Merge 8d2170c713253c02eee11d3b1822a6dd808545fc into 673277e510ebd996b62a2fcc76169bf3cce29910

* [YouTube] Extract playlist items from LOCKUP_VIEW_MODEL_...
* resolves #33073
* thx seproDev (yt-dlp/yt-dlp#11615)

Co-authored-by: sepro <sepro@sepr0.com>

test/test_jsinterp.py

@@ -459,6 +459,10 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return undefined >> 5}', 0)
         self._test('function f(){return 42 << NaN}', 42)
         self._test('function f(){return 42 << Infinity}', 42)
+        self._test('function f(){return 0.0 << null}', 0)
+        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)
 
     def test_negative(self):
         self._test('function f(){return 2    *    -2.0    ;}', -4)

test/test_youtube_signature.py

@@ -219,6 +219,10 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
         'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
     ),
+    (
+        'https://www.youtube.com/s/player/9c6dfc4a/player_ias.vflset/en_US/base.js',
+        'jbu7ylIosQHyJyJV', 'uwI0ESiynAmhNg',
+    ),
 ]
 
 

youtube_dl/casefold.py

@@ -10,9 +10,10 @@ from .compat import (
 # https://github.com/unicode-org/icu/blob/main/icu4c/source/data/unidata/CaseFolding.txt
 # In case newly foldable Unicode characters are defined, paste the new version
 # of the text inside the ''' marks.
-# The text is expected to have only blank lines andlines with 1st character #,
+# The text is expected to have only blank lines and lines with 1st character #,
 # all ignored, and fold definitions like this:
-# `from_hex_code; space_separated_to_hex_code_list; comment`
+# `from_hex_code; status; space_separated_to_hex_code_list; comment`
+# Only `status` C/F are used.
 
 _map_str = '''
 # CaseFolding-15.0.0.txt
@@ -1657,11 +1658,6 @@ _map = dict(
 del _map_str
 
 
-def casefold(s):
+def _casefold(s):
     assert isinstance(s, compat_str)
     return ''.join((_map.get(c, c) for c in s))
-
-
-__all__ = [
-    'casefold',
-]

youtube_dl/compat.py

@@ -44,7 +44,7 @@ try:
     compat_str.casefold
     compat_casefold = lambda s: s.casefold()
 except AttributeError:
-    from .casefold import casefold as compat_casefold
+    from .casefold import _casefold as compat_casefold
 
 try:
     import collections.abc as compat_collections_abc
@@ -3116,17 +3116,21 @@ else:
     compat_kwargs = lambda kwargs: kwargs
 
 
+# compat_numeric_types
 try:
     compat_numeric_types = (int, float, long, complex)
 except NameError:  # Python 3
     compat_numeric_types = (int, float, complex)
 
 
+# compat_integer_types
 try:
     compat_integer_types = (int, long)
 except NameError:  # Python 3
     compat_integer_types = (int, )
 
+# compat_int
+compat_int = compat_integer_types[-1]
 
 if sys.version_info < (2, 7):
     def compat_socket_create_connection(address, timeout, source_address=None):
@@ -3532,6 +3536,7 @@ __all__ = [
     'compat_http_client',
     'compat_http_server',
     'compat_input',
+    'compat_int',
     'compat_integer_types',
     'compat_itertools_count',
     'compat_itertools_zip_longest',

youtube_dl/extractor/youtube.py

@@ -27,6 +27,7 @@ from ..compat import (
 )
 from ..jsinterp import JSInterpreter
 from ..utils import (
+    bug_reports_message,
     clean_html,
     dict_get,
     error_to_compat_str,
@@ -65,6 +66,7 @@ from ..utils import (
     url_or_none,
     urlencode_postdata,
     urljoin,
+    variadic,
 )
 
 
@@ -460,6 +462,26 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'uploader': uploader,
         }
 
+    @staticmethod
+    def _extract_thumbnails(data, *path_list, **kw_final_key):
+        """
+        Extract thumbnails from thumbnails dict
+        @param path_list: path list to level that contains 'thumbnails' key
+        """
+        final_key = kw_final_key.get('final_key', 'thumbnails')
+
+        return traverse_obj(data, ((
+            tuple(variadic(path) + (final_key, Ellipsis)
+                  for path in path_list or [()])), {
+            'url': ('url', T(url_or_none),
+                    # Sometimes youtube gives a wrong thumbnail URL. See:
+                    # https://github.com/yt-dlp/yt-dlp/issues/233
+                    # https://github.com/ytdl-org/youtube-dl/issues/28023
+                    T(lambda u: update_url(u, query=None) if u and 'maxresdefault' in u else u)),
+            'height': ('height', T(int_or_none)),
+            'width': ('width', T(int_or_none)),
+        }, T(lambda t: t if t.get('url') else None)))
+
     def _search_results(self, query, params):
         data = {
             'context': {
@@ -3183,8 +3205,12 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             expected_type=txt_or_none)
 
     def _grid_entries(self, grid_renderer):
-        for item in grid_renderer['items']:
-            if not isinstance(item, dict):
+        for item in traverse_obj(grid_renderer, ('items', Ellipsis, T(dict))):
+            lockup_view_model = traverse_obj(item, ('lockupViewModel', T(dict)))
+            if lockup_view_model:
+                entry = self._extract_lockup_view_model(lockup_view_model)
+                if entry:
+                    yield entry
                 continue
             renderer = self._extract_grid_item_renderer(item)
             if not isinstance(renderer, dict):
@@ -3268,6 +3294,25 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 continue
             yield self._extract_video(renderer)
 
+    def _extract_lockup_view_model(self, view_model):
+        content_id = view_model.get('contentId')
+        if not content_id:
+            return
+        content_type = view_model.get('contentType')
+        if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'):
+            self.report_warning(
+                'Unsupported lockup view model content type "{0}"{1}'.format(content_type, bug_reports_message()), only_once=True)
+            return
+        return merge_dicts(self.url_result(
+            update_url_query('https://www.youtube.com/playlist', {'list': content_id}),
+            ie=YoutubeTabIE.ie_key(), video_id=content_id), {
+                'title': traverse_obj(view_model, (
+                    'metadata', 'lockupMetadataViewModel', 'title', 'content', T(compat_str))),
+                'thumbnails': self._extract_thumbnails(view_model, (
+                    'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail',
+                    'thumbnailViewModel', 'image'), final_key='sources'),
+        })
+
     def _video_entry(self, video_renderer):
         video_id = video_renderer.get('videoId')
         if video_id:

youtube_dl/jsinterp.py

@@ -24,6 +24,8 @@ from .compat import (
     compat_collections_chain_map as ChainMap,
     compat_contextlib_suppress,
     compat_filter as filter,
+    compat_int,
+    compat_integer_types,
     compat_itertools_zip_longest as zip_longest,
     compat_map as map,
     compat_numeric_types,
@@ -70,14 +72,27 @@ class JS_Undefined(object):
     pass
 
 
-def _js_bit_op(op):
+def _js_bit_op(op, is_shift=False):
 
-    def zeroise(x):
-        return 0 if x in (None, JS_Undefined, _NaN, _Infinity) else x
+    def zeroise(x, is_shift_arg=False):
+        if isinstance(x, compat_integer_types):
+            return (x % 32) if is_shift_arg else (x & 0xffffffff)
+        try:
+            x = float(x)
+            if is_shift_arg:
+                x = int(x % 32)
+            elif x < 0:
+                x = -compat_int(-x % 0xffffffff)
+            else:
+                x = compat_int(x % 0xffffffff)
+        except (ValueError, TypeError):
+            # also here for int(NaN), including float('inf') % 32
+            x = 0
+        return x
 
     @wraps_op(op)
     def wrapped(a, b):
-        return op(zeroise(a), zeroise(b)) & 0xffffffff
+        return op(zeroise(a), zeroise(b, is_shift)) & 0xffffffff
 
     return wrapped
 
@@ -253,8 +268,8 @@ def _js_typeof(expr):
 # avoid dict to maintain order
 # definition None => Defined in JSInterpreter._operator
 _OPERATORS = (
-    ('>>', _js_bit_op(operator.rshift)),
-    ('<<', _js_bit_op(operator.lshift)),
+    ('>>', _js_bit_op(operator.rshift, True)),
+    ('<<', _js_bit_op(operator.lshift, True)),
     ('+', _js_add),
     ('-', _js_arith_op(operator.sub)),
     ('*', _js_arith_op(operator.mul)),