test/helper.py

@@ -5,9 +5,9 @@ import hashlib
 import json
 import os.path
 import re
+import types
 import ssl
 import sys
-import types
 import unittest
 
 import youtube_dl.extractor
@@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
             op, _, expected_num = expected.partition(':')
             expected_num = int(expected_num)
             if op == 'mincount':
-                assert_func = self.assertGreaterEqual
+                assert_func = assertGreaterEqual
                 msg_tmpl = 'Expected %d items in field %s, but only got %d'
             elif op == 'maxcount':
-                assert_func = self.assertLessEqual
+                assert_func = assertLessEqual
                 msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
             elif op == 'count':
-                assert_func = self.assertEqual
+                assert_func = assertEqual
                 msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
             else:
                 assert False
             assert_func(
-                len(got), expected_num,
+                self, len(got), expected_num,
                 msg_tmpl % (expected_num, field, len(got)))
             return
         self.assertEqual(
@@ -262,6 +262,27 @@ def assertRegexpMatches(self, text, regexp, msg=None):
             self.assertTrue(m, msg)
 
 
+def assertGreaterEqual(self, got, expected, msg=None):
+    if not (got >= expected):
+        if msg is None:
+            msg = '%r not greater than or equal to %r' % (got, expected)
+        self.assertTrue(got >= expected, msg)
+
+
+def assertLessEqual(self, got, expected, msg=None):
+    if not (got <= expected):
+        if msg is None:
+            msg = '%r not less than or equal to %r' % (got, expected)
+        self.assertTrue(got <= expected, msg)
+
+
+def assertEqual(self, got, expected, msg=None):
+    if not (got == expected):
+        if msg is None:
+            msg = '%r not equal to %r' % (got, expected)
+        self.assertTrue(got == expected, msg)
+
+
 def expect_warnings(ydl, warnings_re):
     real_warning = ydl.report_warning
 

test/test_download.py

@@ -9,6 +9,8 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertGreaterEqual,
+    assertLessEqual,
     expect_warnings,
     get_params,
     gettestcases,
@@ -34,20 +36,12 @@ from youtube_dl.utils import (
     ExtractorError,
     error_to_compat_str,
     format_bytes,
-    IDENTITY,
-    preferredencoding,
     UnavailableVideoError,
 )
 from youtube_dl.extractor import get_info_extractor
 
 RETRIES = 3
 
-# Some unittest APIs require actual str
-if not isinstance('TEST', str):
-    _encode_str = lambda s: s.encode(preferredencoding())
-else:
-    _encode_str = IDENTITY
-
 
 class YoutubeDL(youtube_dl.YoutubeDL):
     def __init__(self, *args, **kwargs):
@@ -108,7 +102,7 @@ def generator(test_case, tname):
 
         def print_skipping(reason):
             print('Skipping %s: %s' % (test_case['name'], reason))
-            self.skipTest(_encode_str(reason))
+            self.skipTest(reason)
 
         if not ie.working():
             print_skipping('IE marked as not _WORKING')
@@ -193,14 +187,16 @@ def generator(test_case, tname):
                 expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
 
             if 'playlist_mincount' in test_case:
-                self.assertGreaterEqual(
+                assertGreaterEqual(
+                    self,
                     len(res_dict['entries']),
                     test_case['playlist_mincount'],
                     'Expected at least %d in playlist %s, but got only %d' % (
                         test_case['playlist_mincount'], test_case['url'],
                         len(res_dict['entries'])))
             if 'playlist_maxcount' in test_case:
-                self.assertLessEqual(
+                assertLessEqual(
+                    self,
                     len(res_dict['entries']),
                     test_case['playlist_maxcount'],
                     'Expected at most %d in playlist %s, but got %d' % (
@@ -247,8 +243,8 @@ def generator(test_case, tname):
                         if params.get('test'):
                             expected_minsize = max(expected_minsize, 10000)
                         got_fsize = os.path.getsize(tc_filename)
-                        self.assertGreaterEqual(
+                        assertGreaterEqual(
-                            got_fsize, expected_minsize,
+                            self, got_fsize, expected_minsize,
                             'Expected %s to be at least %s, but it\'s only %s ' %
                             (tc_filename, format_bytes(expected_minsize),
                                 format_bytes(got_fsize)))

test/test_jsinterp.py

@@ -577,11 +577,9 @@ class TestJSInterpreter(unittest.TestCase):
     def test_unary_operators(self):
         jsi = JSInterpreter('function f(){return 2  -  - - 2;}')
         self.assertEqual(jsi.call_function('f'), 0)
-        jsi = JSInterpreter('function f(){return 2 + - + - - 2;}')
+        # fails
-        self.assertEqual(jsi.call_function('f'), 0)
+        # jsi = JSInterpreter('function f(){return 2 + - + - - 2;}')
-        # https://github.com/ytdl-org/youtube-dl/issues/32815
+        # self.assertEqual(jsi.call_function('f'), 0)
-        jsi = JSInterpreter('function f(){return 0  - 7 * - 6;}')
-        self.assertEqual(jsi.call_function('f'), 42)
 
     """ # fails so far
     def test_packed(self):

test/test_utils.py

@@ -14,11 +14,9 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import io
 import itertools
 import json
-import types
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
-    _UnsafeExtensionError,
     age_restricted,
     args_to_str,
     base_url,
@@ -272,27 +270,6 @@ class TestUtil(unittest.TestCase):
             expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
             '%s/expanded' % compat_getenv('HOME'))
 
-    _uncommon_extensions = [
-        ('exe', 'abc.exe.ext'),
-        ('de', 'abc.de.ext'),
-        ('../.mp4', None),
-        ('..\\.mp4', None),
-    ]
-
-    def assertUnsafeExtension(self, ext=None):
-        assert_raises = self.assertRaises(_UnsafeExtensionError)
-        assert_raises.ext = ext
-        orig_exit = assert_raises.__exit__
-
-        def my_exit(self_, exc_type, exc_val, exc_tb):
-            did_raise = orig_exit(exc_type, exc_val, exc_tb)
-            if did_raise and assert_raises.ext is not None:
-                self.assertEqual(assert_raises.ext, assert_raises.exception.extension, 'Unsafe extension  not as unexpected')
-            return did_raise
-
-        assert_raises.__exit__ = types.MethodType(my_exit, assert_raises)
-        return assert_raises
-
     def test_prepend_extension(self):
         self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
         self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
@@ -301,19 +278,6 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
 
-        # Test uncommon extensions
-        self.assertEqual(prepend_extension('abc.ext', 'bin'), 'abc.bin.ext')
-        for ext, result in self._uncommon_extensions:
-            with self.assertUnsafeExtension(ext):
-                prepend_extension('abc', ext)
-            if result:
-                self.assertEqual(prepend_extension('abc.ext', ext, 'ext'), result)
-            else:
-                with self.assertUnsafeExtension(ext):
-                    prepend_extension('abc.ext', ext, 'ext')
-            with self.assertUnsafeExtension(ext):
-                prepend_extension('abc.unexpected_ext', ext, 'ext')
-
     def test_replace_extension(self):
         self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
         self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
@@ -322,16 +286,6 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
         self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
 
-        # Test uncommon extensions
-        self.assertEqual(replace_extension('abc.ext', 'bin'), 'abc.unknown_video')
-        for ext, _ in self._uncommon_extensions:
-            with self.assertUnsafeExtension(ext):
-                replace_extension('abc', ext)
-            with self.assertUnsafeExtension(ext):
-                replace_extension('abc.ext', ext, 'ext')
-            with self.assertUnsafeExtension(ext):
-                replace_extension('abc.unexpected_ext', ext, 'ext')
-
     def test_subtitles_filename(self):
         self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
         self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')

test/test_youtube_signature.py

@@ -158,10 +158,6 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
         '_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ',
     ),
-    (
-        'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
-        '1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
-    ),
 ]
 
 

youtube_dl/YoutubeDL.py

@@ -7,7 +7,6 @@ import collections
 import copy
 import datetime
 import errno
-import functools
 import io
 import itertools
 import json
@@ -54,7 +53,6 @@ from .compat import (
     compat_urllib_request_DataHandler,
 )
 from .utils import (
-    _UnsafeExtensionError,
     age_restricted,
     args_to_str,
     bug_reports_message,
@@ -131,20 +129,6 @@ if compat_os_name == 'nt':
     import ctypes
 
 
-def _catch_unsafe_file_extension(func):
-    @functools.wraps(func)
-    def wrapper(self, *args, **kwargs):
-        try:
-            return func(self, *args, **kwargs)
-        except _UnsafeExtensionError as error:
-            self.report_error(
-                '{0} found; to avoid damaging your system, this value is disallowed.'
-                ' If you believe this is an error{1}').format(
-                    error.message, bug_reports_message(','))
-
-    return wrapper
-
-
 class YoutubeDL(object):
     """YoutubeDL class.
 
@@ -1055,8 +1039,8 @@ class YoutubeDL(object):
         elif result_type in ('playlist', 'multi_video'):
             # Protect from infinite recursion due to recursively nested playlists
             # (see https://github.com/ytdl-org/youtube-dl/issues/27833)
-            webpage_url = ie_result.get('webpage_url')  # not all pl/mv have this
+            webpage_url = ie_result['webpage_url']
-            if webpage_url and webpage_url in self._playlist_urls:
+            if webpage_url in self._playlist_urls:
                 self.to_screen(
                     '[download] Skipping already downloaded playlist: %s'
                     % ie_result.get('title') or ie_result.get('id'))
@@ -1064,10 +1048,6 @@ class YoutubeDL(object):
 
             self._playlist_level += 1
             self._playlist_urls.add(webpage_url)
-            new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
-            if new_result:
-                new_result.update(ie_result)
-                ie_result = new_result
             try:
                 return self.__process_playlist(ie_result, download)
             finally:
@@ -1613,28 +1593,6 @@ class YoutubeDL(object):
         self.cookiejar.add_cookie_header(pr)
         return pr.get_header('Cookie')
 
-    def _fill_common_fields(self, info_dict, final=True):
-
-        for ts_key, date_key in (
-                ('timestamp', 'upload_date'),
-                ('release_timestamp', 'release_date'),
-        ):
-            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
-                # Working around out-of-range timestamp values (e.g. negative ones on Windows,
-                # see http://bugs.python.org/issue1646728)
-                try:
-                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
-                    info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
-                except (ValueError, OverflowError, OSError):
-                    pass
-
-        # Auto generate title fields corresponding to the *_number fields when missing
-        # in order to always have clean titles. This is very common for TV series.
-        if final:
-            for field in ('chapter', 'season', 'episode'):
-                if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
-                    info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
-
     def process_video_result(self, info_dict, download=True):
         assert info_dict.get('_type', 'video') == 'video'
 
@@ -1702,7 +1660,24 @@ class YoutubeDL(object):
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
-        self._fill_common_fields(info_dict)
+        for ts_key, date_key in (
+                ('timestamp', 'upload_date'),
+                ('release_timestamp', 'release_date'),
+        ):
+            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
+                # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+                # see http://bugs.python.org/issue1646728)
+                try:
+                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
+                    info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
+                except (ValueError, OverflowError, OSError):
+                    pass
+
+        # Auto generate title fields corresponding to the *_number fields when missing
+        # in order to always have clean titles. This is very common for TV series.
+        for field in ('chapter', 'season', 'episode'):
+            if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
+                info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
 
         for cc_kind in ('subtitles', 'automatic_captions'):
             cc = info_dict.get(cc_kind)
@@ -1941,7 +1916,6 @@ class YoutubeDL(object):
         if self.params.get('forcejson', False):
             self.to_stdout(json.dumps(self.sanitize_info(info_dict)))
 
-    @_catch_unsafe_file_extension
     def process_info(self, info_dict):
         """Process a single resolved IE result."""
 

youtube_dl/__init__.py

@@ -21,7 +21,6 @@ from .compat import (
     workaround_optparse_bug9161,
 )
 from .utils import (
-    _UnsafeExtensionError,
     DateRange,
     decodeOption,
     DEFAULT_OUTTMPL,
@@ -174,9 +173,6 @@ def _real_main(argv=None):
     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 
-    if opts.no_check_extensions:
-        _UnsafeExtensionError.lenient = True
-
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
             parsed_retries = float('inf')

youtube_dl/extractor/common.py

@@ -3033,6 +3033,7 @@ class InfoExtractor(object):
             transform_source=transform_source, default=None)
 
     def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
+
         # allow passing `transform_source` through to _find_jwplayer_data()
         transform_source = kwargs.pop('transform_source', None)
         kwfind = compat_kwargs({'transform_source': transform_source}) if transform_source else {}

youtube_dl/extractor/extractors.py

@@ -898,13 +898,21 @@ from .ooyala import (
 )
 from .ora import OraTVIE
 from .orf import (
-    ORFONIE,
+    ORFTVthekIE,
-    ORFONLiveIE,
+    ORFFM4IE,
     ORFFM4StoryIE,
+    ORFOE1IE,
+    ORFOE3IE,
+    ORFNOEIE,
+    ORFWIEIE,
+    ORFBGLIE,
+    ORFOOEIE,
+    ORFSTMIE,
+    ORFKTNIE,
+    ORFSBGIE,
+    ORFTIRIE,
+    ORFVBGIE,
     ORFIPTVIE,
-    ORFPodcastIE,
-    ORFRadioIE,
-    ORFRadioCollectionIE,
 )
 from .outsidetv import OutsideTVIE
 from .packtpub import (

youtube_dl/extractor/mixcloud.py

@@ -1,4 +1,3 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools
@@ -11,7 +10,7 @@ from ..compat import (
     compat_ord,
     compat_str,
     compat_urllib_parse_unquote,
-    compat_zip as zip,
+    compat_zip
 )
 from ..utils import (
     int_or_none,
@@ -25,7 +24,7 @@ class MixcloudBaseIE(InfoExtractor):
     def _call_api(self, object_type, object_fields, display_id, username, slug=None):
         lookup_key = object_type + 'Lookup'
         return self._download_json(
-            'https://app.mixcloud.com/graphql', display_id, query={
+            'https://www.mixcloud.com/graphql', display_id, query={
                 'query': '''{
   %s(lookup: {username: "%s"%s}) {
     %s
@@ -45,7 +44,7 @@ class MixcloudIE(MixcloudBaseIE):
             'ext': 'm4a',
             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
-            'uploader': 'dholbach',  # was: 'Daniel Holbach',
+            'uploader': 'Daniel Holbach',
             'uploader_id': 'dholbach',
             'thumbnail': r're:https?://.*\.jpg',
             'view_count': int,
@@ -58,7 +57,7 @@ class MixcloudIE(MixcloudBaseIE):
             'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
             'ext': 'mp3',
             'title': 'Caribou 7 inch Vinyl Mix & Chat',
-            'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
+            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
             'uploader': 'Gilles Peterson Worldwide',
             'uploader_id': 'gillespeterson',
             'thumbnail': 're:https?://.*',
@@ -66,23 +65,6 @@ class MixcloudIE(MixcloudBaseIE):
             'timestamp': 1422987057,
             'upload_date': '20150203',
         },
-        'params': {
-            'skip_download': '404 not found',
-        },
-    }, {
-        'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
-        'info_dict': {
-            'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
-            'ext': 'm4a',
-            'title': 'Carnival Música Popular Brasileira Mix',
-            'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
-            'timestamp': 1454347174,
-            'upload_date': '20160201',
-            'uploader': 'Gilles Peterson Worldwide',
-            'uploader_id': 'gillespeterson',
-            'thumbnail': 're:https?://.*',
-            'view_count': int,
-        },
     }, {
         'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
         'only_matching': True,
@@ -94,10 +76,10 @@ class MixcloudIE(MixcloudBaseIE):
         """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
         return ''.join([
             compat_chr(compat_ord(ch) ^ compat_ord(k))
-            for ch, k in zip(ciphertext, itertools.cycle(key))])
+            for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
 
     def _real_extract(self, url):
-        username, slug = self._match_valid_url(url).groups()
+        username, slug = re.match(self._VALID_URL, url).groups()
         username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
         track_id = '%s_%s' % (username, slug)
 

youtube_dl/extractor/palcomp3.py

@@ -8,7 +8,7 @@ from ..compat import compat_str
 from ..utils import (
     int_or_none,
     str_or_none,
-    traverse_obj,
+    try_get,
 )
 
 
@@ -118,8 +118,7 @@ class PalcoMP3ArtistIE(PalcoMP3BaseIE):
         artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
 
         def entries():
-            for music in traverse_obj(artist, (
+            for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
-                    'musics', 'nodes', lambda _, m: m['musicID'])):
                 yield self._parse_music(music)
 
         return self.playlist_result(
@@ -138,7 +137,7 @@ class PalcoMP3VideoIE(PalcoMP3BaseIE):
             'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
             'description': 'md5:7043342c09a224598e93546e98e49282',
             'upload_date': '20161107',
-            'uploader_id': '@maiaramaraisaoficial',
+            'uploader_id': 'maiaramaraisaoficial',
             'uploader': 'Maiara e Maraisa',
         }
     }]

youtube_dl/extractor/vidlii.py

@@ -4,7 +4,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-
 from ..utils import (
     float_or_none,
     get_element_by_id,
@@ -12,7 +11,6 @@ from ..utils import (
     strip_or_none,
     unified_strdate,
     urljoin,
-    str_to_int,
 )
 
 
@@ -37,26 +35,6 @@ class VidLiiIE(InfoExtractor):
             'categories': ['News & Politics'],
             'tags': ['Vidlii', 'Jan', 'Videogames'],
         }
-    }, {
-        # HD
-        'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
-        'md5': '450e7da379c884788c3a4fa02a3ce1a4',
-        'info_dict': {
-            'id': '2Ng8Abj2Fkl',
-            'ext': 'mp4',
-            'title': 'test',
-            'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
-            'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
-            'uploader': 'VidLii',
-            'uploader_url': 'https://www.vidlii.com/user/VidLii',
-            'upload_date': '20200927',
-            'duration': 5,
-            'view_count': int,
-            'comment_count': int,
-            'average_rating': float,
-            'categories': ['Film & Animation'],
-            'tags': list,
-        },
     }, {
         'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
         'only_matching': True,
@@ -68,32 +46,11 @@ class VidLiiIE(InfoExtractor):
         webpage = self._download_webpage(
             'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
 
-        formats = []
+        video_url = self._search_regex(
+            r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
+            'video url', group='url')
 
-        def add_format(format_url, height=None):
+        title = self._search_regex(
-            height = int(self._search_regex(r'(\d+)\.mp4',
-                         format_url, 'height', default=360))
-
-            formats.append({
-                'url': format_url,
-                'format_id': '%dp' % height if height else None,
-                'height': height,
-            })
-
-        sources = re.findall(
-            r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
-            webpage)
-
-        formats = []
-        if len(sources) > 1:
-            add_format(sources[1][1])
-            self._check_formats(formats, video_id)
-        if len(sources) > 0:
-            add_format(sources[0][1])
-
-        self._sort_formats(formats)
-
-        title = self._html_search_regex(
             (r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
             'title')
 
@@ -125,9 +82,9 @@ class VidLiiIE(InfoExtractor):
             default=None) or self._search_regex(
             r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
 
-        view_count = str_to_int(self._html_search_regex(
+        view_count = int_or_none(self._search_regex(
-            (r'<strong>([\d,.]+)</strong> views',
+            (r'<strong>(\d+)</strong> views',
-             r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
+             r'Views\s*:\s*<strong>(\d+)</strong>'),
             webpage, 'view count', fatal=False))
 
         comment_count = int_or_none(self._search_regex(
@@ -152,7 +109,7 @@ class VidLiiIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'formats': formats,
+            'url': video_url,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

youtube_dl/jsinterp.py

@@ -14,7 +14,6 @@ from .utils import (
     remove_quotes,
     unified_timestamp,
     variadic,
-    write_string,
 )
 from .compat import (
     compat_basestring,
@@ -54,16 +53,15 @@ def wraps_op(op):
 
 # NB In principle NaN cannot be checked by membership.
 # Here all NaN values are actually this one, so _NaN is _NaN,
-# although _NaN != _NaN. Ditto Infinity.
+# although _NaN != _NaN.
 
 _NaN = float('nan')
-_Infinity = float('inf')
 
 
 def _js_bit_op(op):
 
     def zeroise(x):
-        return 0 if x in (None, JS_Undefined, _NaN, _Infinity) else x
+        return 0 if x in (None, JS_Undefined, _NaN) else x
 
     @wraps_op(op)
     def wrapped(a, b):
@@ -86,7 +84,7 @@ def _js_arith_op(op):
 def _js_div(a, b):
     if JS_Undefined in (a, b) or not (a or b):
         return _NaN
-    return operator.truediv(a or 0, b) if b else _Infinity
+    return operator.truediv(a or 0, b) if b else float('inf')
 
 
 def _js_mod(a, b):
@@ -222,42 +220,6 @@ class LocalNameSpace(ChainMap):
         return 'LocalNameSpace%s' % (self.maps, )
 
 
-class Debugger(object):
-    ENABLED = False
-
-    @staticmethod
-    def write(*args, **kwargs):
-        level = kwargs.get('level', 100)
-
-        def truncate_string(s, left, right=0):
-            if s is None or len(s) <= left + right:
-                return s
-            return '...'.join((s[:left - 3], s[-right:] if right else ''))
-
-        write_string('[debug] JS: {0}{1}\n'.format(
-            '  ' * (100 - level),
-            ' '.join(truncate_string(compat_str(x), 50, 50) for x in args)))
-
-    @classmethod
-    def wrap_interpreter(cls, f):
-        def interpret_statement(self, stmt, local_vars, allow_recursion, *args, **kwargs):
-            if cls.ENABLED and stmt.strip():
-                cls.write(stmt, level=allow_recursion)
-            try:
-                ret, should_ret = f(self, stmt, local_vars, allow_recursion, *args, **kwargs)
-            except Exception as e:
-                if cls.ENABLED:
-                    if isinstance(e, ExtractorError):
-                        e = e.orig_msg
-                    cls.write('=> Raises:', e, '<-|', stmt, level=allow_recursion)
-                raise
-            if cls.ENABLED and stmt.strip():
-                if should_ret or not repr(ret) == stmt:
-                    cls.write(['->', '=>'][should_ret], repr(ret), '<-|', stmt, level=allow_recursion)
-            return ret, should_ret
-        return interpret_statement
-
-
 class JSInterpreter(object):
     __named_object_counter = 0
 
@@ -345,7 +307,8 @@ class JSInterpreter(object):
     def __op_chars(cls):
         op_chars = set(';,[')
         for op in cls._all_operators():
-            op_chars.update(op[0])
+            for c in op[0]:
+                op_chars.add(c)
         return op_chars
 
     def _named_object(self, namespace, obj):
@@ -363,8 +326,9 @@ class JSInterpreter(object):
         # collections.Counter() is ~10% slower in both 2.7 and 3.9
         counters = dict((k, 0) for k in _MATCHING_PARENS.values())
         start, splits, pos, delim_len = 0, 0, 0, len(delim) - 1
-        in_quote, escaping, after_op, in_regex_char_group = None, False, True, False
+        in_quote, escaping, skipping = None, False, 0
-        skipping = 0
+        after_op, in_regex_char_group = True, False
+
         for idx, char in enumerate(expr):
             paren_delta = 0
             if not in_quote:
@@ -418,12 +382,10 @@ class JSInterpreter(object):
         return separated[0][1:].strip(), separated[1].strip()
 
     @staticmethod
-    def _all_operators(_cached=[]):
+    def _all_operators():
-        if not _cached:
+        return itertools.chain(
-            _cached.extend(itertools.chain(
             # Ref: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Operator_Precedence
-                _SC_OPERATORS, _LOG_OPERATORS, _COMP_OPERATORS, _OPERATORS))
+            _SC_OPERATORS, _LOG_OPERATORS, _COMP_OPERATORS, _OPERATORS)
-        return _cached
 
     def _operator(self, op, left_val, right_expr, expr, local_vars, allow_recursion):
         if op in ('||', '&&'):
@@ -454,7 +416,7 @@ class JSInterpreter(object):
         except Exception as e:
             if allow_undefined:
                 return JS_Undefined
-            raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
+            raise self.Exception('Cannot get index {idx:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
         try:
@@ -476,7 +438,6 @@ class JSInterpreter(object):
     _FINALLY_RE = re.compile(r'finally\s*\{')
     _SWITCH_RE = re.compile(r'switch\s*\(')
 
-    @Debugger.wrap_interpreter
     def interpret_statement(self, stmt, local_vars, allow_recursion=100):
         if allow_recursion < 0:
             raise self.Exception('Recursion limit reached')
@@ -550,6 +511,7 @@ class JSInterpreter(object):
                 expr = self._dump(inner, local_vars) + outer
 
         if expr.startswith('('):
+
             m = re.match(r'\((?P<d>[a-z])%(?P<e>[a-z])\.length\+(?P=e)\.length\)%(?P=e)\.length', expr)
             if m:
                 # short-cut eval of frequently used `(d%e.length+e.length)%e.length`, worth ~6% on `pytest -k test_nsig`
@@ -731,7 +693,7 @@ class JSInterpreter(object):
                 (?P<op>{_OPERATOR_RE})?
                 =(?!=)(?P<expr>.*)$
             )|(?P<return>
-                (?!if|return|true|false|null|undefined|NaN|Infinity)(?P<name>{_NAME_RE})$
+                (?!if|return|true|false|null|undefined)(?P<name>{_NAME_RE})$
             )|(?P<indexing>
                 (?P<in>{_NAME_RE})\[(?P<idx>.+)\]$
             )|(?P<attribute>
@@ -765,12 +727,11 @@ class JSInterpreter(object):
             raise JS_Break()
         elif expr == 'continue':
             raise JS_Continue()
+
         elif expr == 'undefined':
             return JS_Undefined, should_return
         elif expr == 'NaN':
             return _NaN, should_return
-        elif expr == 'Infinity':
-            return _Infinity, should_return
 
         elif md.get('return'):
             return local_vars[m.group('name')], should_return
@@ -799,27 +760,17 @@ class JSInterpreter(object):
             right_expr = separated.pop()
             # handle operators that are both unary and binary, minimal BODMAS
             if op in ('+', '-'):
-                # simplify/adjust consecutive instances of these operators
                 undone = 0
                 while len(separated) > 1 and not separated[-1].strip():
                     undone += 1
                     separated.pop()
                 if op == '-' and undone % 2 != 0:
                     right_expr = op + right_expr
-                elif op == '+':
-                    while len(separated) > 1 and separated[-1].strip() in self.OP_CHARS:
-                        right_expr = separated.pop() + right_expr
-                # hanging op at end of left => unary + (strip) or - (push right)
                 left_val = separated[-1]
                 for dm_op in ('*', '%', '/', '**'):
                     bodmas = tuple(self._separate(left_val, dm_op, skip_delims=skip_delim))
                     if len(bodmas) > 1 and not bodmas[-1].strip():
                         expr = op.join(separated) + op + right_expr
-                        if len(separated) > 1:
-                            separated.pop()
-                            right_expr = op.join((left_val, right_expr))
-                        else:
-                            separated = [op.join((left_val, right_expr))]
                         right_expr = None
                         break
                 if right_expr is None:
@@ -846,8 +797,6 @@ class JSInterpreter(object):
 
             def eval_method():
                 if (variable, member) == ('console', 'debug'):
-                    if Debugger.ENABLED:
-                        Debugger.write(self.interpret_expression('[{}]'.format(arg_str), local_vars, allow_recursion))
                     return
                 types = {
                     'String': compat_str,

youtube_dl/options.py

@@ -533,10 +533,6 @@ def parseOpts(overrideArguments=None):
         '--no-check-certificate',
         action='store_true', dest='no_check_certificate', default=False,
         help='Suppress HTTPS certificate validation')
-    workarounds.add_option(
-        '--no-check-extensions',
-        action='store_true', dest='no_check_extensions', default=False,
-        help='Suppress file extension validation')
     workarounds.add_option(
         '--prefer-insecure',
         '--prefer-unsecure', action='store_true', dest='prefer_insecure',

youtube_dl/utils.py

@@ -1717,6 +1717,21 @@ TIMEZONE_NAMES = {
     'PST': -8, 'PDT': -7   # Pacific
 }
 
+KNOWN_EXTENSIONS = (
+    'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
+    'flv', 'f4v', 'f4a', 'f4b',
+    'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
+    'mkv', 'mka', 'mk3d',
+    'avi', 'divx',
+    'mov',
+    'asf', 'wmv', 'wma',
+    '3gp', '3g2',
+    'mp3',
+    'flac',
+    'ape',
+    'wav',
+    'f4f', 'f4m', 'm3u8', 'smil')
+
 # needed for sanitizing filenames in restricted mode
 ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
                         itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
@@ -2391,7 +2406,7 @@ class ExtractorError(YoutubeDLError):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
         """
-        self.orig_msg = msg
+
         if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
             expected = True
         if video_id is not None:
@@ -3944,22 +3959,19 @@ def parse_duration(s):
     return duration
 
 
-def _change_extension(prepend, filename, ext, expected_real_ext=None):
+def prepend_extension(filename, ext, expected_real_ext=None):
     name, real_ext = os.path.splitext(filename)
-    sanitize_extension = _UnsafeExtensionError.sanitize_extension
+    return (
-
+        '{0}.{1}{2}'.format(name, ext, real_ext)
-    if not expected_real_ext or real_ext.partition('.')[0::2] == ('', expected_real_ext):
+        if not expected_real_ext or real_ext[1:] == expected_real_ext
-        filename = name
+        else '{0}.{1}'.format(filename, ext))
-        if prepend and real_ext:
-            sanitize_extension(ext, prepend=prepend)
-            return ''.join((filename, '.', ext, real_ext))
-
-    # Mitigate path traversal and file impersonation attacks
-    return '.'.join((filename, sanitize_extension(ext)))
 
 
-prepend_extension = functools.partial(_change_extension, True)
+def replace_extension(filename, ext, expected_real_ext=None):
-replace_extension = functools.partial(_change_extension, False)
+    name, real_ext = os.path.splitext(filename)
+    return '{0}.{1}'.format(
+        name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
+        ext)
 
 
 def check_executable(exe, args=[]):
@@ -6549,138 +6561,3 @@ def join_nonempty(*values, **kwargs):
     if from_dict is not None:
         values = (traverse_obj(from_dict, variadic(v)) for v in values)
     return delim.join(map(compat_str, filter(None, values)))
-
-
-class Namespace(object):
-    """Immutable namespace"""
-
-    def __init__(self, **kw_attr):
-        self.__dict__.update(kw_attr)
-
-    def __iter__(self):
-        return iter(self.__dict__.values())
-
-    @property
-    def items_(self):
-        return self.__dict__.items()
-
-
-MEDIA_EXTENSIONS = Namespace(
-    common_video=('avi', 'flv', 'mkv', 'mov', 'mp4', 'webm'),
-    video=('3g2', '3gp', 'f4v', 'mk3d', 'divx', 'mpg', 'ogv', 'm4v', 'wmv'),
-    common_audio=('aiff', 'alac', 'flac', 'm4a', 'mka', 'mp3', 'ogg', 'opus', 'wav'),
-    audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4p', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma', 'weba'),
-    thumbnails=('jpg', 'png', 'webp'),
-    # storyboards=('mhtml', ),
-    subtitles=('srt', 'vtt', 'ass', 'lrc', 'ttml'),
-    manifests=('f4f', 'f4m', 'm3u8', 'smil', 'mpd'),
-)
-MEDIA_EXTENSIONS.video = MEDIA_EXTENSIONS.common_video + MEDIA_EXTENSIONS.video
-MEDIA_EXTENSIONS.audio = MEDIA_EXTENSIONS.common_audio + MEDIA_EXTENSIONS.audio
-
-KNOWN_EXTENSIONS = (
-    MEDIA_EXTENSIONS.video + MEDIA_EXTENSIONS.audio
-    + MEDIA_EXTENSIONS.manifests
-)
-
-
-class _UnsafeExtensionError(Exception):
-    """
-    Mitigation exception for unwanted file overwrite/path traversal
-
-    Ref: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j
-    """
-    _ALLOWED_EXTENSIONS = frozenset(itertools.chain(
-        (   # internal
-            'description',
-            'json',
-            'meta',
-            'orig',
-            'part',
-            'temp',
-            'uncut',
-            'unknown_video',
-            'ytdl',
-        ),
-        # video
-        MEDIA_EXTENSIONS.video, (
-            'avif',
-            'ismv',
-            'm2ts',
-            'm4s',
-            'mng',
-            'mpeg',
-            'qt',
-            'swf',
-            'ts',
-            'vp9',
-            'wvm',
-        ),
-        # audio
-        MEDIA_EXTENSIONS.audio, (
-            'isma',
-            'mid',
-            'mpga',
-            'ra',
-        ),
-        # image
-        MEDIA_EXTENSIONS.thumbnails, (
-            'bmp',
-            'gif',
-            'ico',
-            'heic',
-            'jng',
-            'jpeg',
-            'jxl',
-            'svg',
-            'tif',
-            'wbmp',
-        ),
-        # subtitle
-        MEDIA_EXTENSIONS.subtitles, (
-            'dfxp',
-            'fs',
-            'ismt',
-            'sami',
-            'scc',
-            'ssa',
-            'tt',
-        ),
-        # others
-        MEDIA_EXTENSIONS.manifests,
-        (
-            # not used in yt-dl
-            # *MEDIA_EXTENSIONS.storyboards,
-            # 'desktop',
-            # 'ism',
-            # 'm3u',
-            # 'sbv',
-            # 'swp',
-            # 'url',
-            # 'webloc',
-            # 'xml',
-        )))
-
-    def __init__(self, extension):
-        super(_UnsafeExtensionError, self).__init__('unsafe file extension: {0!r}'.format(extension))
-        self.extension = extension
-
-    # support --no-check-extensions
-    lenient = False
-
-    @classmethod
-    def sanitize_extension(cls, extension, **kwargs):
-        # ... /, *, prepend=False
-        prepend = kwargs.get('prepend', False)
-
-        if '/' in extension or '\\' in extension:
-            raise cls(extension)
-
-        if not prepend:
-            last = extension.rpartition('.')[-1]
-            if last == 'bin':
-                extension = last = 'unknown_video'
-            if not (cls.lenient or last.lower() in cls._ALLOWED_EXTENSIONS):
-                raise cls(extension)
-
-        return extension