@ -408,7 +407,7 @@ def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=Fal
 
     elif id:
         func = get_element_html_by_id if html else get_element_by_id
-        return functools.partial(func, id, tag=tag)
+        return functools.partial(func, id, tag=tag or ANY_TAG)
 
     index = int(bool(html))
     return lambda html: get_element_text_and_html_by_tag(tag, html)[index]
@@ -436,6 +435,20 @@ def find_elements(*, tag=None, cls=None, attr=None, value=None, html=False):
     return functools.partial(func, cls)
 
 
+def trim_str(*, start=None, end=None):
+    def trim(s):
+        if s is None:
+            return None
+        start_idx = 0
+        if start and s.startswith(start):
+            start_idx = len(start)
+        if end and s.endswith(end):
+            return s[start_idx:-len(end)]
+        return s[start_idx:]
+
+    return trim
+
+
 def get_first(obj, *paths, **kwargs):
     return traverse_obj(obj, *((..., *variadic(keys)) for keys in paths), **kwargs, get_all=False)