fix url matching & test placement

Authored by: bashonly

.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

@@ -1553,9 +1553,9 @@ The available fields are:
 
 All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. E.g. `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred value for the fields, separated by a `:`. E.g. `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two preferred values, the first for video and the second for audio. E.g. `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. E.g. `filesize~1G` prefers the format with filesize closest to 1 GiB.
 
-The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behavior can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
+The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behavior can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
 
-Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. Dolby Vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.
+Note that the default for hdr is `hdr:12`; i.e. Dolby Vision is not preferred. This choice was made since DV formats are not yet fully compatible with most devices. This may be changed in the future.
 
 If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all respects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`.
 
@@ -2205,7 +2205,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * `avconv` is not supported as an alternative to `ffmpeg`
 * yt-dlp stores config files in slightly different locations to youtube-dl. See [CONFIGURATION](#configuration) for a list of correct locations
 * The default [output template](#output-template) is `%(title)s [%(id)s].%(ext)s`. There is no real reason for this change. This was changed before yt-dlp was ever made public and now there are no plans to change it back to `%(title)s-%(id)s.%(ext)s`. Instead, you may use `--compat-options filename`
-* The default [format sorting](#sorting-formats) is different from youtube-dl and prefers higher resolution and better codecs rather than higher bitrates. You can use the `--format-sort` option to change this to any order you prefer, or use `--compat-options format-sort` to use youtube-dl's sorting order
+* The default [format sorting](#sorting-formats) is different from youtube-dl and prefers higher resolution and better codecs rather than higher bitrates. You can use the `--format-sort` option to change this to any order you prefer, or use `--compat-options format-sort` to use youtube-dl's sorting order. Older versions of yt-dlp preferred VP9 due to its broader compatibility; you can use `--compat-options prefer-vp9-sort` to revert to that format sorting preference. These two compat options cannot be used together
 * The default format selector is `bv*+ba/b`. This means that if a combined video + audio format that is better than the best video-only format is found, the former will be preferred. Use `-f bv+ba/b` or `--compat-options format-spec` to revert this
 * Unlike youtube-dlc, yt-dlp does not allow merging multiple audio/video streams into one file by default (since this conflicts with the use of `-f bv*+ba`). If needed, this feature must be enabled using `--audio-multistreams` and `--video-multistreams`. You can also use `--compat-options multistreams` to enable both
 * `--no-abort-on-error` is enabled by default. Use `--abort-on-error` or `--compat-options abort-on-error` to abort on errors instead
@@ -2234,11 +2234,11 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 For ease of use, a few more compat options are available:
 
 * `--compat-options all`: Use all compat options (**Do NOT use this!**)
-* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
+* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort`
-* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
+* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort`
 * `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization,no-youtube-prefer-utc-upload-date`
 * `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
-* `--compat-options 2023`: Currently does nothing. Use this to enable all future compat options
+* `--compat-options 2023`: Same as `--compat-options prefer-vp9-sort`. Use this to enable all future compat options
 
 The following compat options restore vulnerable behavior from before security patches:
 

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 result := cls.group_lookup().get(group):
-        if not result:
+            return result, subgroup or None
-            if subgroup:
-                return None, value
-            subgroup = group
-            result = cls.subgroup_lookup().get(subgroup)
 
-        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 := groups[item]:
-            if group:
                 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 := self.AUTHOR_INDICATOR_RE.match(line):
-                if match:
                     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 match := self.REVERT_RE.fullmatch(commit.short):
-            if revert_match:
+                reverts[match.group(1)] = commit
-                reverts[revert_match.group(1)] = commit
                 continue
 
-            fix_match = self.FIXES_RE.search(commit.short)
+            if fix_commitish:
-            if fix_match:
+                fixes[fix_commitish].append(commit)
-                commitish = fix_match.group(1)
-                fixes[commitish].append(commit)
 
             commits[commit.hash] = commit
 
         for commitish, revert_commit in reverts.items():
-            reverted = commits.pop(commitish, None)
+            if reverted := commits.pop(commitish, None):
-            if reverted:
                 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 := get_new_contributors(args.contributors_path, commits):
-    if new_contributors:
         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_aes.py

@@ -83,6 +83,18 @@ class TestAES(unittest.TestCase):
                 data, intlist_to_bytes(self.key), authentication_tag, intlist_to_bytes(self.iv[:12]))
             self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
 
+    def test_gcm_aligned_decrypt(self):
+        data = b'\x159Y\xcf5eud\x90\x9c\x85&]\x14\x1d\x0f'
+        authentication_tag = b'\x08\xb1\x9d!&\x98\xd0\xeaRq\x90\xe6;\xb5]\xd8'
+
+        decrypted = intlist_to_bytes(aes_gcm_decrypt_and_verify(
+            list(data), self.key, list(authentication_tag), self.iv[:12]))
+        self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg[:16])
+        if Cryptodome.AES:
+            decrypted = aes_gcm_decrypt_and_verify_bytes(
+                data, bytes(self.key), authentication_tag, bytes(self.iv[:12]))
+            self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg[:16])
+
     def test_decrypt_text(self):
         password = intlist_to_bytes(self.key).decode()
         encrypted = base64.b64encode(

test/test_traversal.py

@@ -9,12 +9,17 @@ from yt_dlp.utils import (
     determine_ext,
     dict_get,
     int_or_none,
+    join_nonempty,
     str_or_none,
 )
 from yt_dlp.utils.traversal import (
-    traverse_obj,
+    find_element,
+    find_elements,
     require,
     subs_list_to_dict,
+    traverse_obj,
+    trim_str,
+    unpack,
 )
 
 _TEST_DATA = {
@@ -34,6 +39,14 @@ _TEST_DATA = {
     'dict': {},
 }
 
+_TEST_HTML = '''<html><body>
+    <div class="a">1</div>
+    <div class="a" id="x" custom="z">2</div>
+    <div class="b" data-id="y" custom="z">3</div>
+    <p class="a">4</p>
+    <p id="d" custom="e">5</p>
+</body></html>'''
+
 
 class TestTraversal:
     def test_traversal_base(self):
@@ -495,6 +508,73 @@ 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'
+
+    def test_unpack(self):
+        assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
+        assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
+        assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3'
+        with pytest.raises(TypeError):
+            unpack(join_nonempty)()
+        with pytest.raises(TypeError):
+            unpack()
+
+    def test_find_element(self):
+        for improper_kwargs in [
+            dict(attr='data-id'),
+            dict(value='y'),
+            dict(attr='data-id', value='y', cls='a'),
+            dict(attr='data-id', value='y', id='x'),
+            dict(cls='a', id='x'),
+            dict(cls='a', tag='p'),
+            dict(cls='[ab]', regex=True),
+        ]:
+            with pytest.raises(AssertionError):
+                find_element(**improper_kwargs)(_TEST_HTML)
+
+        assert find_element(cls='a')(_TEST_HTML) == '1'
+        assert find_element(cls='a', html=True)(_TEST_HTML) == '<div class="a">1</div>'
+        assert find_element(id='x')(_TEST_HTML) == '2'
+        assert find_element(id='[ex]')(_TEST_HTML) is None
+        assert find_element(id='[ex]', regex=True)(_TEST_HTML) == '2'
+        assert find_element(id='x', html=True)(_TEST_HTML) == '<div class="a" id="x" custom="z">2</div>'
+        assert find_element(attr='data-id', value='y')(_TEST_HTML) == '3'
+        assert find_element(attr='data-id', value='y(?:es)?')(_TEST_HTML) is None
+        assert find_element(attr='data-id', value='y(?:es)?', regex=True)(_TEST_HTML) == '3'
+        assert find_element(
+            attr='data-id', value='y', html=True)(_TEST_HTML) == '<div class="b" data-id="y" custom="z">3</div>'
+
+    def test_find_elements(self):
+        for improper_kwargs in [
+            dict(tag='p'),
+            dict(attr='data-id'),
+            dict(value='y'),
+            dict(attr='data-id', value='y', cls='a'),
+            dict(cls='a', tag='div'),
+            dict(cls='[ab]', regex=True),
+        ]:
+            with pytest.raises(AssertionError):
+                find_elements(**improper_kwargs)(_TEST_HTML)
+
+        assert find_elements(cls='a')(_TEST_HTML) == ['1', '2', '4']
+        assert find_elements(cls='a', html=True)(_TEST_HTML) == [
+            '<div class="a">1</div>', '<div class="a" id="x" custom="z">2</div>', '<p class="a">4</p>']
+        assert find_elements(attr='custom', value='z')(_TEST_HTML) == ['2', '3']
+        assert find_elements(attr='custom', value='[ez]')(_TEST_HTML) == []
+        assert find_elements(attr='custom', value='[ez]', regex=True)(_TEST_HTML) == ['2', '3', '5']
+
 
 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

@@ -470,7 +470,7 @@ class YoutubeDL:
                        The following options do not work when used through the API:
                        filename, abort-on-error, multistreams, no-live-chat,
                        format-sort, no-clean-infojson, no-playlist-metafiles,
-                       no-keep-subs, no-attach-info-json, allow-unsafe-ext.
+                       no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort.
                        Refer __init__.py for their implementation
     progress_template: Dictionary of templates for progress outputs.
                        Allowed keys are 'download', 'postprocess',

yt_dlp/__init__.py

@@ -159,6 +159,9 @@ def set_compat_opts(opts):
             opts.embed_infojson = False
     if 'format-sort' in opts.compat_opts:
         opts.format_sort.extend(FormatSorter.ytdl_default)
+    elif 'prefer-vp9-sort' in opts.compat_opts:
+        opts.format_sort.extend(FormatSorter._prefer_vp9_sort)
+
     _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
     _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
     if _video_multistreams_set is False and _audio_multistreams_set is False:

yt_dlp/aes.py

@@ -230,11 +230,11 @@ def aes_gcm_decrypt_and_verify(data, key, tag, nonce):
     iv_ctr = inc(j0)
 
     decrypted_data = aes_ctr_decrypt(data, key, iv_ctr + [0] * (BLOCK_SIZE_BYTES - len(iv_ctr)))
-    pad_len = len(data) // 16 * 16
+    pad_len = (BLOCK_SIZE_BYTES - (len(data) % BLOCK_SIZE_BYTES)) % BLOCK_SIZE_BYTES
     s_tag = ghash(
         hash_subkey,
         data
-        + [0] * (BLOCK_SIZE_BYTES - len(data) + pad_len)        # pad
+        + [0] * pad_len                                         # pad
         + bytes_to_intlist((0 * 8).to_bytes(8, 'big')           # length of associated data
                            + ((len(data) * 8).to_bytes(8, 'big'))),  # length of data
     )

yt_dlp/extractor/_extractors.py

@@ -278,6 +278,7 @@ from .bleacherreport import (
 from .blerp import BlerpIE
 from .blogger import BloggerIE
 from .bloomberg import BloombergIE
+from .bluesky import BlueskyIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE
 from .boosty import BoostyIE

yt_dlp/extractor/bfmtv.py

@@ -1,18 +1,33 @@
 import re
 
 from .common import InfoExtractor
-from ..utils import extract_attributes
+from ..utils import ExtractorError, extract_attributes
 
 
 class BFMTVBaseIE(InfoExtractor):
     _VALID_URL_BASE = r'https?://(?:www\.|rmc\.)?bfmtv\.com/'
     _VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
-    _VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>)'
+    _VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>.*?</div>)'
+    _VIDEO_ELEMENT_REGEX = r'(<video-js[^>]+>)'
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
 
-    def _brightcove_url_result(self, video_id, video_block):
+    def _extract_video(self, video_block):
-        account_id = video_block.get('accountid') or '876450612001'
+        video_element = self._search_regex(
-        player_id = video_block.get('playerid') or 'I2qBTln4u'
+            self._VIDEO_ELEMENT_REGEX, video_block, 'video element', default=None)
+        if video_element:
+            video_element_attrs = extract_attributes(video_element)
+            video_id = video_element_attrs.get('data-video-id')
+            if not video_id:
+                return
+            account_id = video_element_attrs.get('data-account') or '876450610001'
+            player_id = video_element_attrs.get('adjustplayer') or '19dszYXgm'
+        else:
+            video_block_attrs = extract_attributes(video_block)
+            video_id = video_block_attrs.get('videoid')
+            if not video_id:
+                return
+            account_id = video_block_attrs.get('accountid') or '876630703001'
+            player_id = video_block_attrs.get('playerid') or 'KbPwEbuHx'
         return self.url_result(
             self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
             'BrightcoveNew', video_id)
@@ -40,23 +55,25 @@ class BFMTVIE(BFMTVBaseIE):
     def _real_extract(self, url):
         bfmtv_id = self._match_id(url)
         webpage = self._download_webpage(url, bfmtv_id)
-        video_block = extract_attributes(self._search_regex(
+        video = self._extract_video(self._search_regex(
             self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
-        return self._brightcove_url_result(video_block['videoid'], video_block)
+        if not video:
+            raise ExtractorError('Failed to extract video')
+        return video
 
 
-class BFMTVLiveIE(BFMTVIE):  # XXX: Do not subclass from concrete IE
+class BFMTVLiveIE(BFMTVBaseIE):
     IE_NAME = 'bfmtv:live'
     _VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
     _TESTS = [{
         'url': 'https://www.bfmtv.com/en-direct/',
         'info_dict': {
-            'id': '5615950982001',
+            'id': '6346069778112',
             'ext': 'mp4',
-            'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'title': r're:^Le Live BFM TV \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
             'uploader_id': '876450610001',
-            'upload_date': '20220926',
+            'upload_date': '20240202',
-            'timestamp': 1664207191,
+            'timestamp': 1706887572,
             'live_status': 'is_live',
             'thumbnail': r're:https://.+/image\.jpg',
             'tags': [],
@@ -69,6 +86,15 @@ class BFMTVLiveIE(BFMTVIE):  # XXX: Do not subclass from concrete IE
         'only_matching': True,
     }]
 
+    def _real_extract(self, url):
+        bfmtv_id = self._match_id(url)
+        webpage = self._download_webpage(url, bfmtv_id)
+        video = self._extract_video(self._search_regex(
+            self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
+        if not video:
+            raise ExtractorError('Failed to extract video')
+        return video
+
 
 class BFMTVArticleIE(BFMTVBaseIE):
     IE_NAME = 'bfmtv:article'
@@ -102,18 +128,16 @@ class BFMTVArticleIE(BFMTVBaseIE):
         },
     }]
 
+    def _entries(self, webpage):
+        for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
+            video = self._extract_video(video_block_el)
+            if video:
+                yield video
+
     def _real_extract(self, url):
         bfmtv_id = self._match_id(url)
         webpage = self._download_webpage(url, bfmtv_id)
 
-        entries = []
-        for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
-            video_block = extract_attributes(video_block_el)
-            video_id = video_block.get('videoid')
-            if not video_id:
-                continue
-            entries.append(self._brightcove_url_result(video_id, video_block))
-
         return self.playlist_result(
-            entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
+            self._entries(webpage), bfmtv_id, self._og_search_title(webpage, fatal=False),
             self._html_search_meta(['og:description', 'description'], webpage))

yt_dlp/extractor/bluesky.py

@@ -0,0 +1,388 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    format_field,
+    int_or_none,
+    mimetype2ext,
+    orderedSet,
+    parse_iso8601,
+    truncate_string,
+    update_url_query,
+    url_basename,
+    url_or_none,
+    variadic,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BlueskyIE(InfoExtractor):
+    _VALID_URL = [
+        r'https?://(?:www\.)?(?:bsky\.app|main\.bsky\.dev)/profile/(?P<handle>[\w.:%-]+)/post/(?P<id>\w+)',
+        r'at://(?P<handle>[\w.:%-]+)/app\.bsky\.feed\.post/(?P<id>\w+)',
+    ]
+    _TESTS = [{
+        'url': 'https://bsky.app/profile/blu3blue.bsky.social/post/3l4omssdl632g',
+        'md5': '375539c1930ab05d15585ed772ab54fd',
+        'info_dict': {
+            'id': '3l4omssdl632g',
+            'ext': 'mp4',
+            'uploader': 'Blu3Blu3Lilith',
+            'uploader_id': 'blu3blue.bsky.social',
+            'uploader_url': 'https://bsky.app/profile/blu3blue.bsky.social',
+            'channel_id': 'did:plc:pzdr5ylumf7vmvwasrpr5bf2',
+            'channel_url': 'https://bsky.app/profile/did:plc:pzdr5ylumf7vmvwasrpr5bf2',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'OMG WE HAVE VIDEOS NOW',
+            'description': 'OMG WE HAVE VIDEOS NOW',
+            'upload_date': '20240921',
+            'timestamp': 1726940605,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+        },
+    }, {
+        'url': 'https://bsky.app/profile/bsky.app/post/3l3vgf77uco2g',
+        'md5': 'b9e344fdbce9f2852c668a97efefb105',
+        'info_dict': {
+            'id': '3l3vgf77uco2g',
+            'ext': 'mp4',
+            'uploader': 'Bluesky',
+            'uploader_id': 'bsky.app',
+            'uploader_url': 'https://bsky.app/profile/bsky.app',
+            'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
+            'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'Bluesky now has video! Update your app to versi...',
+            'alt_title': 'Bluesky video feature announcement',
+            'description': r're:(?s)Bluesky now has video! .{239}',
+            'upload_date': '20240911',
+            'timestamp': 1726074716,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+            'subtitles': {
+                'en': 'mincount:1',
+            },
+        },
+    }, {
+        'url': 'https://main.bsky.dev/profile/souris.moe/post/3l4qhp7bcs52c',
+        'md5': '5f2df8c200b5633eb7fb2c984d29772f',
+        'info_dict': {
+            'id': '3l4qhp7bcs52c',
+            'ext': 'mp4',
+            'uploader': 'souris',
+            'uploader_id': 'souris.moe',
+            'uploader_url': 'https://bsky.app/profile/souris.moe',
+            'channel_id': 'did:plc:tj7g244gl5v6ai6cm4f4wlqp',
+            'channel_url': 'https://bsky.app/profile/did:plc:tj7g244gl5v6ai6cm4f4wlqp',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'Bluesky video #3l4qhp7bcs52c',
+            'upload_date': '20240922',
+            'timestamp': 1727003838,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+        },
+    }, {
+        'url': 'https://bsky.app/profile/de1.pds.tentacle.expert/post/3l3w4tnezek2e',
+        'md5': '1af9c7fda061cf7593bbffca89e43d1c',
+        'info_dict': {
+            'id': '3l3w4tnezek2e',
+            'ext': 'mp4',
+            'uploader': 'clean',
+            'uploader_id': 'de1.pds.tentacle.expert',
+            'uploader_url': 'https://bsky.app/profile/de1.pds.tentacle.expert',
+            'channel_id': 'did:web:de1.tentacle.expert',
+            'channel_url': 'https://bsky.app/profile/did:web:de1.tentacle.expert',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'Bluesky video #3l3w4tnezek2e',
+            'upload_date': '20240911',
+            'timestamp': 1726098823,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+        },
+    }, {
+        'url': 'https://bsky.app/profile/yunayuispink.bsky.social/post/3l7gqcfes742o',
+        'info_dict': {
+            'id': 'XxK3t_5V3ao',
+            'ext': 'mp4',
+            'uploader': 'yunayu',
+            'uploader_id': '@yunayuispink',
+            'uploader_url': 'https://www.youtube.com/@yunayuispink',
+            'channel': 'yunayu',
+            'channel_id': 'UCPLvXnHa7lTyNoR_dGsU14w',
+            'channel_url': 'https://www.youtube.com/channel/UCPLvXnHa7lTyNoR_dGsU14w',
+            'thumbnail': 'https://i.ytimg.com/vi_webp/XxK3t_5V3ao/maxresdefault.webp',
+            'description': r're:Have a good goodx10000day',
+            'title': '5min vs 5hours drawing',
+            'availability': 'public',
+            'live_status': 'not_live',
+            'playable_in_embed': True,
+            'upload_date': '20241026',
+            'timestamp': 1729967784,
+            'duration': 321,
+            'age_limit': 0,
+            'like_count': int,
+            'view_count': int,
+            'comment_count': int,
+            'channel_follower_count': int,
+            'categories': ['Entertainment'],
+            'tags': [],
+        },
+        'add_ie': ['Youtube'],
+    }, {
+        'url': 'https://bsky.app/profile/endshark.bsky.social/post/3jzxjkcemae2m',
+        'info_dict': {
+            'id': '222792849',
+            'ext': 'mp3',
+            'uploader': 'LASERBAT',
+            'uploader_id': 'laserbatx',
+            'uploader_url': 'https://laserbatx.bandcamp.com',
+            'artists': ['LASERBAT'],
+            'album_artists': ['LASERBAT'],
+            'album': 'Hari Nezumi [EP]',
+            'track': 'Forward to the End',
+            'title': 'LASERBAT - Forward to the End',
+            'thumbnail': 'https://f4.bcbits.com/img/a2507705510_5.jpg',
+            'duration': 228.571,
+            'track_id': '222792849',
+            'release_date': '20230423',
+            'upload_date': '20230423',
+            'timestamp': 1682276040.0,
+            'release_timestamp': 1682276040.0,
+            'track_number': 1,
+        },
+        'add_ie': ['Bandcamp'],
+    }, {
+        'url': 'https://bsky.app/profile/dannybhoix.bsky.social/post/3l6oe5mtr2c2j',
+        'md5': 'b9e344fdbce9f2852c668a97efefb105',
+        'info_dict': {
+            'id': '3l3vgf77uco2g',
+            'ext': 'mp4',
+            'uploader': 'Bluesky',
+            'uploader_id': 'bsky.app',
+            'uploader_url': 'https://bsky.app/profile/bsky.app',
+            'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
+            'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'Bluesky now has video! Update your app to versi...',
+            'alt_title': 'Bluesky video feature announcement',
+            'description': r're:(?s)Bluesky now has video! .{239}',
+            'upload_date': '20240911',
+            'timestamp': 1726074716,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+            'subtitles': {
+                'en': 'mincount:1',
+            },
+        },
+    }, {
+        'url': 'https://bsky.app/profile/alt.bun.how/post/3l7rdfxhyds2f',
+        'md5': '8775118b235cf9fa6b5ad30f95cda75c',
+        'info_dict': {
+            'id': '3l7rdfxhyds2f',
+            'ext': 'mp4',
+            'uploader': 'cinnamon',
+            'uploader_id': 'alt.bun.how',
+            'uploader_url': 'https://bsky.app/profile/alt.bun.how',
+            'channel_id': 'did:plc:7x6rtuenkuvxq3zsvffp2ide',
+            'channel_url': 'https://bsky.app/profile/did:plc:7x6rtuenkuvxq3zsvffp2ide',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'crazy that i look like this tbh',
+            'description': 'crazy that i look like this tbh',
+            'upload_date': '20241030',
+            'timestamp': 1730332128,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': ['sexual'],
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'at://did:plc:ia76kvnndjutgedggx2ibrem/app.bsky.feed.post/3l6zrz6zyl2dr',
+        'md5': '71b0eb6d85d03145e6af6642c7fc6d78',
+        'info_dict': {
+            'id': '3l6zrz6zyl2dr',
+            'ext': 'mp4',
+            'uploader': 'mary🐇',
+            'uploader_id': 'mary.my.id',
+            'uploader_url': 'https://bsky.app/profile/mary.my.id',
+            'channel_id': 'did:plc:ia76kvnndjutgedggx2ibrem',
+            'channel_url': 'https://bsky.app/profile/did:plc:ia76kvnndjutgedggx2ibrem',
+            'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+            'title': 'Bluesky video #3l6zrz6zyl2dr',
+            'upload_date': '20241021',
+            'timestamp': 1729523172,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'tags': [],
+        },
+    }, {
+        'url': 'https://bsky.app/profile/purpleicetea.bsky.social/post/3l7gv55dc2o2w',
+        'info_dict': {
+            'id': '3l7gv55dc2o2w',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '3l7gv55dc2o2w',
+                'ext': 'mp4',
+                'upload_date': '20241026',
+                'description': 'One of my favorite videos',
+                'comment_count': int,
+                'uploader_url': 'https://bsky.app/profile/purpleicetea.bsky.social',
+                'uploader': 'Purple.Ice.Tea',
+                'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+                'channel_url': 'https://bsky.app/profile/did:plc:bjh5ffwya5f53dfy47dezuwx',
+                'like_count': int,
+                'channel_id': 'did:plc:bjh5ffwya5f53dfy47dezuwx',
+                'repost_count': int,
+                'timestamp': 1729973202,
+                'tags': [],
+                'uploader_id': 'purpleicetea.bsky.social',
+                'title': 'One of my favorite videos',
+            },
+        }, {
+            'info_dict': {
+                'id': '3l77u64l7le2e',
+                'ext': 'mp4',
+                'title': 'hearing people on twitter say that bluesky isn\'...',
+                'like_count': int,
+                'uploader_id': 'thafnine.net',
+                'uploader_url': 'https://bsky.app/profile/thafnine.net',
+                'upload_date': '20241024',
+                'channel_url': 'https://bsky.app/profile/did:plc:6ttyq36rhiyed7wu3ws7dmqj',
+                'description': r're:(?s)hearing people on twitter say that bluesky .{93}',
+                'tags': [],
+                'alt_title': 'md5:9b1ee1937fb3d1a81e932f9ec14d560e',
+                'uploader': 'T9',
+                'channel_id': 'did:plc:6ttyq36rhiyed7wu3ws7dmqj',
+                'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
+                'timestamp': 1729731642,
+                'comment_count': int,
+                'repost_count': int,
+            },
+        }],
+    }]
+    _BLOB_URL_TMPL = '{}/xrpc/com.atproto.sync.getBlob'
+
+    def _get_service_endpoint(self, did, video_id):
+        if did.startswith('did:web:'):
+            url = f'https://{did[8:]}/.well-known/did.json'
+        else:
+            url = f'https://plc.directory/{did}'
+        services = self._download_json(
+            url, video_id, 'Fetching service endpoint', 'Falling back to bsky.social', fatal=False)
+        return traverse_obj(
+            services, ('service', lambda _, x: x['type'] == 'AtprotoPersonalDataServer',
+                       'serviceEndpoint', {url_or_none}, any)) or 'https://bsky.social'
+
+    def _real_extract(self, url):
+        handle, video_id = self._match_valid_url(url).group('handle', 'id')
+
+        post = self._download_json(
+            'https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread',
+            video_id, query={
+                'uri': f'at://{handle}/app.bsky.feed.post/{video_id}',
+                'depth': 0,
+                'parentHeight': 0,
+            })['thread']['post']
+
+        entries = []
+        # app.bsky.embed.video.view/app.bsky.embed.external.view
+        entries.extend(self._extract_videos(post, video_id))
+        # app.bsky.embed.recordWithMedia.view
+        entries.extend(self._extract_videos(
+            post, video_id, embed_path=('embed', 'media'), record_subpath=('embed', 'media')))
+        # app.bsky.embed.record.view
+        if nested_post := traverse_obj(post, ('embed', 'record', ('record', None), {dict}, any)):
+            entries.extend(self._extract_videos(
+                nested_post, video_id, embed_path=('embeds', 0), record_path='value'))
+
+        if not entries:
+            raise ExtractorError('No video could be found in this post', expected=True)
+        if len(entries) == 1:
+            return entries[0]
+        return self.playlist_result(entries, video_id)
+
+    @staticmethod
+    def _build_profile_url(path):
+        return format_field(path, None, 'https://bsky.app/profile/%s', default=None)
+
+    def _extract_videos(self, root, video_id, embed_path='embed', record_path='record', record_subpath='embed'):
+        embed_path = variadic(embed_path, (str, bytes, dict, set))
+        record_path = variadic(record_path, (str, bytes, dict, set))
+        record_subpath = variadic(record_subpath, (str, bytes, dict, set))
+
+        entries = []
+        if external_uri := traverse_obj(root, (
+                ((*record_path, *record_subpath), embed_path), 'external', 'uri', {url_or_none}, any)):
+            entries.append(self.url_result(external_uri))
+        if playlist := traverse_obj(root, (*embed_path, 'playlist', {url_or_none})):
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                playlist, video_id, 'mp4', m3u8_id='hls', fatal=False)
+        else:
+            return entries
+
+        video_cid = traverse_obj(
+            root, (*embed_path, 'cid', {str}),
+            (*record_path, *record_subpath, 'video', 'ref', '$link', {str}))
+        did = traverse_obj(root, ('author', 'did', {str}))
+
+        if did and video_cid:
+            endpoint = self._get_service_endpoint(did, video_id)
+
+            formats.append({
+                'format_id': 'blob',
+                'url': update_url_query(
+                    self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': video_cid}),
+                **traverse_obj(root, (*embed_path, 'aspectRatio', {
+                    'width': ('width', {int_or_none}),
+                    'height': ('height', {int_or_none}),
+                })),
+                **traverse_obj(root, (*record_path, *record_subpath, 'video', {
+                    'filesize': ('size', {int_or_none}),
+                    'ext': ('mimeType', {mimetype2ext}),
+                })),
+            })
+
+            for sub_data in traverse_obj(root, (
+                    *record_path, *record_subpath, 'captions', lambda _, v: v['file']['ref']['$link'])):
+                subtitles.setdefault(sub_data.get('lang') or 'und', []).append({
+                    'url': update_url_query(
+                        self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': sub_data['file']['ref']['$link']}),
+                    'ext': traverse_obj(sub_data, ('file', 'mimeType', {mimetype2ext})),
+                })
+
+        entries.append({
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(root, {
+                'id': ('uri', {url_basename}),
+                'thumbnail': (*embed_path, 'thumbnail', {url_or_none}),
+                'alt_title': (*embed_path, 'alt', {str}, filter),
+                'uploader': ('author', 'displayName', {str}),
+                'uploader_id': ('author', 'handle', {str}),
+                'uploader_url': ('author', 'handle', {self._build_profile_url}),
+                'channel_id': ('author', 'did', {str}),
+                'channel_url': ('author', 'did', {self._build_profile_url}),
+                'like_count': ('likeCount', {int_or_none}),
+                'repost_count': ('repostCount', {int_or_none}),
+                'comment_count': ('replyCount', {int_or_none}),
+                'timestamp': ('indexedAt', {parse_iso8601}),
+                'tags': ('labels', ..., 'val', {str}, all, {orderedSet}),
+                'age_limit': (
+                    'labels', ..., 'val', {lambda x: 18 if x in ('sexual', 'porn', 'graphic-media') else None}, any),
+                'description': (*record_path, 'text', {str}, filter),
+                'title': (*record_path, 'text', {lambda x: x.replace('\n', '')}, {truncate_string(left=50)}),
+            }),
+        })
+        return entries

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',
+            'upload_date': '20161217',
-            'timestamp': 1494622500,
+            '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/',
+        'url': 'https://www.3cat.cat/3cat/crims-josep-tallada-lespereu-me-part-1/video/6031387/',
-        'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
+        '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',
+            'subtitles': 'mincount:1',
-            'age_limit': 16,
+            '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/common.py

@@ -1409,6 +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):

yt_dlp/extractor/dailymotion.py

@@ -10,11 +10,13 @@ from ..utils import (
     OnDemandPagedList,
     age_restricted,
     clean_html,
+    extract_attributes,
     int_or_none,
     traverse_obj,
     try_get,
     unescapeHTML,
     unsmuggle_url,
+    update_url,
     url_or_none,
     urlencode_postdata,
 )
@@ -99,12 +101,20 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
 class DailymotionIE(DailymotionBaseInfoExtractor):
     _VALID_URL = r'''(?ix)
                     https?://
+                    (?:
+                        dai\.ly/|
                         (?:
-                            (?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:(?:embed|swf|\#)/)|player(?:/\w+)?\.html\?)?video|swf)|
+                            (?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}|
-                            (?:www\.)?lequipe\.fr/video|dai\.ly
+                            (?:www\.)?lequipe\.fr
+                        )/
+                        (?:
+                            swf/(?!video)|
+                            (?:(?:crawler|embed|swf)/)?video/|
+                            player(?:/[\da-z]+)?\.html\?(?:video|(?P<is_playlist>playlist))=
                         )
-                        [/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
+                    )
-                    '''
+                    (?P<id>[^/?_&#]+)(?:[\w-]*\?playlist=(?P<playlist_id>x[0-9a-z]+))?
+    '''
     IE_NAME = 'dailymotion'
     _EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
     _TESTS = [{
@@ -218,10 +228,67 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
     }, {
         'url': 'https://geo.dailymotion.com/player/xakln.html?video=x8mjju4&customConfig%5BcustomParams%5D=%2Ffr-fr%2Ftennis%2Fwimbledon-mens-singles%2Farticles-video',
         'only_matching': True,
+    }, {  # playlist-only
+        'url': 'https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj',
+        'only_matching': True,
+    }, {
+        'url': 'https://geo.dailymotion.com/player/xmyye.html?video=x93blhi',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dailymotion.com/crawler/video/x8u4owg',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dailymotion.com/embed/video/x8u4owg',
+        'only_matching': True,
     }, {
         'url': 'https://dai.ly/x94cnnk',
         'only_matching': True,
     }]
+    _WEBPAGE_TESTS = [{
+        # https://geo.dailymotion.com/player/xmyye.html?video=x93blhi
+        'url': 'https://www.financialounge.com/video/2024/08/01/borse-europee-in-rosso-dopo-la-fed-a-milano-volano-mediobanca-e-tim-edizione-del-1-agosto/',
+        'info_dict': {
+            'id': 'x93blhi',
+            'ext': 'mp4',
+            'title': 'OnAir - 01/08/24',
+            'description': '',
+            'duration': 217,
+            'timestamp': 1722505658,
+            'upload_date': '20240801',
+            'uploader': 'Financialounge',
+            'uploader_id': 'x2vtgmm',
+            'age_limit': 0,
+            'tags': [],
+            'view_count': int,
+            'like_count': int,
+        },
+    }, {
+        # https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
+        'url': 'https://www.cycleworld.com/blogs/ask-kevin/ducati-continues-to-evolve-with-v4/',
+        'info_dict': {
+            'id': 'x7wdsj',
+        },
+        'playlist_mincount': 50,
+    }, {
+        # https://www.dailymotion.com/crawler/video/x8u4owg
+        'url': 'https://www.leparisien.fr/environnement/video-le-veloto-la-voiture-a-pedales-qui-aimerait-se-faire-une-place-sur-les-routes-09-03-2024-KCYMCPM4WFHJXMSKBUI66UNFPU.php',
+        'info_dict': {
+            'id': 'x8u4owg',
+            'ext': 'mp4',
+            'like_count': int,
+            'uploader': 'Le Parisien',
+            'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
+            'upload_date': '20240309',
+            'view_count': int,
+            'timestamp': 1709997866,
+            'age_limit': 0,
+            'uploader_id': 'x32f7b',
+            'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
+            'duration': 428.0,
+            'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
+            'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
+        },
+    }]
     _GEO_BYPASS = False
     _COMMON_MEDIA_FIELDS = '''description
       geoblockedCountries {
@@ -236,16 +303,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         for mobj in re.finditer(
                 r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
             yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
+        for mobj in re.finditer(
+                r'(?s)<script [^>]*\bsrc=(["\'])(?:https?:)?//[\w-]+\.dailymotion\.com/player/(?:(?!\1).)+\1[^>]*>', webpage):
+            attrs = extract_attributes(mobj.group(0))
+            player_url = url_or_none(attrs.get('src'))
+            if not player_url:
+                continue
+            player_url = player_url.replace('.js', '.html')
+            if player_url.startswith('//'):
+                player_url = f'https:{player_url}'
+            if video_id := attrs.get('data-video'):
+                query_string = f'video={video_id}'
+            elif playlist_id := attrs.get('data-playlist'):
+                query_string = f'playlist={playlist_id}'
+            else:
+                continue
+            yield update_url(player_url, query=query_string)
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url)
-        video_id, playlist_id = self._match_valid_url(url).groups()
+        video_id, is_playlist, playlist_id = self._match_valid_url(url).group('id', 'is_playlist', 'playlist_id')
 
-        if playlist_id:
+        if is_playlist:  # We matched the playlist query param as video_id
-            if self._yes_playlist(playlist_id, video_id):
+            playlist_id = video_id
-                return self.url_result(
+            video_id = None
-                    'http://www.dailymotion.com/playlist/' + playlist_id,
+
-                    'DailymotionPlaylist', playlist_id)
+        if self._yes_playlist(playlist_id, video_id):
+            return self.url_result(
+                f'http://www.dailymotion.com/playlist/{playlist_id}',
+                'DailymotionPlaylist', playlist_id)
 
         password = self.get_param('videopassword')
         media = self._call_api(
@@ -287,6 +373,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         is_live = media.get('isOnAir')
         formats = []
         subtitles = {}
+
         for quality, media_list in metadata['qualities'].items():
             for m in media_list:
                 media_url = m.get('url')
@@ -294,9 +381,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 if not media_url or media_type == 'application/vnd.lumberjack.manifest':
                     continue
                 if media_type == 'application/x-mpegURL':
-                    fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    fmt, subs = self._extract_m3u8_formats_and_subtitles(
                         media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
-                    formats.extend(fmts)
+                    formats.extend(fmt)
                     self._merge_subtitles(subs, target=subtitles)
                 else:
                     f = {
@@ -452,7 +539,7 @@ class DailymotionSearchIE(DailymotionPlaylistBaseIE):
 
 class DailymotionUserIE(DailymotionPlaylistBaseIE):
     IE_NAME = 'dailymotion:user'
-    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search|crawler)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.dailymotion.com/user/nqtv',
         'info_dict': {

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/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',
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
-                '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'}]},
                 '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',
+                'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
-                'uploader_id': 'ovp@yle.fi',
-                'duration': 319,
-                'view_count': int,
-                'upload_date': '20211202',
-                'release_date': '20211215',
-                'timestamp': 1638448202,
-                'subtitles': {},
                 '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', ...)):
+        for sub in traverse_obj(video_data, ('ongoing_ondemand', 'subtitles', lambda _, v: url_or_none(v['uri']))):
-            if url_or_none(sub.get('uri')):
+            subtitles.setdefault(sub.get('language') or 'und', []).append({
-                subtitles.setdefault(sub.get('language') or 'und', []).append({
+                'url': sub['uri'],
-                    'url': sub['uri'],
+                'ext': 'srt',
-                    'ext': 'srt',
+                'name': sub.get('kind'),
-                    'name': sub.get('kind'),
+            })
-                })
 
-        if is_podcast:
+        info_dict, metadata = {}, {}
-            info_dict = {
+        if is_podcast and traverse_obj(video_data, ('ongoing_ondemand', 'media_url', {url_or_none})):
-                'url': video_data['data']['ongoing_ondemand']['media_url'],
+            metadata = video_data['ongoing_ondemand']
-            }
+            info_dict['url'] = metadata['media_url']
-        elif kaltura_id := traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id', {str})):
+        elif traverse_obj(video_data, ('ongoing_event', 'manifest_url', {url_or_none})):
-            info_dict = {
+            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(
+            raise ExtractorError('Unable to extract content')
-                video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls')
+
+        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)
+            'title': episode,
-                      or episode or info.get('title')),
             'description': description,
-            'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
+            'series': series,
-                       or 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)
+            'episode_number': int_or_none(episode_number),
-                               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),
             '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
+            msg = f'{self._OAUTH_DISPLAY_ID}: Using password input as refresh token'
-
+            if self.get_param('cachedir') is not False:
-        # Allow refresh token passed to initialize cache
+                msg += ' and caching token to disk; you should supply an empty password next time'
-        if refresh_token:
+            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:
@@ -4776,7 +4777,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'live_status': live_status,
             'release_timestamp': live_start_time,
             '_format_sort_fields': (  # source_preference is lower for potentially damaged formats
-                'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'),
+                'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang', 'proto'),
         }
 
         subtitles = {}
@@ -7857,7 +7858,7 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
             'section_start': int(clip_data['startTimeMs']) / 1000,
             'section_end': int(clip_data['endTimeMs']) / 1000,
             '_format_sort_fields': (  # https protocol is prioritized for ffmpeg compatibility
-                'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang'),
+                'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang'),
         }
 
 

yt_dlp/options.py

@@ -483,13 +483,13 @@ def create_parser():
                 'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
                 'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
                 'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
-                'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext',
+                'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext', 'prefer-vp9-sort',
             }, 'aliases': {
-                'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
+                'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
-                'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
+                'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
                 '2021': ['2022', 'no-certifi', 'filename-sanitization'],
                 '2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
-                '2023': [],
+                '2023': ['prefer-vp9-sort'],
             },
         }, help=(
             'Options that can help keep compatibility with youtube-dl or youtube-dlc '

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',
@@ -5277,11 +5288,13 @@ 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}'
 
 
+@partial_application
 def truncate_string(s, left, right=0):
     assert left > 3 and right >= 0
     if s is None or len(s) <= left + right:
@@ -5324,8 +5337,11 @@ class FormatSorter:
     regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'
 
     default = ('hidden', 'aud_or_vid', 'hasvid', 'ie_pref', 'lang', 'quality',
-               'res', 'fps', 'hdr:12', 'vcodec:vp9.2', 'channels', 'acodec',
+               'res', 'fps', 'hdr:12', 'vcodec', 'channels', 'acodec',
                'size', 'br', 'asr', 'proto', 'ext', 'hasaud', 'source', 'id')  # These must not be aliases
+    _prefer_vp9_sort = ('hidden', 'aud_or_vid', 'hasvid', 'ie_pref', 'lang', 'quality',
+                        'res', 'fps', 'hdr:12', 'vcodec:vp9.2', 'channels', 'acodec',
+                        'size', 'br', 'asr', 'proto', 'ext', 'hasaud', 'source', 'id')
     ytdl_default = ('hasaud', 'lang', 'quality', 'tbr', 'filesize', 'vbr',
                     'height', 'width', 'proto', 'vext', 'abr', 'aext',
                     'fps', 'fs_approx', 'source', 'id')

yt_dlp/utils/traversal.py

@@ -20,6 +20,7 @@ from ._utils import (
     get_elements_html_by_class,
     get_elements_html_by_attribute,
     get_elements_by_attribute,
+    get_element_by_class,
     get_element_html_by_attribute,
     get_element_by_attribute,
     get_element_html_by_id,
@@ -373,7 +374,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
 
 
 @typing.overload
-def find_element(*, attr: str, value: str, tag: str | None = None, html=False): ...
+def find_element(*, attr: str, value: str, tag: str | None = None, html=False, regex=False): ...
 
 
 @typing.overload
@@ -381,34 +382,34 @@ def find_element(*, cls: str, html=False): ...
 
 
 @typing.overload
-def find_element(*, id: str, tag: str | None = None, html=False): ...
+def find_element(*, id: str, tag: str | None = None, html=False, regex=False): ...
 
 
 @typing.overload
-def find_element(*, tag: str, html=False): ...
+def find_element(*, tag: str, html=False, regex=False): ...
 
 
-def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=False):
+def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=False, regex=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:
+    ANY_TAG = r'[\w:.-]+'
-        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, escape_value=not regex)
 
     elif cls:
         assert not id, 'Cannot match both cls and id'
         assert tag is None, 'Cannot match both cls and tag'
-        func = get_element_html_by_class if html else get_elements_by_class
+        assert not regex, 'Cannot use regex with cls'
+        func = get_element_html_by_class if html else get_element_by_class
         return functools.partial(func, cls)
 
     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, escape_value=not regex)
 
     index = int(bool(html))
     return lambda html: get_element_text_and_html_by_tag(tag, html)[index]
@@ -419,23 +420,46 @@ def find_elements(*, cls: str, html=False): ...
 
 
 @typing.overload
-def find_elements(*, attr: str, value: str, tag: str | None = None, html=False): ...
+def find_elements(*, attr: str, value: str, tag: str | None = None, html=False, regex=False): ...
 
 
-def find_elements(*, tag=None, cls=None, attr=None, value=None, html=False):
+def find_elements(*, tag=None, cls=None, attr=None, value=None, html=False, regex=False):
     # deliberately using `cls=` for ease of readability
     assert cls or (attr and value), 'One of cls or (attr AND value) is required'
 
     if attr and value:
         assert not cls, 'Cannot match both attr and cls'
         func = get_elements_html_by_attribute if html else get_elements_by_attribute
-        return functools.partial(func, attr, value, tag=tag or r'[\w:.-]+')
+        return functools.partial(func, attr, value, tag=tag or r'[\w:.-]+', escape_value=not regex)
 
     assert not tag, 'Cannot match both cls and tag'
+    assert not regex, 'Cannot use regex with cls'
     func = get_elements_html_by_class if html else get_elements_by_class
     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 unpack(func):
+    @functools.wraps(func)
+    def inner(items, **kwargs):
+        return func(*items, **kwargs)
+
+    return inner
+
+
 def get_first(obj, *paths, **kwargs):
     return traverse_obj(obj, *((..., *variadic(keys)) for keys in paths), **kwargs, get_all=False)