Merge f7dc45d3a643063e653e0dcda9faeb9973ad93b5 into 420d53387cff54ea1fccca061438d59bdb50a39c

* from yt-dlp/yt-dlp#12313
* also fix d7c2708

.gitignore

@@ -1,3 +1,4 @@
+__pycache__/
 *.pyc
 *.pyo
 *.class
@@ -5,6 +6,7 @@
 *.DS_Store
 wine-py2exe/
 py2exe.log
+.pytest_cache/
 *.kate-swp
 build/
 dist/

test/test_jsinterp.py

@@ -11,6 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import math
 import re
+import time
 
 from youtube_dl.compat import compat_str as str
 from youtube_dl.jsinterp import JS_Undefined, JSInterpreter
@@ -208,6 +209,34 @@ class TestJSInterpreter(unittest.TestCase):
         self._test(jsi, 86000, args=['12/31/1969 18:01:26 MDT'])
         # epoch 0
         self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
+        # undefined
+        self._test(jsi, NaN, args=[JS_Undefined])
+        # y,m,d, ... - may fail with older dates lacking DST data
+        jsi = JSInterpreter(
+            'function f() { return new Date(%s); }'
+            % ('2024, 5, 29, 2, 52, 12, 42',))
+        self._test(jsi, (
+            1719625932042                           # UK value
+            + (
+                + 3600                              # back to GMT
+                + (time.altzone if time.daylight    # host's DST
+                   else time.timezone)
+            ) * 1000))
+        # no arg
+        self.assertAlmostEqual(JSInterpreter(
+            'function f() { return new Date() - 0; }').call_function('f'),
+            time.time() * 1000, delta=100)
+        # Date.now()
+        self.assertAlmostEqual(JSInterpreter(
+            'function f() { return Date.now(); }').call_function('f'),
+            time.time() * 1000, delta=100)
+        # Date.parse()
+        jsi = JSInterpreter('function f(dt) { return Date.parse(dt); }')
+        self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
+        # Date.UTC()
+        jsi = JSInterpreter('function f() { return Date.UTC(%s); }'
+                            % ('1970, 0, 1, 0, 0, 0, 0',))
+        self._test(jsi, 0)
 
     def test_call(self):
         jsi = JSInterpreter('''
@@ -463,6 +492,14 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return NaN << 42}', 0)
         self._test('function f(){return "21.9" << 1}', 42)
         self._test('function f(){return 21 << 4294967297}', 42)
+        self._test('function f(){return true << "5";}', 32)
+        self._test('function f(){return true << true;}', 2)
+        self._test('function f(){return "19" & "21.9";}', 17)
+        self._test('function f(){return "19" & false;}', 0)
+        self._test('function f(){return "11.0" >> "2.1";}', 2)
+        self._test('function f(){return 5 ^ 9;}', 12)
+        self._test('function f(){return 0.0 << NaN}', 0)
+        self._test('function f(){return null << undefined}', 0)
 
     def test_negative(self):
         self._test('function f(){return 2    *    -2.0    ;}', -4)

test/test_utils.py

@@ -1603,11 +1603,14 @@ Line 1
 
     def test_get_element_by_class(self):
         html = '''
-            <span class="foo bar">nice</span>
+            <span class="foo bar baz-bam">nice</span>
         '''
 
         self.assertEqual(get_element_by_class('foo', html), 'nice')
+        self.assertEqual(get_element_by_class('bar', html), 'nice')
         self.assertEqual(get_element_by_class('no-such-class', html), None)
+        self.assertEqual(get_element_by_class('baz', html), None)
+        self.assertEqual(get_element_by_class('bam', html), None)
 
     def test_get_element_by_attribute(self):
         html = '''
@@ -1626,10 +1629,13 @@ Line 1
 
     def test_get_elements_by_class(self):
         html = '''
-            <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+            <span class="foo bar baz-bam">nice</span><span class="foo bar">also nice</span>
         '''
 
         self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_class('bar', html), ['nice', 'also nice'])
+        self.assertEqual(get_elements_by_class('baz', html), [])
+        self.assertEqual(get_elements_by_class('bam', html), [])
         self.assertEqual(get_elements_by_class('no-such-class', html), [])
 
     def test_get_elements_by_attribute(self):

test/test_youtube_signature.py

@@ -223,6 +223,18 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/9c6dfc4a/player_ias.vflset/en_US/base.js',
         'jbu7ylIosQHyJyJV', 'uwI0ESiynAmhNg',
     ),
+    (
+        'https://www.youtube.com/s/player/f6e09c70/player_ias.vflset/en_US/base.js',
+        'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
+    ),
+    (
+        'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
+        'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
+    ),
+    (
+        'https://www.youtube.com/s/player/91201489/player_ias_tce.vflset/en_US/base.js',
+        'W9HJZKktxuYoDTqW', 'U48vOZHaeYS6vO',
+    ),
 ]
 
 
@@ -284,7 +296,7 @@ def t_factory(name, sig_func, url_pattern):
 
 
 def signature(jscode, sig_input):
-    func = YoutubeIE(FakeYDL())._parse_sig_js(jscode)
+    func = YoutubeIE(FakeYDL({'cachedir': False}))._parse_sig_js(jscode)
     src_sig = (
         compat_str(string.printable[:sig_input])
         if isinstance(sig_input, int) else sig_input)
@@ -292,9 +304,10 @@ def signature(jscode, sig_input):
 
 
 def n_sig(jscode, sig_input):
-    funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode)
+    ie = YoutubeIE(FakeYDL({'cachedir': False}))
-    return JSInterpreter(jscode).call_function(
+    jsi = JSInterpreter(jscode)
-        funcname, sig_input, _ytdl_do_not_return=sig_input)
+    jsi, _, func_code = ie._extract_n_function_code_jsi(sig_input, jsi)
+    return ie._extract_n_function_from_code(jsi, func_code)(sig_input)
 
 
 make_sig_test = t_factory(

youtube_dl/__init__.py

@@ -18,7 +18,7 @@ from .compat import (
     compat_getpass,
     compat_register_utf8,
     compat_shlex_split,
-    workaround_optparse_bug9161,
+    _workaround_optparse_bug9161,
 )
 from .utils import (
     _UnsafeExtensionError,
@@ -50,7 +50,7 @@ def _real_main(argv=None):
     # Compatibility fix for Windows
     compat_register_utf8()
 
-    workaround_optparse_bug9161()
+    _workaround_optparse_bug9161()
 
     setproctitle('youtube-dl')
 

youtube_dl/compat.py

@@ -16,7 +16,6 @@ import os
 import platform
 import re
 import shlex
-import shutil
 import socket
 import struct
 import subprocess
@@ -24,11 +23,15 @@ import sys
 import types
 import xml.etree.ElementTree
 
+_IDENTITY = lambda x: x
+
 # naming convention
 # 'compat_' + Python3_name.replace('.', '_')
 # other aliases exist for convenience and/or legacy
+# wrap disposable test values in type() to reclaim storage
 
-# deal with critical unicode/str things first
+# deal with critical unicode/str things first:
+# compat_str, compat_basestring, compat_chr
 try:
     # Python 2
     compat_str, compat_basestring, compat_chr = (
@@ -39,18 +42,23 @@ except NameError:
         str, (str, bytes), chr
     )
 
-# casefold
+
+# compat_casefold
 try:
     compat_str.casefold
     compat_casefold = lambda s: s.casefold()
 except AttributeError:
     from .casefold import _casefold as compat_casefold
 
+
+# compat_collections_abc
 try:
     import collections.abc as compat_collections_abc
 except ImportError:
     import collections as compat_collections_abc
 
+
+# compat_urllib_request
 try:
     import urllib.request as compat_urllib_request
 except ImportError:  # Python 2
@@ -79,11 +87,15 @@ except TypeError:
     _add_init_method_arg(compat_urllib_request.Request)
     del _add_init_method_arg
 
+
+# compat_urllib_error
 try:
     import urllib.error as compat_urllib_error
 except ImportError:  # Python 2
     import urllib2 as compat_urllib_error
 
+
+# compat_urllib_parse
 try:
     import urllib.parse as compat_urllib_parse
 except ImportError:  # Python 2
@@ -98,17 +110,23 @@ except ImportError:  # Python 2
 compat_urlparse = compat_urllib_parse
 compat_urllib_parse_urlparse = compat_urllib_parse.urlparse
 
+
+# compat_urllib_response
 try:
     import urllib.response as compat_urllib_response
 except ImportError:  # Python 2
     import urllib as compat_urllib_response
 
+
+# compat_urllib_response.addinfourl
 try:
     compat_urllib_response.addinfourl.status
 except AttributeError:
     # .getcode() is deprecated in Py 3.
     compat_urllib_response.addinfourl.status = property(lambda self: self.getcode())
 
+
+# compat_http_cookiejar
 try:
     import http.cookiejar as compat_cookiejar
 except ImportError:  # Python 2
@@ -127,12 +145,16 @@ else:
     compat_cookiejar_Cookie = compat_cookiejar.Cookie
 compat_http_cookiejar_Cookie = compat_cookiejar_Cookie
 
+
+# compat_http_cookies
 try:
     import http.cookies as compat_cookies
 except ImportError:  # Python 2
     import Cookie as compat_cookies
 compat_http_cookies = compat_cookies
 
+
+# compat_http_cookies_SimpleCookie
 if sys.version_info[0] == 2 or sys.version_info < (3, 3):
     class compat_cookies_SimpleCookie(compat_cookies.SimpleCookie):
         def load(self, rawdata):
@@ -155,11 +177,15 @@ else:
     compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
 compat_http_cookies_SimpleCookie = compat_cookies_SimpleCookie
 
+
+# compat_html_entities, probably useless now
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
+
+# compat_html_entities_html5
 try:  # Python >= 3.3
     compat_html_entities_html5 = compat_html_entities.html5
 except AttributeError:
@@ -2408,18 +2434,24 @@ except AttributeError:
     # Py < 3.1
     compat_http_client.HTTPResponse.getcode = lambda self: self.status
 
+
+# compat_urllib_HTTPError
 try:
     from urllib.error import HTTPError as compat_HTTPError
 except ImportError:  # Python 2
     from urllib2 import HTTPError as compat_HTTPError
 compat_urllib_HTTPError = compat_HTTPError
 
+
+# compat_urllib_request_urlretrieve
 try:
     from urllib.request import urlretrieve as compat_urlretrieve
 except ImportError:  # Python 2
     from urllib import urlretrieve as compat_urlretrieve
 compat_urllib_request_urlretrieve = compat_urlretrieve
 
+
+# compat_html_parser_HTMLParser, compat_html_parser_HTMLParseError
 try:
     from HTMLParser import (
         HTMLParser as compat_HTMLParser,
@@ -2432,22 +2464,33 @@ except ImportError:  # Python 3
         # HTMLParseError was deprecated in Python 3.3 and removed in
         # Python 3.5. Introducing dummy exception for Python >3.5 for compatible
         # and uniform cross-version exception handling
+
         class compat_HTMLParseError(Exception):
             pass
+
 compat_html_parser_HTMLParser = compat_HTMLParser
 compat_html_parser_HTMLParseError = compat_HTMLParseError
 
+
+# compat_subprocess_get_DEVNULL
 try:
     _DEVNULL = subprocess.DEVNULL
     compat_subprocess_get_DEVNULL = lambda: _DEVNULL
 except AttributeError:
     compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
 
+
+# compat_http_server
 try:
     import http.server as compat_http_server
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
+
+# compat_urllib_parse_unquote_to_bytes,
+# compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus,
+# compat_urllib_parse_urlencode,
+# compat_urllib_parse_parse_qs
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
@@ -2598,6 +2641,8 @@ except ImportError:  # Python 2
 
 compat_urllib_parse_parse_qs = compat_parse_qs
 
+
+# compat_urllib_request_DataHandler
 try:
     from urllib.request import DataHandler as compat_urllib_request_DataHandler
 except ImportError:  # Python < 3.4
@@ -2632,16 +2677,20 @@ except ImportError:  # Python < 3.4
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
+
+# compat_xml_etree_ElementTree_ParseError
 try:
     from xml.etree.ElementTree import ParseError as compat_xml_parse_error
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 compat_xml_etree_ElementTree_ParseError = compat_xml_parse_error
 
-etree = xml.etree.ElementTree
+
+# compat_xml_etree_ElementTree_Element
+_etree = xml.etree.ElementTree
 
 
-class _TreeBuilder(etree.TreeBuilder):
+class _TreeBuilder(_etree.TreeBuilder):
     def doctype(self, name, pubid, system):
         pass
 
@@ -2650,7 +2699,7 @@ try:
     # xml.etree.ElementTree.Element is a method in Python <=2.6 and
     # the following will crash with:
     #  TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types
-    isinstance(None, etree.Element)
+    isinstance(None, _etree.Element)
     from xml.etree.ElementTree import Element as compat_etree_Element
 except TypeError:  # Python <=2.6
     from xml.etree.ElementTree import _ElementInterface as compat_etree_Element
@@ -2658,12 +2707,12 @@ compat_xml_etree_ElementTree_Element = compat_etree_Element
 
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
-        return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
+        return _etree.XML(text, parser=_etree.XMLParser(target=_TreeBuilder()))
 else:
     # python 2.x tries to encode unicode strings with ascii (see the
     # XMLParser._fixtext method)
     try:
-        _etree_iter = etree.Element.iter
+        _etree_iter = _etree.Element.iter
     except AttributeError:  # Python <=2.6
         def _etree_iter(root):
             for el in root.findall('*'):
@@ -2675,27 +2724,29 @@ else:
     # 2.7 source
     def _XML(text, parser=None):
         if not parser:
-            parser = etree.XMLParser(target=_TreeBuilder())
+            parser = _etree.XMLParser(target=_TreeBuilder())
         parser.feed(text)
         return parser.close()
 
     def _element_factory(*args, **kwargs):
-        el = etree.Element(*args, **kwargs)
+        el = _etree.Element(*args, **kwargs)
         for k, v in el.items():
             if isinstance(v, bytes):
                 el.set(k, v.decode('utf-8'))
         return el
 
     def compat_etree_fromstring(text):
-        doc = _XML(text, parser=etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory)))
+        doc = _XML(text, parser=_etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory)))
         for el in _etree_iter(doc):
             if el.text is not None and isinstance(el.text, bytes):
                 el.text = el.text.decode('utf-8')
         return doc
 
-if hasattr(etree, 'register_namespace'):
+
-    compat_etree_register_namespace = etree.register_namespace
+# compat_xml_etree_register_namespace
-else:
+try:
+    compat_etree_register_namespace = _etree.register_namespace
+except AttributeError:
     def compat_etree_register_namespace(prefix, uri):
         """Register a namespace prefix.
         The registry is global, and any existing mapping for either the
@@ -2704,14 +2755,16 @@ else:
         attributes in this namespace will be serialized with prefix if possible.
         ValueError is raised if prefix is reserved or is invalid.
         """
-        if re.match(r"ns\d+$", prefix):
+        if re.match(r'ns\d+$', prefix):
-            raise ValueError("Prefix format reserved for internal use")
+            raise ValueError('Prefix format reserved for internal use')
-        for k, v in list(etree._namespace_map.items()):
+        for k, v in list(_etree._namespace_map.items()):
             if k == uri or v == prefix:
-                del etree._namespace_map[k]
+                del _etree._namespace_map[k]
-        etree._namespace_map[uri] = prefix
+        _etree._namespace_map[uri] = prefix
 compat_xml_etree_register_namespace = compat_etree_register_namespace
 
+
+# compat_xpath, compat_etree_iterfind
 if sys.version_info < (2, 7):
     # Here comes the crazy part: In 2.6, if the xpath is a unicode,
     # .//node does not match if a node is a direct child of . !
@@ -2898,7 +2951,6 @@ if sys.version_info < (2, 7):
         def __init__(self, root):
             self.root = root
 
-    ##
     # Generate all matching objects.
 
     def compat_etree_iterfind(elem, path, namespaces=None):
@@ -2933,13 +2985,15 @@ if sys.version_info < (2, 7):
 
 
 else:
-    compat_xpath = lambda xpath: xpath
     compat_etree_iterfind = lambda element, match: element.iterfind(match)
+    compat_xpath = _IDENTITY
 
 
+# compat_os_name
 compat_os_name = os._name if os.name == 'java' else os.name
 
 
+# compat_shlex_quote
 if compat_os_name == 'nt':
     def compat_shlex_quote(s):
         return s if re.match(r'^[-_\w./]+$', s) else '"%s"' % s.replace('"', '\\"')
@@ -2954,6 +3008,7 @@ else:
                 return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
+# compat_shlex.split
 try:
     args = shlex.split('中文')
     assert (isinstance(args, list)
@@ -2969,6 +3024,7 @@ except (AssertionError, UnicodeEncodeError):
         return list(map(lambda s: s.decode('utf-8'), shlex.split(s, comments, posix)))
 
 
+# compat_ord
 def compat_ord(c):
     if isinstance(c, int):
         return c
@@ -2976,6 +3032,7 @@ def compat_ord(c):
         return ord(c)
 
 
+# compat_getenv, compat_os_path_expanduser, compat_setenv
 if sys.version_info >= (3, 0):
     compat_getenv = os.getenv
     compat_expanduser = os.path.expanduser
@@ -3063,6 +3120,7 @@ else:
 compat_os_path_expanduser = compat_expanduser
 
 
+# compat_os_path_realpath
 if compat_os_name == 'nt' and sys.version_info < (3, 8):
     # os.path.realpath on Windows does not follow symbolic links
     # prior to Python 3.8 (see https://bugs.python.org/issue9949)
@@ -3076,6 +3134,7 @@ else:
 compat_os_path_realpath = compat_realpath
 
 
+# compat_print
 if sys.version_info < (3, 0):
     def compat_print(s):
         from .utils import preferredencoding
@@ -3086,6 +3145,7 @@ else:
         print(s)
 
 
+# compat_getpass_getpass
 if sys.version_info < (3, 0) and sys.platform == 'win32':
     def compat_getpass(prompt, *args, **kwargs):
         if isinstance(prompt, compat_str):
@@ -3098,22 +3158,22 @@ else:
 compat_getpass_getpass = compat_getpass
 
 
+# compat_input
 try:
     compat_input = raw_input
 except NameError:  # Python 3
     compat_input = input
 
 
+# compat_kwargs
 # Python < 2.6.5 require kwargs to be bytes
 try:
-    def _testfunc(x):
+    (lambda x: x)(**{'x': 0})
-        pass
-    _testfunc(**{'x': 0})
 except TypeError:
     def compat_kwargs(kwargs):
         return dict((bytes(k), v) for k, v in kwargs.items())
 else:
-    compat_kwargs = lambda kwargs: kwargs
+    compat_kwargs = _IDENTITY
 
 
 # compat_numeric_types
@@ -3132,6 +3192,8 @@ except NameError:  # Python 3
 # compat_int
 compat_int = compat_integer_types[-1]
 
+
+# compat_socket_create_connection
 if sys.version_info < (2, 7):
     def compat_socket_create_connection(address, timeout, source_address=None):
         host, port = address
@@ -3158,6 +3220,7 @@ else:
     compat_socket_create_connection = socket.create_connection
 
 
+# compat_contextlib_suppress
 try:
     from contextlib import suppress as compat_contextlib_suppress
 except ImportError:
@@ -3205,7 +3268,7 @@ except AttributeError:
 
 # Fix https://github.com/ytdl-org/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
-def workaround_optparse_bug9161():
+def _workaround_optparse_bug9161():
     op = optparse.OptionParser()
     og = optparse.OptionGroup(op, 'foo')
     try:
@@ -3224,9 +3287,10 @@ def workaround_optparse_bug9161():
         optparse.OptionGroup.add_option = _compat_add_option
 
 
-if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
+# compat_shutil_get_terminal_size
-    compat_get_terminal_size = shutil.get_terminal_size
+try:
-else:
+    from shutil import get_terminal_size as compat_get_terminal_size  # Python >= 3.3
+except ImportError:
     _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
 
     def compat_get_terminal_size(fallback=(80, 24)):
@@ -3256,27 +3320,33 @@ else:
                 columns = _columns
             if lines is None or lines <= 0:
                 lines = _lines
+
         return _terminal_size(columns, lines)
 
+compat_shutil_get_terminal_size = compat_get_terminal_size
 
+
+# compat_itertools_count
 try:
-    itertools.count(start=0, step=1)
+    type(itertools.count(start=0, step=1))
     compat_itertools_count = itertools.count
-except TypeError:  # Python 2.6
+except TypeError:  # Python 2.6 lacks step
     def compat_itertools_count(start=0, step=1):
         while True:
             yield start
             start += step
 
 
+# compat_tokenize_tokenize
 if sys.version_info >= (3, 0):
     from tokenize import tokenize as compat_tokenize_tokenize
 else:
     from tokenize import generate_tokens as compat_tokenize_tokenize
 
 
+# compat_struct_pack, compat_struct_unpack, compat_Struct
 try:
-    struct.pack('!I', 0)
+    type(struct.pack('!I', 0))
 except TypeError:
     # In Python 2.6 and 2.7.x < 2.7.7, struct requires a bytes argument
     # See https://bugs.python.org/issue19099
@@ -3308,8 +3378,10 @@ else:
         compat_Struct = struct.Struct
 
 
-# compat_map/filter() returning an iterator, supposedly the
+# builtins returning an iterator
-# same versioning as for zip below
+
+# compat_map, compat_filter
+# supposedly the same versioning as for zip below
 try:
     from future_builtins import map as compat_map
 except ImportError:
@@ -3326,6 +3398,7 @@ except ImportError:
     except ImportError:
         compat_filter = filter
 
+# compat_zip
 try:
     from future_builtins import zip as compat_zip
 except ImportError:  # not 2.6+ or is 3.x
@@ -3335,6 +3408,7 @@ except ImportError:  # not 2.6+ or is 3.x
         compat_zip = zip
 
 
+# compat_itertools_zip_longest
 # method renamed between Py2/3
 try:
     from itertools import zip_longest as compat_itertools_zip_longest
@@ -3342,7 +3416,8 @@ except ImportError:
     from itertools import izip_longest as compat_itertools_zip_longest
 
 
-# new class in collections
+# compat_collections_chain_map
+# collections.ChainMap: new class
 try:
     from collections import ChainMap as compat_collections_chain_map
     # Py3.3's ChainMap is deficient
@@ -3398,19 +3473,22 @@ except ImportError:
         def new_child(self, m=None, **kwargs):
             m = m or {}
             m.update(kwargs)
-            return compat_collections_chain_map(m, *self.maps)
+            # support inheritance !
+            return type(self)(m, *self.maps)
 
         @property
         def parents(self):
-            return compat_collections_chain_map(*(self.maps[1:]))
+            return type(self)(*(self.maps[1:]))
 
 
+# compat_re_Pattern, compat_re_Match
 # Pythons disagree on the type of a pattern (RegexObject, _sre.SRE_Pattern, Pattern, ...?)
 compat_re_Pattern = type(re.compile(''))
 # and on the type of a match
 compat_re_Match = type(re.match('a', 'a'))
 
 
+# compat_base64_b64decode
 if sys.version_info < (3, 3):
     def compat_b64decode(s, *args, **kwargs):
         if isinstance(s, compat_str):
@@ -3422,6 +3500,7 @@ else:
 compat_base64_b64decode = compat_b64decode
 
 
+# compat_ctypes_WINFUNCTYPE
 if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0):
     # PyPy2 prior to version 5.4.0 expects byte strings as Windows function
     # names, see the original PyPy issue [1] and the youtube-dl one [2].
@@ -3440,6 +3519,7 @@ else:
         return ctypes.WINFUNCTYPE(*args, **kwargs)
 
 
+# compat_open
 if sys.version_info < (3, 0):
     # open(file, mode='r', buffering=- 1, encoding=None, errors=None, newline=None, closefd=True) not: opener=None
     def compat_open(file_, *args, **kwargs):
@@ -3467,18 +3547,28 @@ except AttributeError:
     def compat_datetime_timedelta_total_seconds(td):
         return (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
 
+
 # optional decompression packages
+# compat_brotli
 # PyPi brotli package implements 'br' Content-Encoding
 try:
     import brotli as compat_brotli
 except ImportError:
     compat_brotli = None
+# compat_ncompress
 # PyPi ncompress package implements 'compress' Content-Encoding
 try:
     import ncompress as compat_ncompress
 except ImportError:
     compat_ncompress = None
 
+# compat_zstandard
+# PyPi zstandard package implements 'zstd' Content-Encoding (RFC 8878 7.2)
+try:
+    import zstandard as compat_zstandard
+except ImportError:
+    compat_zstandard = None
+
 
 legacy = [
     'compat_HTMLParseError',
@@ -3495,6 +3585,7 @@ legacy = [
     'compat_getpass',
     'compat_parse_qs',
     'compat_realpath',
+    'compat_shlex_split',
     'compat_urllib_parse_parse_qs',
     'compat_urllib_parse_unquote',
     'compat_urllib_parse_unquote_plus',
@@ -3508,8 +3599,6 @@ legacy = [
 
 
 __all__ = [
-    'compat_html_parser_HTMLParseError',
-    'compat_html_parser_HTMLParser',
     'compat_Struct',
     'compat_base64_b64decode',
     'compat_basestring',
@@ -3518,13 +3607,9 @@ __all__ = [
     'compat_chr',
     'compat_collections_abc',
     'compat_collections_chain_map',
-    'compat_datetime_timedelta_total_seconds',
-    'compat_http_cookiejar',
-    'compat_http_cookiejar_Cookie',
-    'compat_http_cookies',
-    'compat_http_cookies_SimpleCookie',
     'compat_contextlib_suppress',
     'compat_ctypes_WINFUNCTYPE',
+    'compat_datetime_timedelta_total_seconds',
     'compat_etree_fromstring',
     'compat_etree_iterfind',
     'compat_filter',
@@ -3533,6 +3618,12 @@ __all__ = [
     'compat_getpass_getpass',
     'compat_html_entities',
     'compat_html_entities_html5',
+    'compat_html_parser_HTMLParseError',
+    'compat_html_parser_HTMLParser',
+    'compat_http_cookiejar',
+    'compat_http_cookiejar_Cookie',
+    'compat_http_cookies',
+    'compat_http_cookies_SimpleCookie',
     'compat_http_client',
     'compat_http_server',
     'compat_input',
@@ -3555,7 +3646,7 @@ __all__ = [
     'compat_register_utf8',
     'compat_setenv',
     'compat_shlex_quote',
-    'compat_shlex_split',
+    'compat_shutil_get_terminal_size',
     'compat_socket_create_connection',
     'compat_str',
     'compat_struct_pack',
@@ -3575,5 +3666,5 @@ __all__ = [
     'compat_xml_etree_register_namespace',
     'compat_xpath',
     'compat_zip',
-    'workaround_optparse_bug9161',
+    'compat_zstandard',
 ]

youtube_dl/extractor/common.py

@@ -3128,7 +3128,8 @@ class InfoExtractor(object):
                 continue
             urls.add(source_url)
             source_type = source.get('type') or ''
-            ext = mimetype2ext(source_type) or determine_ext(source_url)
+            # https://github.com/yt-dlp/yt-dlp/pull/10956
+            ext = determine_ext(source_url, default_ext=mimetype2ext(source_type))
             if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',

youtube_dl/extractor/generic.py

@@ -31,10 +31,14 @@ from ..utils import (
     parse_resolution,
     sanitized_Request,
     smuggle_url,
+    strip_or_none,
+    T,
+    traverse_obj,
     unescapeHTML,
     unified_timestamp,
     unsmuggle_url,
     UnsupportedError,
+    update_url_query,
     url_or_none,
     urljoin,
     xpath_attr,
@@ -2237,6 +2241,7 @@ class GenericIE(InfoExtractor):
                 'display_id': 'kelis-4th-of-july',
                 'ext': 'mp4',
                 'title': 'Kelis - 4th Of July',
+                'description': 'Kelis - 4th Of July',
                 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
             },
         }, {
@@ -2246,7 +2251,7 @@ class GenericIE(InfoExtractor):
                 'id': '105',
                 'display_id': 'kelis-4th-of-july',
                 'ext': 'mp4',
-                'title': 'Kelis - 4th Of July / Embed Player',
+                'title': r're:Kelis - 4th Of July(?: / Embed Player)?$',
                 'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
             },
             'params': {
@@ -2297,6 +2302,32 @@ class GenericIE(InfoExtractor):
                 'title': 'Syren De Mer  onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
                 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
             },
+            'skip': 'needs Referer ?',
+        }, {
+            # KVS Player v10
+            'url': 'https://www.cambro.tv/588174/marleny-1/',
+            'md5': '759d2050590986c6fc341da0592c4d8e',
+            'info_dict': {
+                'id': '588174',
+                'display_id': 'marleny-1',
+                'ext': 'mp4',
+                'title': 'marleny 1',
+                'description': 'la maestra de tic toc',
+                'thumbnail': r're:https?://www\.cambro\.tv/contents/videos_screenshots/588000/588174/preview\.jpg',
+                'age_limit': 18,
+            },
+        }, {
+            # KVS Player v10 embed, NSFW
+            'url': 'https://www.cambro.tv/embed/436185',
+            'md5': '24338dc8b182900a2c9eda075a0a46c0',
+            'info_dict': {
+                'id': '436185',
+                'display_id': 'jaeandbailey-chaturbate-webcam-porn-videos',
+                'ext': 'mp4',
+                'title': 'jaeandbailey Chaturbate webcam porn videos',
+                'thumbnail': r're:https?://www\.cambro\.tv/contents/videos_screenshots/436000/436185/preview\.jpg',
+                'age_limit': 18,
+            },
         }, {
             'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
             'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
@@ -2309,14 +2340,16 @@ class GenericIE(InfoExtractor):
                 'height': 720,
                 'age_limit': 18,
             },
+            # 'skip': 'Geo-blocked in some mjurisdictions',
         }, {
+            # KVS Player v2
             'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
             'md5': 'e2f0a4c329f7986280b7328e24036d60',
             'info_dict': {
                 'id': '284002',
                 'display_id': 'just-out-of-the-shower-joi',
                 'ext': 'mp4',
-                'title': 'Just Out Of The Shower JOI - Shooshtime',
+                'title': r're:Just Out Of The Shower JOI(?: - Shooshtime)?$',
                 'height': 720,
                 'age_limit': 18,
             },
@@ -2482,9 +2515,12 @@ class GenericIE(InfoExtractor):
             return '/'.join(urlparts) + '?' + url_query
 
         flashvars = self._search_regex(
-            r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
+            r'''(?<![=!+*-])=\s*kt_player\s*\(\s*'kt_player'\s*,\s*[^)]+,\s*([\w$]+)\s*\)''',
-            webpage, 'flashvars')
+            webpage, 'flashvars name', default='flashvars')
-        flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
+        flashvars = self._search_json(
+            r'<script(?:\s[^>]*)?>[\s\S]*?var\s+%s\s*=' % (flashvars,),
+            webpage, 'flashvars', video_id, end_pattern=r';[\s\S]*?</script>',
+            transform_source=js_to_json)
 
         # extract the part after the last / as the display_id from the
         # canonical URL.
@@ -2493,12 +2529,7 @@ class GenericIE(InfoExtractor):
             r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
             webpage, 'display_id', fatal=False
         )
-        title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
+        title = flashvars.get('video_title') or self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
-
-        thumbnail = flashvars['preview_url']
-        if thumbnail.startswith('//'):
-            protocol, _, _ = url.partition('/')
-            thumbnail = protocol + thumbnail
 
         url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
         formats = []
@@ -2506,9 +2537,13 @@ class GenericIE(InfoExtractor):
             if '/get_file/' not in flashvars[key]:
                 continue
             format_id = flashvars.get(key + '_text', key)
+            f_url = urljoin(url, getrealurl(flashvars[key], flashvars['license_code']))
+            rnd = flashvars.get('rnd', key)
+            if rnd:
+                f_url = update_url_query(f_url, {'rnd': rnd})
             formats.append(merge_dicts(
                 parse_resolution(format_id) or parse_resolution(flashvars[key]), {
-                    'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
+                    'url': f_url,
                     'format_id': format_id,
                     'ext': 'mp4',
                     'http_headers': {'Referer': url},
@@ -2518,13 +2553,31 @@ class GenericIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        return {
+        csv2list = (T(lambda s: s.split(',')), Ellipsis, T(strip_or_none))
+        info = traverse_obj(flashvars, {
+            'tags': ('video_tags',) + csv2list,
+            'categories': ('video_categories',) + csv2list,
+            'thumbnails': (
+                T(dict.items), lambda _, k_v: k_v[0].startswith('preview_url'), {
+                    'url': (1, T(lambda u: urljoin(url, u))),
+                    'preference': (0, T(lambda k: 100 - len(k))),
+                }),
+        })
+        info = merge_dicts(info, {
             'id': flashvars['video_id'],
             'display_id': display_id,
             'title': title,
-            'thumbnail': thumbnail,
             'formats': formats,
-        }
+        })
+
+        # check-porn test for embed pages
+        if 'age_limit' not in info and traverse_obj(info, (
+                ('title', (('tags', 'categories'), Ellipsis) or []),
+                T(lambda t: bool(re.search(r'(?i)(?:^|\s+)porn(?:$|\s+)', t)) or None)),
+                get_all=False):
+            info['age_limit'] = 18
+
+        return info
 
     def _real_extract(self, url):
         if url.startswith('//'):
@@ -3598,7 +3651,7 @@ class GenericIE(InfoExtractor):
              ), webpage, 'KVS player', group='ver', default=False)
         if found:
             self.report_extraction('%s: KVS Player' % (video_id, ))
-            if found.split('.')[0] not in ('4', '5', '6'):
+            if found.split('.')[0] not in ('2', '4', '5', '6', '10'):
                 self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
             return merge_dicts(
                 self._extract_kvs(url, webpage, video_id),

youtube_dl/extractor/hentaistigma.py

@@ -1,6 +1,11 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    merge_dicts,
+    traverse_obj,
+)
 
 
 class HentaiStigmaIE(InfoExtractor):
@@ -24,16 +29,17 @@ class HentaiStigmaIE(InfoExtractor):
         title = self._html_search_regex(
             r'<h2[^>]+class="posttitle"[^>]*><a[^>]*>([^<]+)</a>',
             webpage, 'title')
-        wrap_url = self._html_search_regex(
+
+        wrap_url = self._search_regex(
             r'<iframe[^>]+src="([^"]+mp4)"', webpage, 'wrapper url')
-        wrap_webpage = self._download_webpage(wrap_url, video_id)
 
-        video_url = self._html_search_regex(
+        vid_page = self._download_webpage(wrap_url, video_id)
-            r'file\s*:\s*"([^"]+)"', wrap_webpage, 'video url')
 
-        return {
+        entries = self._parse_html5_media_entries(wrap_url, vid_page, video_id)
+        self._sort_formats(traverse_obj(entries, (0, 'formats')) or [])
+
+        return merge_dicts({
             'id': video_id,
-            'url': video_url,
             'title': title,
             'age_limit': 18,
-        }
+        }, entries[0])

youtube_dl/extractor/kaltura.py

@@ -23,7 +23,7 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)|
                     https?://
-                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
+                        (?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/
                         (?:
                             (?:
                                 # flash player

youtube_dl/extractor/mgoon.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class MgoonIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?
-    (?:(:?m\.)?mgoon\.com/(?:ch/(?:.+)/v|play/view)|
+    (?:(?:m\.)?mgoon\.com/(?:ch/(?:.+)/v|play/view)|
         video\.mgoon\.com)/(?P<id>[0-9]+)'''
     _API_URL = 'http://mpos.mgoon.com/player/video?id={0:}'
     _TESTS = [

youtube_dl/extractor/orf.py

@@ -112,7 +112,7 @@ class ORFRadioIE(ORFRadioBase):
 
     _VALID_URL = (
         r'https?://sound\.orf\.at/radio/(?P<station>{0})/sendung/(?P<id>\d+)(?:/(?P<show>\w+))?'.format(_STATION_RE),
-        r'https?://(?P<station>{0})\.orf\.at/player/(?P<date>\d{{8}})/(?P<id>\d+)'.format(_STATION_RE),
+        r'https?://(?P<station>{0})\.orf\.at/(?:player|programm)/(?P<date>\d{{8}})/(?P<id>\d+)'.format(_STATION_RE),
     )
 
     _TESTS = [{
@@ -150,6 +150,10 @@ class ORFRadioIE(ORFRadioBase):
             'duration': 1500,
         },
         'skip': 'Shows from ORF Sound are only available for 30 days.'
+    }, {
+        # yt-dlp/yt-dlp#11014
+        'url': 'https://oe1.orf.at/programm/20240916/769302/Playgrounds',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/xfileshare.py

@@ -12,7 +12,9 @@ from ..utils import (
     clean_html,
     decode_packed_codes,
     determine_ext,
+    extract_attributes,
     ExtractorError,
+    get_element_by_class,
     get_element_by_id,
     int_or_none,
     merge_dicts,
@@ -56,39 +58,40 @@ def aa_decode(aa_code):
 
 class XFileShareIE(InfoExtractor):
     _SITES = (
-        # status check 2024-02: site availability, G site: search
+        # status check 2024-10: site availability, G site: search
-        (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstreeam.tv
+        (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstream.tv
-        (r'filemoon\.sx/.', 'FileMoon'),
+        (r'filemoon\.(?:sx|to|in)', 'FileMoon'),
-        (r'gounlimited\.to', 'GoUnlimited'),  # no media pages listed
+        # (r'gounlimited\.to', 'GoUnlimited'),  # domain not found
         (r'govid\.me', 'GoVid'),  # no media pages listed
-        (r'highstream\.tv', 'HighStream'),  # clipwatching.com redirects here
+        (r'highstream\.tv', 'HighStream'),  # Cloudflare says host error 522, clipwatching.com now dead
-        (r'holavid\.com', 'HolaVid'),  # Cloudflare says host error 522
+        (r'holavid\.com', 'HolaVid'),  # hoster default home page
-        # (r'streamty\.com', 'Streamty'),  # no media pages listed, connection timeout
+        # (r'streamty\.com', 'Streamty'),  # spam parking domain
-        # (r'thevideobee\.to', 'TheVideoBee'),  # no pages listed, refuses connection
+        # (r'thevideobee\.to', 'TheVideoBee'),  # domain for sale
-        (r'uqload\.to', 'Uqload'),  # .com, .co redirect here
+        (r'uqload\.ws', 'Uqload'),  # .com, .co, .to redirect here
-        (r'(?:vedbam\.xyz|vadbam.net)', 'V?dB?m'),  # vidbom.com redirects here, but no valid media pages listed
+        # (r'(vadbam.net', 'VadBam'),  # domain not found
+        (r'(?:vedbam\.xyz|vadbam\.net|vbn\d\.vdbtm\.shop)', 'V?dB?m'),  # vidbom.com redirects here, but no valid media pages listed
         (r'vidlo\.us', 'vidlo'),  # no valid media pages listed
         (r'vidlocker\.xyz', 'VidLocker'),  # no media pages listed
-        (r'(?:w\d\.)?viidshar\.com', 'VidShare'),  # vidshare.tv redirects here
+        (r'(?:w\d\.)?viidshar\.com', 'VidShare'),  # vidshare.tv parked
         # (r'vup\.to', 'VUp'),  # domain not found
-        (r'wolfstream\.tv', 'WolfStream'),
+        # (r'wolfstream\.tv', 'WolfStream'),  # domain not found
-        (r'xvideosharing\.com', 'XVideoSharing'),  # just started showing 'maintenance mode'
+        (r'xvideosharing\.com', 'XVideoSharing'),
     )
 
     IE_DESC = 'XFileShare-based sites: %s' % ', '.join(list(zip(*_SITES))[1])
-    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?P<sub>[a-z]/|)(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
                   % '|'.join(site for site in list(zip(*_SITES))[0]))
     _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
 
     _FILE_NOT_FOUND_REGEXES = (
-        r'>(?:404 - )?File Not Found<',
+        r'>\s*(?:404 - )?File Not Found\s*<',
-        r'>The file was removed by administrator<',
+        r'>\s*The file was removed by administrator\s*<',
     )
     _TITLE_REGEXES = (
         r'style="z-index: [0-9]+;">([^<]+)</span>',
         r'<td nowrap>([^<]+)</td>',
         r'h4-fine[^>]*>([^<]+)<',
-        r'>Watch (.+)[ <]',
+        r'>Watch (.+?)(?: mp4)?(?: The Ultimate Free Video Hosting Solution for Webmasters and Bloggers)?<',
         r'<h2 class="video-page-head">([^<]+)</h2>',
         r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to (dead)
         r'title\s*:\s*"([^"]+)"',  # govid.me
@@ -106,38 +109,41 @@ class XFileShareIE(InfoExtractor):
 
     _TESTS = [{
         'note': 'link in `sources`',
-        'url': 'https://uqload.to/dcsu06gdb45o',
+        'url': 'https://uqload.ws/4sah252totrk.html',
-        'md5': '7f8db187b254379440bf4fcad094ae86',
+        'md5': '1f11151b5044862fbc3c112732f9f7d8',
         'info_dict': {
-            'id': 'dcsu06gdb45o',
+            'id': '4sah252totrk',
             'ext': 'mp4',
-            'title': 'f2e31015957e74c8c8427982e161c3fc mp4',
+            'title': 'JEONGHAN WONWOO Interview With Allure Korea Arabic Sub',
             'thumbnail': r're:https://.*\.jpg'
         },
         'params': {
             'nocheckcertificate': True,
         },
-        'expected_warnings': ['Unable to extract JWPlayer data'],
+        # 'expected_warnings': ['Unable to extract JWPlayer data'],
     }, {
-        'note': 'link in decoded `sources`',
+        'note': 'link in Playerjs',  # need test with 'link in decoded `sources`'
-        'url': 'https://xvideosharing.com/1tlg6agrrdgc',
+        'url': 'https://xvideosharing.com/8cnupzc1z8xq.html',
-        'md5': '2608ce41932c1657ae56258a64e647d9',
+        'md5': '9725ca7229e8f3046f2417da3bd5eddc',
         'info_dict': {
-            'id': '1tlg6agrrdgc',
+            'id': '8cnupzc1z8xq',
             'ext': 'mp4',
-            'title': '0121',
+            'title': 'HEVC X265 Big Buck Bunny 1080 10s 20MB',
             'thumbnail': r're:https?://.*\.jpg',
         },
-        'skip': 'This server is in maintenance mode.',
     }, {
-        'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
+        'note': 'JWPlayer link in un-p,a,c,k,e,d JS, in player frame',
-        'url': 'https://filemoon.sx/e/dw40rxrzruqz',
+        'url': 'https://filemoon.sx/d/fbsxidybremo',
-        'md5': '5a713742f57ac4aef29b74733e8dda01',
+        'md5': '82007a71661630f60e866f0d6ed31b2a',
         'info_dict': {
-            'id': 'dw40rxrzruqz',
+            'id': 'fbsxidybremo',
-            'title': 'dw40rxrzruqz',
+            'title': 'Uchouten',
             'ext': 'mp4'
         },
+        'params': {
+            'skip_download': 'ffmpeg',
+        },
+        'expected_warnings': ['hlsnative has detected features it does not support'],
     }, {
         'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
         'url': 'https://vadbam.net/6lnbkci96wly.html',
@@ -150,7 +156,7 @@ class XFileShareIE(InfoExtractor):
     }, {
         'note': 'JWPlayer link in clear',
         'url': 'https://w1.viidshar.com/nnibe0xf0h79.html',
-        'md5': 'f0a580ce9df06cc61b4a5c979d672367',
+        'md5': 'b95b97978093bc287c322307c689bd94',
         'info_dict': {
             'id': 'nnibe0xf0h79',
             'title': 'JaGa 68ar',
@@ -160,27 +166,21 @@ class XFileShareIE(InfoExtractor):
             'skip_download': 'ffmpeg',
         },
         'expected_warnings': ['hlsnative has detected features it does not support'],
-    }, {
-        'note': 'JWPlayer link in clear',
-        'url': 'https://wolfstream.tv/a3drtehyrg52.html',
-        'md5': '1901d86a79c5e0c6a51bdc9a4cfd3769',
-        'info_dict': {
-            'id': 'a3drtehyrg52',
-            'title': 'NFL 2023 W04 DET@GB',
-            'ext': 'mp4'
-        },
     }, {
         'url': 'https://aparat.cam/n4d6dh0wvlpr',
         'only_matching': True,
-    }, {
-        'url': 'https://uqload.to/ug5somm0ctnk.html',
-        'only_matching': True,
     }, {
         'url': 'https://highstream.tv/2owiyz3sjoux',
         'only_matching': True,
     }, {
         'url': 'https://vedbam.xyz/6lnbkci96wly.html',
         'only_matching': True,
+    }, {
+        'url': 'https://vbn2.vdbtm.shop/6lnbkci96wly.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://filemoon.in/e/5abn1ze9jifb',
+        'only_matching': True,
     }]
 
     @classmethod
@@ -194,17 +194,26 @@ class XFileShareIE(InfoExtractor):
         return list(yield_urls())
 
     def _real_extract(self, url):
-        host, video_id = self._match_valid_url(url).group('host', 'id')
+        host, sub, video_id = self._match_valid_url(url).group('host', 'sub', 'id')
 
-        url = 'https://%s/%s' % (
+        url = 'https://%s/%s%s' % (
-            host,
+            host, sub,
             'embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
         webpage = self._download_webpage(url, video_id)
-        container_div = get_element_by_id('container', webpage) or webpage
+        main = self._search_regex(
+            r'(?s)<main>(.+)</main>', webpage, 'main', default=webpage)
+        container_div = (
+            get_element_by_id('container', main)
+            or get_element_by_class('container', main)
+            or webpage)
         if self._search_regex(
                 r'>This server is in maintenance mode\.', container_div,
                 'maint error', group=0, default=None):
             raise ExtractorError(clean_html(container_div), expected=True)
+        if self._search_regex(
+                'not available in your country', container_div,
+                'geo block', group=0, default=None):
+            self.raise_geo_restricted()
         if self._search_regex(
                 self._FILE_NOT_FOUND_REGEXES, container_div,
                 'missing video error', group=0, default=None):
@@ -228,38 +237,41 @@ class XFileShareIE(InfoExtractor):
 
         title = (
             self._search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
-            or self._og_search_title(webpage, default=None)
+            or self._og_search_title(webpage, default='')).strip()
-            or video_id).strip()
 
-        obf_code = True
+        def deobfuscate(html):
-        while obf_code:
             for regex, func in (
                     (r'(?s)(?<!-)\b(eval\(function\(p,a,c,k,e,d\)\{(?:(?!</script>).)+\)\))',
                      decode_packed_codes),
                     (r'(ﾟ.+)', aa_decode)):
-                obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
+                obf_code = self._search_regex(regex, html, 'obfuscated code', default=None)
                 if obf_code:
-                    webpage = webpage.replace(obf_code, func(obf_code))
+                    return html.replace(obf_code, func(obf_code))
-                    break
 
+        def jw_extract(html):
             jwplayer_data = self._find_jwplayer_data(
-            webpage.replace(r'\'', '\''), video_id)
+                html.replace(r'\'', '\''), video_id)
             result = self._parse_jwplayer_data(
                 jwplayer_data, video_id, require_title=False,
                 m3u8_id='hls', mpd_id='dash')
-
+            result = traverse_obj(result, (
-        if not traverse_obj(result, 'formats'):
+                (None, ('entries', 0)), T(lambda r: r if r['formats'] else None)),
-            if jwplayer_data:
+                get_all=False) or {}
+            if not result and jwplayer_data:
                 self.report_warning(
                     'Failed to extract JWPlayer formats', video_id=video_id)
+            return result
+
+        def extract_from_links(html):
             urls = set()
             for regex in self._SOURCE_URL_REGEXES:
-                for mobj in re.finditer(regex, webpage):
+                for mobj in re.finditer(regex, html):
                     urls.add(mobj.group('url'))
 
-            sources = self._search_regex(
+            sources = self._search_json(
-                r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
+                r'\bsources\s*:', webpage, 'sources', video_id,
-            urls.update(traverse_obj(sources, (T(lambda s: self._parse_json(s, video_id)), Ellipsis)))
+                contains_pattern=r'\[(?!{)[^\]]+\]', default=[])
+            urls.update(sources)
 
             formats = []
             for video_url in traverse_obj(urls, (Ellipsis, T(url_or_none))):
@@ -273,7 +285,33 @@ class XFileShareIE(InfoExtractor):
                         'url': video_url,
                         'format_id': 'sd',
                     })
-            result = {'formats': formats}
+            return {'formats': formats}
+
+        def extract_info(html):
+            html = deobfuscate(html) or html
+            result = jw_extract(html)
+            if not result.get('formats'):
+                result = extract_from_links(html)
+            return result
+
+        def pages_to_extract(html):
+            yield html
+            # page with separate protected download page also has player link
+            player_iframe = self._search_regex(
+                r'(<iframe\s[^>]+>)',
+                get_element_by_id('iframe-holder', html) or '',
+                'player iframe', default='')
+            player_url = extract_attributes(player_iframe).get('src')
+            if player_url:
+                html = self._download_webpage(player_url, video_id, note='Downloading player page', fatal=False)
+            if html:
+                yield html
+
+        result = {}
+        for html in pages_to_extract(webpage):
+            result = extract_info(html)
+            if result.get('formats'):
+                break
 
         self._sort_formats(result['formats'])
 

youtube_dl/extractor/yandexmusic.py

@@ -30,17 +30,20 @@ class YandexMusicBaseIE(InfoExtractor):
     @staticmethod
     def _raise_captcha():
         raise ExtractorError(
-            'YandexMusic has considered youtube-dl requests automated and '
+            'YandexMusic has considered youtube-dl requests automated '
-            'asks you to solve a CAPTCHA. You can either wait for some '
+            'and asks you to solve a CAPTCHA. You can wait for some time '
-            'time until unblocked and optionally use --sleep-interval '
+            'until unblocked and optionally use --sleep-interval in future; '
-            'in future or alternatively you can go to https://music.yandex.ru/ '
+            'otherwise solve the CAPTCHA at https://music.yandex.ru/, '
-            'solve CAPTCHA, then export cookies and pass cookie file to '
+            'then export cookies and pass the cookie file to youtube-dl '
-            'youtube-dl with --cookies',
+            'with --cookies.',
             expected=True)
 
     def _download_webpage_handle(self, *args, **kwargs):
         webpage = super(YandexMusicBaseIE, self)._download_webpage_handle(*args, **kwargs)
-        if 'Нам очень жаль, но запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage:
+        blocked_ip_msg = (
+            'Нам очень жаль, но запросы, поступившие с '
+            'вашего IP-адреса, похожи на автоматические.')
+        if blocked_ip_msg in (webpage or [''])[0]:
             self._raise_captcha()
         return webpage
 

youtube_dl/extractor/youtube.py

@@ -122,7 +122,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'TVHTML5',
-                    'clientVersion': '7.20241201.18.00',
+                    'clientVersion': '7.20250120.19.00',
+                    'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
                 },
             },
             'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
@@ -1851,11 +1852,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         if func_code:
             return jsi, player_id, func_code
+        return self._extract_n_function_code_jsi(video_id, jsi, player_id)
 
-        func_name = self._extract_n_function_name(jscode)
+    def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
+
+        var_ay = self._search_regex(
+            r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"[^"]+"\s*\.\s*split\("\{"\))(?=\s*[,;])',
+            jsi.code, 'useful values', default='')
+
+        func_name = self._extract_n_function_name(jsi.code)
 
         func_code = jsi.extract_function_code(func_name)
+        if var_ay:
+            func_code = (func_code[0], ';\n'.join((var_ay, func_code[1])))
 
+        if player_id:
             self.cache.store('youtube-nsig', player_id, func_code)
         return jsi, player_id, func_code
 

youtube_dl/jsinterp.py

@@ -1,10 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import calendar
 import itertools
 import json
 import operator
 import re
+import time
 
 from functools import update_wrapper, wraps
 
@@ -12,8 +14,10 @@ from .utils import (
     error_to_compat_str,
     ExtractorError,
     float_or_none,
+    int_or_none,
     js_to_json,
     remove_quotes,
+    str_or_none,
     unified_timestamp,
     variadic,
     write_string,
@@ -150,6 +154,7 @@ def _js_to_primitive(v):
     )
 
 
+# more exact: yt-dlp/yt-dlp#12110
 def _js_toString(v):
     return (
         'undefined' if v is JS_Undefined
@@ -158,7 +163,7 @@ def _js_toString(v):
         else 'null' if v is None
         # bool <= int: do this first
         else ('false', 'true')[v] if isinstance(v, bool)
-        else '{0:.7f}'.format(v).rstrip('.0') if isinstance(v, compat_numeric_types)
+        else re.sub(r'(?<=\d)\.?0*$', '', '{0:.7f}'.format(v)) if isinstance(v, compat_numeric_types)
         else _js_to_primitive(v))
 
 
@@ -404,6 +409,7 @@ class JSInterpreter(object):
     class Exception(ExtractorError):
         def __init__(self, msg, *args, **kwargs):
             expr = kwargs.pop('expr', None)
+            msg = str_or_none(msg, default='"None"')
             if expr is not None:
                 msg = '{0} in: {1!r:.100}'.format(msg.rstrip(), expr)
             super(JSInterpreter.Exception, self).__init__(msg, *args, **kwargs)
@@ -431,6 +437,7 @@ class JSInterpreter(object):
                 flags, _ = self.regex_flags(flags)
             # First, avoid https://github.com/python/cpython/issues/74534
             self.__self = None
+            pattern_txt = str_or_none(pattern_txt) or '(?:)'
             self.__pattern_txt = pattern_txt.replace('[[', r'[\[')
             self.__flags = flags
 
@@ -475,6 +482,73 @@ class JSInterpreter(object):
                 flags |= cls.RE_FLAGS[ch]
             return flags, expr[idx + 1:]
 
+    class JS_Date(object):
+        _t = None
+
+        @staticmethod
+        def __ymd_etc(*args, **kw_is_utc):
+            # args: year, monthIndex, day, hours, minutes, seconds, milliseconds
+            is_utc = kw_is_utc.get('is_utc', False)
+
+            args = list(args[:7])
+            args += [0] * (9 - len(args))
+            args[1] += 1  # month 0..11 -> 1..12
+            ms = args[6]
+            for i in range(6, 9):
+                args[i] = -1  # don't know
+            if is_utc:
+                args[-1] = 1
+            # TODO: [MDN] When a segment overflows or underflows its expected
+            # range, it usually "carries over to" or "borrows from" the higher segment.
+            try:
+                mktime = calendar.timegm if is_utc else time.mktime
+                return mktime(time.struct_time(args)) * 1000 + ms
+            except (OverflowError, ValueError):
+                return None
+
+        @classmethod
+        def UTC(cls, *args):
+            t = cls.__ymd_etc(*args, is_utc=True)
+            return _NaN if t is None else t
+
+        @staticmethod
+        def parse(date_str, **kw_is_raw):
+            is_raw = kw_is_raw.get('is_raw', False)
+
+            t = unified_timestamp(str_or_none(date_str), False)
+            return int(t * 1000) if t is not None else t if is_raw else _NaN
+
+        @staticmethod
+        def now(**kw_is_raw):
+            is_raw = kw_is_raw.get('is_raw', False)
+
+            t = time.time()
+            return int(t * 1000) if t is not None else t if is_raw else _NaN
+
+        def __init__(self, *args):
+            if not args:
+                args = [self.now(is_raw=True)]
+            if len(args) == 1:
+                if isinstance(args[0], JSInterpreter.JS_Date):
+                    self._t = int_or_none(args[0].valueOf(), default=None)
+                else:
+                    arg_type = _js_typeof(args[0])
+                    if arg_type == 'string':
+                        self._t = self.parse(args[0], is_raw=True)
+                    elif arg_type == 'number':
+                        self._t = int(args[0])
+            else:
+                self._t = self.__ymd_etc(*args)
+
+        def toString(self):
+            try:
+                return time.strftime('%a %b %0d %Y %H:%M:%S %Z%z', self._t).rstrip()
+            except TypeError:
+                return "Invalid Date"
+
+        def valueOf(self):
+            return _NaN if self._t is None else self._t
+
     @classmethod
     def __op_chars(cls):
         op_chars = set(';,[')
@@ -599,14 +673,15 @@ class JSInterpreter(object):
         except Exception as e:
             raise self.Exception('Failed to evaluate {left_val!r:.50} {op} {right_val!r:.50}'.format(**locals()), expr, cause=e)
 
-    def _index(self, obj, idx, allow_undefined=True):
+    def _index(self, obj, idx, allow_undefined=None):
         if idx == 'length' and isinstance(obj, list):
             return len(obj)
         try:
             return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
         except (TypeError, KeyError, IndexError) as e:
-            if allow_undefined:
+            # allow_undefined is None gives correct behaviour
-                # when is not allowed?
+            if allow_undefined or (
+                    allow_undefined is None and not isinstance(e, TypeError)):
                 return JS_Undefined
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
@@ -715,7 +790,7 @@ class JSInterpreter(object):
 
         new_kw, _, obj = expr.partition('new ')
         if not new_kw:
-            for klass, konstr in (('Date', lambda x: int(unified_timestamp(x, False) * 1000)),
+            for klass, konstr in (('Date', lambda *x: self.JS_Date(*x).valueOf()),
                                   ('RegExp', self.JS_RegExp),
                                   ('Error', self.Exception)):
                 if not obj.startswith(klass + '('):
@@ -1034,6 +1109,7 @@ class JSInterpreter(object):
                     'String': compat_str,
                     'Math': float,
                     'Array': list,
+                    'Date': self.JS_Date,
                 }
                 obj = local_vars.get(variable)
                 if obj in (JS_Undefined, None):
@@ -1086,6 +1162,8 @@ class JSInterpreter(object):
                         assertion(len(argvals) == 2, 'takes two arguments')
                         return argvals[0] ** argvals[1]
                     raise self.Exception('Unsupported Math method ' + member, expr=expr)
+                elif obj is self.JS_Date:
+                    return getattr(obj, member)(*argvals)
 
                 if member == 'split':
                     assertion(len(argvals) <= 2, 'takes at most two arguments')

youtube_dl/utils.py

@@ -1960,7 +1960,7 @@ def get_element_by_attribute(attribute, value, html, escape_value=True):
 def get_elements_by_class(class_name, html):
     """Return the content of all tags with the specified class in the passed HTML document as a list"""
     return get_elements_by_attribute(
-        'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+        'class', r'[^\'"]*(?<!-)\b%s\b(?!-)[^\'"]*' % re.escape(class_name),
         html, escape_value=False)
 
 
@@ -4498,7 +4498,7 @@ def strip_jsonp(code):
 def js_to_json(code, *args, **kwargs):
 
     # vars is a dict of (var, val) pairs to substitute
-    vars = args[0] if len(args) > 0 else kwargs.get('vars', {})
+    js_vars = args[0] if len(args) > 0 else kwargs.get('vars', {})
     strict = kwargs.get('strict', False)
 
     STRING_QUOTES = '\'"`'
@@ -4523,9 +4523,13 @@ def js_to_json(code, *args, **kwargs):
                 else escape)
 
     def template_substitute(match):
-        evaluated = js_to_json(match.group(1), vars, strict=strict)
+        evaluated = js_to_json(match.group(1), js_vars, strict=strict)
         if evaluated[0] == '"':
+            try:
                 return json.loads(evaluated)
+            except JSONDecodeError:
+                if strict:
+                    raise
         return evaluated
 
     def fix_kv(m):
@@ -4559,14 +4563,14 @@ def js_to_json(code, *args, **kwargs):
                 i = int(im.group(1), base)
                 return ('"%s":' if v.endswith(':') else '%s') % inv(i)
 
-        if v in vars:
+        if v in js_vars:
             try:
                 if not strict:
-                    json.loads(vars[v])
+                    json.loads(js_vars[v])
             except JSONDecodeError:
-                return inv(json.dumps(vars[v]))
+                return inv(json.dumps(js_vars[v]))
             else:
-                return inv(vars[v])
+                return inv(js_vars[v])
 
         if not strict:
             v = try_call(inv, args=(v,), default=v)
@@ -4577,7 +4581,7 @@ def js_to_json(code, *args, **kwargs):
         raise ValueError('Unknown value: ' + v)
 
     def create_map(mobj):
-        return json.dumps(dict(json.loads(js_to_json(mobj.group(1) or '[]', vars=vars))))
+        return json.dumps(dict(json.loads(js_to_json(mobj.group(1) or '[]', vars=js_vars))))
 
     code = re.sub(r'new Map\((\[.*?\])?\)', create_map, code)
     if not strict:
@@ -6715,3 +6719,8 @@ class _UnsafeExtensionError(Exception):
                 raise cls(extension)
 
         return extension
+
+
+def json_stringify(json_data, **kwargs):
+    kwargs.setdefault('separators', (',', ':'))
+    return json.dumps(json_data, **kwargs).decode('utf-8')