Merge 2833a38215 into e0727e4ab6

Fixes 21792b88b7 (commitcomment-140705274), thx: vonProteus

test/test_downloader_external.py

@@ -18,6 +18,7 @@ from test.helper import (
 )
 from youtube_dl import YoutubeDL
 from youtube_dl.compat import (
+    compat_contextlib_suppress,
     compat_http_cookiejar_Cookie,
     compat_http_server,
     compat_kwargs,
@@ -35,6 +36,9 @@ from youtube_dl.downloader.external import (
     HttpieFD,
     WgetFD,
 )
+from youtube_dl.postprocessor import (
+    FFmpegPostProcessor,
+)
 import threading
 
 TEST_SIZE = 10 * 1024
@@ -227,7 +231,17 @@ class TestAria2cFD(unittest.TestCase):
             self.assertIn('--load-cookies=%s' % downloader._cookies_tempfile, cmd)
 
 
-@ifExternalFDAvailable(FFmpegFD)
+# Handle delegated availability
+def ifFFmpegFDAvailable(externalFD):
+    # raise SkipTest, or set False!
+    avail = ifExternalFDAvailable(externalFD) and False
+    with compat_contextlib_suppress(Exception):
+        avail = FFmpegPostProcessor(downloader=None).available
+    return unittest.skipUnless(
+        avail, externalFD.get_basename() + ' not found')
+
+
+@ifFFmpegFDAvailable(FFmpegFD)
 class TestFFmpegFD(unittest.TestCase):
     _args = []
 

test/test_utils.py

@@ -81,6 +81,7 @@ from youtube_dl.utils import (
     sanitize_filename,
     sanitize_path,
     sanitize_url,
+    sanitized_Request,
     shell_quote,
     smuggle_url,
     str_or_none,
@@ -255,6 +256,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
         self.assertEqual(sanitize_url('foo bar'), 'foo bar')
 
+    def test_sanitized_Request(self):
+        self.assertFalse(sanitized_Request('http://foo.bar').has_header('Authorization'))
+        self.assertFalse(sanitized_Request('http://:foo.bar').has_header('Authorization'))
+        self.assertEqual(sanitized_Request('http://@foo.bar').get_header('Authorization'),
+                         'Basic Og==')
+        self.assertEqual(sanitized_Request('http://:pass@foo.bar').get_header('Authorization'),
+                         'Basic OnBhc3M=')
+        self.assertEqual(sanitized_Request('http://user:@foo.bar').get_header('Authorization'),
+                         'Basic dXNlcjo=')
+        self.assertEqual(sanitized_Request('http://user:pass@foo.bar').get_header('Authorization'),
+                         'Basic dXNlcjpwYXNz')
+
     def test_expand_path(self):
         def env(var):
             return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
@@ -512,11 +525,14 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(float_or_none(set()), None)
 
     def test_int_or_none(self):
+        self.assertEqual(int_or_none(42), 42)
         self.assertEqual(int_or_none('42'), 42)
         self.assertEqual(int_or_none(''), None)
         self.assertEqual(int_or_none(None), None)
         self.assertEqual(int_or_none([]), None)
         self.assertEqual(int_or_none(set()), None)
+        self.assertEqual(int_or_none('42', base=8), 34)
+        self.assertRaises(TypeError, int_or_none(42, base=8))
 
     def test_str_to_int(self):
         self.assertEqual(str_to_int('123,456'), 123456)

youtube_dl/compat.py

@@ -2421,29 +2421,26 @@ except ImportError:  # Python 2
 compat_urllib_request_urlretrieve = compat_urlretrieve
 
 try:
+    from HTMLParser import (
+        HTMLParser as compat_HTMLParser,
+        HTMLParseError as compat_HTMLParseError)
+except ImportError:  # Python 3
     from html.parser import HTMLParser as compat_HTMLParser
-except ImportError:  # Python 2
-    from HTMLParser import HTMLParser as compat_HTMLParser
-compat_html_parser_HTMLParser = compat_HTMLParser
-
-try:  # Python 2
-    from HTMLParser import HTMLParseError as compat_HTMLParseError
-except ImportError:  # Python <3.4
     try:
         from html.parser import HTMLParseError as compat_HTMLParseError
     except ImportError:  # Python >3.4
-
-        # HTMLParseError has been deprecated in Python 3.3 and removed in
+        # 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
 
 try:
-    from subprocess import DEVNULL
-    compat_subprocess_get_DEVNULL = lambda: DEVNULL
-except ImportError:
+    _DEVNULL = subprocess.DEVNULL
+    compat_subprocess_get_DEVNULL = lambda: _DEVNULL
+except AttributeError:
     compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
 
 try:
@@ -2943,6 +2940,51 @@ else:
     compat_socket_create_connection = socket.create_connection
 
 
+try:
+    from contextlib import suppress as compat_contextlib_suppress
+except ImportError:
+    class compat_contextlib_suppress(object):
+        _exceptions = None
+
+        def __init__(self, *exceptions):
+            super(compat_contextlib_suppress, self).__init__()
+            # TODO: [Base]ExceptionGroup (3.12+)
+            self._exceptions = exceptions
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc_val, exc_tb):
+            return exc_val is not None and isinstance(exc_val, self._exceptions or tuple())
+
+
+# subprocess.Popen context manager
+# avoids leaking handles if .communicate() is not called
+try:
+    _Popen = subprocess.Popen
+    # check for required context manager attributes
+    _Popen.__enter__ and _Popen.__exit__
+    compat_subprocess_Popen = _Popen
+except AttributeError:
+    # not a context manager - make one
+    from contextlib import contextmanager
+
+    @contextmanager
+    def compat_subprocess_Popen(*args, **kwargs):
+        popen = None
+        try:
+            popen = _Popen(*args, **kwargs)
+            yield popen
+        finally:
+            if popen:
+                for f in (popen.stdin, popen.stdout, popen.stderr):
+                    if f:
+                        # repeated .close() is OK, but just in case
+                        with compat_contextlib_suppress(EnvironmentError):
+                            f.close()
+                popen.wait()
+
+
 # Fix https://github.com/ytdl-org/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
 def workaround_optparse_bug9161():
@@ -3263,6 +3305,7 @@ __all__ = [
     'compat_http_cookiejar_Cookie',
     'compat_http_cookies',
     'compat_http_cookies_SimpleCookie',
+    'compat_contextlib_suppress',
     'compat_ctypes_WINFUNCTYPE',
     'compat_etree_fromstring',
     'compat_filter',
@@ -3298,6 +3341,7 @@ __all__ = [
     'compat_struct_pack',
     'compat_struct_unpack',
     'compat_subprocess_get_DEVNULL',
+    'compat_subprocess_Popen',
     'compat_tokenize_tokenize',
     'compat_urllib_error',
     'compat_urllib_parse',

youtube_dl/downloader/external.py

@@ -11,8 +11,14 @@ from .common import FileDownloader
 from ..compat import (
     compat_setenv,
     compat_str,
+    compat_subprocess_Popen,
 )
-from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
+
+try:
+    from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
+except ImportError:
+    FFmpegPostProcessor = None
+
 from ..utils import (
     cli_option,
     cli_valueless_option,
@@ -206,7 +212,10 @@ class WgetFD(ExternalFD):
                 retry[1] = '0'
             cmd += retry
         cmd += self._option('--bind-address', 'source_address')
-        cmd += self._option('--proxy', 'proxy')
+        proxy = self.params.get('proxy')
+        if proxy:
+            for var in ('http_proxy', 'https_proxy'):
+                cmd += ['--execute', '%s=%s' % (var, proxy)]
         cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
         cmd += self._configuration_args()
         cmd += ['--', info_dict['url']]
@@ -358,13 +367,14 @@ class FFmpegFD(ExternalFD):
 
     @classmethod
     def available(cls):
-        return FFmpegPostProcessor().available
+        # actual availability can only be confirmed for an instance
+        return bool(FFmpegPostProcessor)
 
     def _call_downloader(self, tmpfilename, info_dict):
-        url = info_dict['url']
-        ffpp = FFmpegPostProcessor(downloader=self)
+        # `downloader` means the parent `YoutubeDL`
+        ffpp = FFmpegPostProcessor(downloader=self.ydl)
         if not ffpp.available:
-            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            self.report_error('ffmpeg required for download but no ffmpeg (nor avconv) executable could be found. Please install one.')
             return False
         ffpp.check_version()
 
@@ -393,6 +403,7 @@ class FFmpegFD(ExternalFD):
         # if end_time:
         #     args += ['-t', compat_str(end_time - start_time)]
 
+        url = info_dict['url']
         cookies = self.ydl.cookiejar.get_cookies_for_url(url)
         if cookies:
             args.extend(['-cookies', ''.join(
@@ -480,21 +491,25 @@ class FFmpegFD(ExternalFD):
 
         self._debug_cmd(args)
 
-        proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
-        try:
-            retval = proc.wait()
-        except BaseException as e:
-            # subprocess.run would send the SIGKILL signal to ffmpeg and the
-            # mp4 file couldn't be played, but if we ask ffmpeg to quit it
-            # produces a file that is playable (this is mostly useful for live
-            # streams). Note that Windows is not affected and produces playable
-            # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
-            if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
-                process_communicate_or_kill(proc, b'q')
-            else:
-                proc.kill()
-                proc.wait()
-            raise
+        # From [1], a PIPE opened in Popen() should be closed, unless
+        # .communicate() is called. Avoid leaking any PIPEs by using Popen
+        # as a context manager (newer Python 3.x and compat)
+        # Fixes "Resource Warning" in test/test_downloader_external.py
+        # [1] https://devpress.csdn.net/python/62fde12d7e66823466192e48.html
+        with compat_subprocess_Popen(args, stdin=subprocess.PIPE, env=env) as proc:
+            try:
+                retval = proc.wait()
+            except BaseException as e:
+                # subprocess.run would send the SIGKILL signal to ffmpeg and the
+                # mp4 file couldn't be played, but if we ask ffmpeg to quit it
+                # produces a file that is playable (this is mostly useful for live
+                # streams). Note that Windows is not affected and produces playable
+                # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
+                if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
+                    process_communicate_or_kill(proc, b'q')
+                else:
+                    proc.kill()
+                raise
         return retval
 
 

youtube_dl/extractor/caffeine.py

@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    merge_dicts,
+    parse_iso8601,
+    T,
+    traverse_obj,
+    txt_or_none,
+    urljoin,
+)
+
+
+class CaffeineTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/]+/video/(?P<id>[0-9a-f-]+)'
+    _TESTS = [{
+        'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e',
+        'info_dict': {
+            'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e',
+            'ext': 'mp4',
+            'title': 'GOOOOD MORNINNNNN #highlights',
+            'timestamp': 1654702180,
+            'upload_date': '20220608',
+            'uploader': 'TsuSurf',
+            'duration': 3145,
+            'age_limit': 17,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        json_data = self._download_json(
+            'https://api.caffeine.tv/social/public/activity/' + video_id,
+            video_id)
+        broadcast_info = traverse_obj(json_data, ('broadcast_info', T(dict))) or {}
+        title = broadcast_info['broadcast_title']
+        video_url = broadcast_info['video_url']
+
+        ext = determine_ext(video_url)
+        if ext == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                video_url, video_id, 'mp4', entry_protocol='m3u8',
+                fatal=False)
+        else:
+            formats = [{'url': video_url}]
+        self._sort_formats(formats)
+
+        return merge_dicts({
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }, traverse_obj(json_data, {
+            'uploader': ((None, 'user'), 'username'),
+        }, get_all=False), traverse_obj(json_data, {
+            'like_count': ('like_count', T(int_or_none)),
+            'view_count': ('view_count', T(int_or_none)),
+            'comment_count': ('comment_count', T(int_or_none)),
+            'tags': ('tags', Ellipsis, T(txt_or_none)),
+            'is_live': 'is_live',
+            'uploader': ('user', 'name'),
+        }), traverse_obj(broadcast_info, {
+            'duration': ('content_duration', T(int_or_none)),
+            'timestamp': ('broadcast_start_time', T(parse_iso8601)),
+            'thumbnail': ('preview_image_path', T(lambda u: urljoin(url, u))),
+            'age_limit': ('content_rating', T(lambda r: r and {
+                # assume Apple Store ratings [1]
+                # 1. https://en.wikipedia.org/wiki/Mobile_software_content_rating_system
+                'FOUR_PLUS': 0,
+                'NINE_PLUS': 9,
+                'TWELVE_PLUS': 12,
+                'SEVENTEEN_PLUS': 17,
+            }.get(r, 17))),
+        }))

youtube_dl/extractor/common.py

@@ -25,6 +25,7 @@ from ..compat import (
     compat_getpass,
     compat_integer_types,
     compat_http_client,
+    compat_kwargs,
     compat_map as map,
     compat_open as open,
     compat_os_name,
@@ -1102,6 +1103,60 @@ class InfoExtractor(object):
             self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
+    def _search_json(self, start_pattern, string, name, video_id, **kwargs):
+        """Searches string for the JSON object specified by start_pattern"""
+
+        # self, start_pattern, string, name, video_id, *, end_pattern='',
+        # contains_pattern=r'{(?s:.+)}', fatal=True, default=NO_DEFAULT
+        # NB: end_pattern is only used to reduce the size of the initial match
+        end_pattern = kwargs.pop('end_pattern', '')
+        # (?:[\s\S]) simulates (?(s):.) (eg)
+        contains_pattern = kwargs.pop('contains_pattern', r'{[\s\S]+}')
+        fatal = kwargs.pop('fatal', True)
+        default = kwargs.pop('default', NO_DEFAULT)
+
+        if default is NO_DEFAULT:
+            default, has_default = {}, False
+        else:
+            fatal, has_default = False, True
+
+        json_string = self._search_regex(
+            r'(?:{0})\s*(?P<json>{1})\s*(?:{2})'.format(
+                start_pattern, contains_pattern, end_pattern),
+            string, name, group='json', fatal=fatal, default=None if has_default else NO_DEFAULT)
+        if not json_string:
+            return default
+
+        # yt-dlp has a special JSON parser that allows trailing text.
+        # Until that arrives here, the diagnostic from the exception
+        # raised by json.loads() is used to extract the wanted text.
+        # Either way, it's a problem if a transform_source() can't
+        # handle the trailing text.
+
+        # force an exception
+        kwargs['fatal'] = True
+
+        # self._downloader._format_err(name, self._downloader.Styles.EMPHASIS)
+        for _ in range(2):
+            try:
+                # return self._parse_json(json_string, video_id, ignore_extra=True, **kwargs)
+                transform_source = kwargs.pop('transform_source', None)
+                if transform_source:
+                    json_string = transform_source(json_string)
+                return self._parse_json(json_string, video_id, **compat_kwargs(kwargs))
+            except ExtractorError as e:
+                end = int_or_none(self._search_regex(r'\(char\s+(\d+)', error_to_compat_str(e), 'end', default=None))
+                if end is not None:
+                    json_string = json_string[:end]
+                    continue
+                msg = 'Unable to extract {0} - Failed to parse JSON'.format(name)
+                if fatal:
+                    raise ExtractorError(msg, cause=e.cause, video_id=video_id)
+                elif not has_default:
+                    self.report_warning(
+                        '{0}: {1}'.format(msg, error_to_compat_str(e)), video_id=video_id)
+            return default
+
     def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
@@ -2966,25 +3021,22 @@ class InfoExtractor(object):
         return formats
 
     def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
-        mobj = re.search(
-            r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
-            webpage)
-        if mobj:
-            try:
-                jwplayer_data = self._parse_json(mobj.group('options'),
-                                                 video_id=video_id,
-                                                 transform_source=transform_source)
-            except ExtractorError:
-                pass
-            else:
-                if isinstance(jwplayer_data, dict):
-                    return jwplayer_data
+        return self._search_json(
+            r'''(?<!-)\bjwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?:(?!</script>).)*?\.\s*(?:setup\s*\(|(?P<load>load)\s*\(\s*\[)''',
+            webpage, 'JWPlayer data', video_id,
+            # must be a {...} or sequence, ending
+            contains_pattern=r'\{[\s\S]*}(?(load)(?:\s*,\s*\{[\s\S]*})*)', end_pattern=r'(?(load)\]|\))',
+            transform_source=transform_source, default=None)
 
     def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
-        jwplayer_data = self._find_jwplayer_data(
-            webpage, video_id, transform_source=js_to_json)
-        return self._parse_jwplayer_data(
-            jwplayer_data, 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 {}
+
+        jwplayer_data = self._find_jwplayer_data(webpage, video_id, **kwfind)
+
+        return self._parse_jwplayer_data(jwplayer_data, video_id, *args, **kwargs)
 
     def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
                              m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
@@ -3018,22 +3070,14 @@ class InfoExtractor(object):
                 mpd_id=mpd_id, rtmp_params=rtmp_params, base_url=base_url)
 
             subtitles = {}
-            tracks = video_data.get('tracks')
-            if tracks and isinstance(tracks, list):
-                for track in tracks:
-                    if not isinstance(track, dict):
-                        continue
-                    track_kind = track.get('kind')
-                    if not track_kind or not isinstance(track_kind, compat_str):
-                        continue
-                    if track_kind.lower() not in ('captions', 'subtitles'):
-                        continue
-                    track_url = urljoin(base_url, track.get('file'))
-                    if not track_url:
-                        continue
-                    subtitles.setdefault(track.get('label') or 'en', []).append({
-                        'url': self._proto_relative_url(track_url)
-                    })
+            for track in traverse_obj(video_data, (
+                    'tracks', lambda _, t: t.get('kind').lower() in ('captions', 'subtitles'))):
+                track_url = urljoin(base_url, track.get('file'))
+                if not track_url:
+                    continue
+                subtitles.setdefault(track.get('label') or 'en', []).append({
+                    'url': self._proto_relative_url(track_url)
+                })
 
             entry = {
                 'id': this_video_id,

youtube_dl/extractor/extractors.py

@@ -159,6 +159,7 @@ from .businessinsider import BusinessInsiderIE
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
+from .caffeine import CaffeineTVIE
 from .callin import CallinIE
 from .camdemy import (
     CamdemyIE,
@@ -382,7 +383,6 @@ from .fc2 import (
     FC2EmbedIE,
 )
 from .fczenit import FczenitIE
-from .filemoon import FileMoonIE
 from .fifa import FifaIE
 from .filmon import (
     FilmOnIE,
@@ -443,6 +443,7 @@ from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
+from .gbnews import GBNewsIE
 from .gdcvault import GDCVaultIE
 from .gedidigital import GediDigitalIE
 from .generic import GenericIE

youtube_dl/extractor/filemoon.py

@@ -1,43 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    decode_packed_codes,
-    js_to_json,
-)
-
-
-class FileMoonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?filemoon\.sx/./(?P<id>\w+)'
-    _TEST = {
-        'url': 'https://filemoon.sx/e/dw40rxrzruqz',
-        'md5': '5a713742f57ac4aef29b74733e8dda01',
-        'info_dict': {
-            'id': 'dw40rxrzruqz',
-            'title': 'dw40rxrzruqz',
-            'ext': 'mp4'
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        matches = re.findall(r'(?s)(eval.*?)</script>', webpage)
-        packed = matches[-1]
-        unpacked = decode_packed_codes(packed)
-        jwplayer_sources = self._parse_json(
-            self._search_regex(
-                r'(?s)player\s*\.\s*setup\s*\(\s*\{\s*sources\s*:\s*(.*?])', unpacked, 'jwplayer sources'),
-            video_id, transform_source=js_to_json)
-
-        formats = self._parse_jwplayer_formats(jwplayer_sources, video_id)
-
-        return {
-            'id': video_id,
-            'title': self._generic_title(url) or video_id,
-            'formats': formats
-        }

youtube_dl/extractor/gbnews.py

@@ -0,0 +1,139 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    ExtractorError,
+    T,
+    traverse_obj,
+    txt_or_none,
+    url_or_none,
+)
+
+
+class GBNewsIE(InfoExtractor):
+    IE_DESC = 'GB News clips, features and live stream'
+
+    # \w+ is normally shows or news, but apparently any word redirects to the correct URL
+    _VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P<id>[^#?]+)'
+
+    _PLATFORM = 'safari'
+    _SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php'
+    _TESTS = [{
+        'url': 'https://www.gbnews.uk/shows/andrew-neils-message-to-companies-choosing-to-boycott-gb-news/106889',
+        'info_dict': {
+            'id': '106889',
+            'ext': 'mp4',
+            'title': "Andrew Neil's message to companies choosing to boycott GB News",
+            'description': 'md5:b281f5d22fd6d5eda64a4e3ba771b351',
+        },
+        'skip': '404 not found',
+    }, {
+        'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row',
+        'info_dict': {
+            'id': '52264136',
+            'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row',
+            'ext': 'mp4',
+            'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism',
+            'description': 'The post was criticised by former employers of the broadcaster',
+        },
+    }, {
+        'url': 'https://www.gbnews.uk/watchlive',
+        'info_dict': {
+            'id': '1069',
+            'display_id': 'watchlive',
+            'ext': 'mp4',
+            'title': 'GB News Live',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url).split('/')[-1]
+
+        webpage = self._download_webpage(url, display_id)
+        # extraction based on https://github.com/ytdl-org/youtube-dl/issues/29341
+        '''
+        <div id="video-106908"
+            class="simplestream"
+            data-id="GB001"
+            data-type="vod"
+            data-key="3Li3Nt2Qs8Ct3Xq9Fi5Uy0Mb2Bj0Qs"
+            data-token="f9c317c727dc07f515b20036c8ef14a6"
+            data-expiry="1624300052"
+            data-uvid="37900558"
+            data-poster="https://thumbnails.simplestreamcdn.com/gbnews/ondemand/37900558.jpg?width=700&"
+            data-npaw="false"
+            data-env="production">
+        '''
+        # exception if no match
+        video_data = self._search_regex(
+            r'(<div\s[^>]*\bclass\s*=\s*(\'|")(?!.*sidebar\b)simplestream(?:\s[\s\w$-]*)?\2[^>]*>)',
+            webpage, 'video data')
+
+        video_data = extract_attributes(video_data)
+        ss_id = video_data.get('data-id')
+        if not ss_id:
+            raise ExtractorError('Simplestream ID not found')
+
+        json_data = self._download_json(
+            self._SSMP_URL, display_id,
+            note='Downloading Simplestream JSON metadata',
+            errnote='Unable to download Simplestream JSON metadata',
+            query={
+                'id': ss_id,
+                'env': video_data.get('data-env', 'production'),
+            }, fatal=False)
+
+        meta_url = traverse_obj(json_data, ('response', 'api_hostname'))
+        if not meta_url:
+            raise ExtractorError('No API host found')
+
+        uvid = video_data['data-uvid']
+        dtype = video_data.get('data-type')
+        stream_data = self._download_json(
+            '%s/api/%s/stream/%s' % (meta_url, 'show' if dtype == 'vod' else dtype, uvid),
+            uvid,
+            query={
+                'key': video_data.get('data-key'),
+                'platform': self._PLATFORM,
+            },
+            headers={
+                'Token': video_data.get('data-token'),
+                'Token-Expiry': video_data.get('data-expiry'),
+                'Uvid': uvid,
+            }, fatal=False)
+
+        stream_url = traverse_obj(stream_data, (
+            'response', 'stream', T(url_or_none)))
+        if not stream_url:
+            raise ExtractorError('No stream data/URL')
+
+        # now known to be a dict
+        stream_data = stream_data['response']
+        drm = stream_data.get('drm')
+        if drm:
+            self.report_drm(uvid)
+
+        formats = self._extract_m3u8_formats(
+            stream_url, uvid, ext='mp4', entry_protocol='m3u8_native',
+            fatal=False)
+        # exception if no formats
+        self._sort_formats(formats)
+
+        return {
+            'id': uvid,
+            'display_id': display_id,
+            'title': (traverse_obj(stream_data, ('title', T(txt_or_none)))
+                      or self._og_search_title(webpage, default=None)
+                      or display_id.replace('-', ' ').capitalize()),
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': (traverse_obj(video_data, ('data-poster', T(url_or_none)))
+                          or self._og_search_thumbnail(webpage)),
+            'formats': formats,
+            'is_live': (dtype == 'live') or None,
+        }

youtube_dl/extractor/vbox7.py

@@ -7,6 +7,7 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_kwargs
 from ..utils import (
+    base_url,
     determine_ext,
     ExtractorError,
     float_or_none,
@@ -14,6 +15,7 @@ from ..utils import (
     T,
     traverse_obj,
     txt_or_none,
+    url_basename,
     url_or_none,
 )
 
@@ -33,8 +35,8 @@ class Vbox7IE(InfoExtractor):
                     '''
     _EMBED_REGEX = [r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)']
     _GEO_COUNTRIES = ['BG']
-    _GEO_BYPASS = False
     _TESTS = [{
+        # the http: URL just redirects here
         'url': 'https://vbox7.com/play:0946fff23c',
         'md5': '50ca1f78345a9c15391af47d8062d074',
         'info_dict': {
@@ -42,17 +44,19 @@ class Vbox7IE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Борисов: Притеснен съм за бъдещето на България',
             'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
-            'thumbnail': r're:^https?://.*\.jpg$',
             'timestamp': 1470982814,
             'upload_date': '20160812',
             'uploader': 'zdraveibulgaria',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'view_count': int,
+            'duration': 2640,
         },
         'expected_warnings': [
             'Unable to download webpage',
         ],
     }, {
         'url': 'http://vbox7.com/play:249bb972c2',
-        'md5': 'aaf19465e37ec0b30b918df83ec32c50',
+        'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {
             'id': '249bb972c2',
             'ext': 'mp4',
@@ -61,7 +65,11 @@ class Vbox7IE(InfoExtractor):
             'timestamp': 1360215023,
             'upload_date': '20130207',
             'uploader': 'svideteliat_ot_varshava',
+            'thumbnail': 'https://i49.vbox7.com/o/249/249bb972c20.jpg',
+            'view_count': int,
+            'duration': 83,
         },
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
         'only_matching': True,
@@ -76,6 +84,9 @@ class Vbox7IE(InfoExtractor):
         if mobj:
             return mobj.group('url')
 
+    # specialisation to transform what looks like ld+json that
+    # may contain invalid character combinations
+
     # transform_source=None, fatal=True
     def _parse_json(self, json_string, video_id, *args, **kwargs):
         if '"@context"' in json_string[:30]:
@@ -103,49 +114,64 @@ class Vbox7IE(InfoExtractor):
 
         now = time.time()
         response = self._download_json(
-            'https://www.vbox7.com/aj/player/item/options?vid=%s' % (video_id,),
-            video_id, headers={'Referer': url})
+            'https://www.vbox7.com/aj/player/item/options', video_id,
+            query={'vid': video_id}, headers={'Referer': url})
         # estimate time to which possible `ago` member is relative
         now = now + 0.5 * (time.time() - now)
 
-        if 'error' in response:
+        if traverse_obj(response, 'error'):
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
 
-        video_url = traverse_obj(response, ('options', 'src', T(url_or_none)))
+        src_url = traverse_obj(response, ('options', 'src', T(url_or_none))) or ''
 
-        if '/na.mp4' in video_url or '':
+        fmt_base = url_basename(src_url).rsplit('.', 1)[0].rsplit('_', 1)[0]
+        if fmt_base in ('na', 'vn'):
             self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
 
-        ext = determine_ext(video_url)
+        ext = determine_ext(src_url)
         if ext == 'mpd':
-            # In case MPD cannot be parsed, or anyway, get mp4 combined
-            # formats usually provided to Safari, iOS, and old Windows
+            # extract MPD
             try:
                 formats, subtitles = self._extract_mpd_formats_and_subtitles(
-                    video_url, video_id, 'dash', fatal=False)
-            except KeyError:
+                    src_url, video_id, 'dash', fatal=False)
+            except KeyError:  # fatal doesn't catch this
                 self.report_warning('Failed to parse MPD manifest')
                 formats, subtitles = [], {}
+        elif ext != 'm3u8':
+            formats = [{
+                'url': src_url,
+            }] if src_url else []
+            subtitles = {}
 
+        if src_url:
+            # possibly extract HLS, based on https://github.com/yt-dlp/yt-dlp/pull/9100
+            fmt_base = base_url(src_url) + fmt_base
+            # prepare for _extract_m3u8_formats_and_subtitles()
+            # hls_formats, hls_subs = self._extract_m3u8_formats_and_subtitles(
+            hls_formats = self._extract_m3u8_formats(
+                '{0}.m3u8'.format(fmt_base), video_id, m3u8_id='hls', fatal=False)
+            formats.extend(hls_formats)
+            # self._merge_subtitles(hls_subs, target=subtitles)
+
+            # In case MPD/HLS cannot be parsed, or anyway, get mp4 combined
+            # formats usually provided to Safari, iOS, and old Windows
             video = response['options']
             resolutions = (1080, 720, 480, 240, 144)
-            highest_res = traverse_obj(video, ('highestRes', T(int))) or resolutions[0]
-            for res in traverse_obj(video, ('resolutions', lambda _, r: int(r) > 0)) or resolutions:
-                if res > highest_res:
-                    continue
-                formats.append({
-                    'url': video_url.replace('.mpd', '_%d.mp4' % res),
-                    'format_id': '%dp' % res,
+            highest_res = traverse_obj(video, (
+                'highestRes', T(int))) or resolutions[0]
+            resolutions = traverse_obj(video, (
+                'resolutions', lambda _, r: highest_res >= int(r) > 0)) or resolutions
+            mp4_formats = traverse_obj(resolutions, (
+                Ellipsis, T(lambda res: {
+                    'url': '{0}_{1}.mp4'.format(fmt_base, res),
+                    'format_id': 'http-{0}'.format(res),
                     'height': res,
-                })
+                })))
             # if above formats are flaky, enable the line below
-            # self._check_formats(formats, video_id)
-        else:
-            formats = [{
-                'url': video_url,
-            }]
-            subtitles = {}
+            # self._check_formats(mp4_formats, video_id)
+            formats.extend(mp4_formats)
+
         self._sort_formats(formats)
 
         webpage = self._download_webpage(url, video_id, fatal=False) or ''

youtube_dl/extractor/videa.py

@@ -6,22 +6,31 @@ import re
 import string
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_b64decode,
+    compat_ord,
+    compat_struct_pack,
+)
 from ..utils import (
     ExtractorError,
     int_or_none,
     mimetype2ext,
     parse_codecs,
+    parse_qs,
     update_url_query,
     urljoin,
     xpath_element,
     xpath_text,
 )
-from ..compat import (
-    compat_b64decode,
-    compat_ord,
-    compat_struct_pack,
-    compat_urlparse,
-)
+
+
+def compat_random_choices(population, *args, **kwargs):
+    # weights=None, *, cum_weights=None, k=1
+    # limited implementation needed here
+    weights = args[0] if args else kwargs.get('weights')
+    assert all(w is None for w in (weights, kwargs.get('cum_weights')))
+    k = kwargs.get('k', 1)
+    return ''.join(random.choice(population) for _ in range(k))
 
 
 class VideaIE(InfoExtractor):
@@ -35,6 +44,7 @@ class VideaIE(InfoExtractor):
                         )
                         (?P<id>[^?#&]+)
                     '''
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1']
     _TESTS = [{
         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
@@ -44,6 +54,7 @@ class VideaIE(InfoExtractor):
             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
             'thumbnail': r're:^https?://.*',
             'duration': 21,
+            'age_limit': 0,
         },
     }, {
         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
@@ -54,6 +65,7 @@ class VideaIE(InfoExtractor):
             'title': 'Supercars előzés',
             'thumbnail': r're:^https?://.*',
             'duration': 64,
+            'age_limit': 0,
         },
     }, {
         'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
@@ -64,6 +76,7 @@ class VideaIE(InfoExtractor):
             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
             'thumbnail': r're:^https?://.*',
             'duration': 21,
+            'age_limit': 0,
         },
     }, {
         'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
@@ -80,11 +93,14 @@ class VideaIE(InfoExtractor):
     }]
     _STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [url for _, url in re.findall(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
-            webpage)]
+    @classmethod
+    def _extract_urls(cls, webpage):
+        def yield_urls():
+            for pattern in cls._EMBED_REGEX:
+                for m in re.finditer(pattern, webpage):
+                    yield m.group('url')
+
+        return list(yield_urls())
 
     @staticmethod
     def rc4(cipher_text, key):
@@ -130,13 +146,13 @@ class VideaIE(InfoExtractor):
         for i in range(0, 32):
             result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
 
-        query = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
-        random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
+        query = parse_qs(player_url)
+        random_seed = ''.join(compat_random_choices(string.ascii_letters + string.digits, k=8))
         query['_s'] = random_seed
         query['_t'] = result[:16]
 
         b64_info, handle = self._download_webpage_handle(
-            'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
+            'http://videa.hu/player/xml', video_id, query=query)
         if b64_info.startswith('<?xml'):
             info = self._parse_xml(b64_info, video_id)
         else:

youtube_dl/extractor/vimeo.py

@@ -673,8 +673,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
             raise
 
         if '//player.vimeo.com/video/' in url:
-            config = self._parse_json(self._search_regex(
-                r'(?s)\b(?:playerC|c)onfig\s*=\s*({.+?})\s*[;\n]', webpage, 'info section'), video_id)
+            config = self._search_json(
+                r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
             if config.get('view') == 4:
                 config = self._verify_player_video_password(
                     redirect_url, video_id, headers)

youtube_dl/extractor/xfileshare.py

@@ -4,20 +4,28 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_chr
+from ..compat import (
+    compat_chr,
+    compat_zip as zip,
+)
 from ..utils import (
+    clean_html,
     decode_packed_codes,
     determine_ext,
     ExtractorError,
+    get_element_by_id,
     int_or_none,
-    js_to_json,
+    merge_dicts,
+    T,
+    traverse_obj,
+    url_or_none,
     urlencode_postdata,
 )
 
 
 # based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
 def aa_decode(aa_code):
-    symbol_table = [
+    symbol_table = (
         ('7', '((ﾟｰﾟ) + (o^_^o))'),
         ('6', '((o^_^o) +(o^_^o))'),
         ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
@@ -26,84 +34,180 @@ def aa_decode(aa_code):
         ('3', '(o^_^o)'),
         ('1', '(ﾟΘﾟ)'),
         ('0', '(c^_^o)'),
-    ]
+        ('+', ''),
+    )
     delim = '(ﾟДﾟ)[ﾟεﾟ]+'
-    ret = ''
-    for aa_char in aa_code.split(delim):
+
+    def chr_from_code(c):
         for val, pat in symbol_table:
-            aa_char = aa_char.replace(pat, val)
-        aa_char = aa_char.replace('+ ', '')
-        m = re.match(r'^\d+', aa_char)
-        if m:
-            ret += compat_chr(int(m.group(0), 8))
+            c = c.replace(pat, val)
+        if c.startswith(('u', 'U')):
+            base = 16
+            c = c[1:]
         else:
-            m = re.match(r'^u([\da-f]+)', aa_char)
-            if m:
-                ret += compat_chr(int(m.group(1), 16))
-    return ret
+            base = 10
+        c = int_or_none(c, base=base)
+        return '' if c is None else compat_chr(c)
+
+    return ''.join(
+        chr_from_code(aa_char)
+        for aa_char in aa_code.split(delim))
 
 
 class XFileShareIE(InfoExtractor):
     _SITES = (
-        (r'aparat\.cam', 'Aparat'),
-        (r'clipwatching\.com', 'ClipWatching'),
-        (r'gounlimited\.to', 'GoUnlimited'),
-        (r'govid\.me', 'GoVid'),
-        (r'holavid\.com', 'HolaVid'),
-        (r'streamty\.com', 'Streamty'),
-        (r'thevideobee\.to', 'TheVideoBee'),
-        (r'uqload\.com', 'Uqload'),
-        (r'vidbom\.com', 'VidBom'),
-        (r'vidlo\.us', 'vidlo'),
-        (r'vidlocker\.xyz', 'VidLocker'),
-        (r'vidshare\.tv', 'VidShare'),
-        (r'vup\.to', 'VUp'),
+        # status check 2024-02: site availability, G site: search
+        (r'aparat\.cam', 'Aparat'),  # Cloudflare says host error 522, apparently changed to wolfstreeam.tv
+        (r'filemoon\.sx/.', 'FileMoon'),
+        (r'gounlimited\.to', 'GoUnlimited'),  # no media pages listed
+        (r'govid\.me', 'GoVid'),  # no media pages listed
+        (r'highstream\.tv', 'HighStream'),  # clipwatching.com redirects here
+        (r'holavid\.com', 'HolaVid'),  # Cloudflare says host error 522
+        # (r'streamty\.com', 'Streamty'),  # no media pages listed, connection timeout
+        # (r'thevideobee\.to', 'TheVideoBee'),  # no pages listed, refuses connection
+        (r'uqload\.to', 'Uqload'),  # .com, .co redirect here
+        (r'(?:vedbam\.xyz|vadbam.net)', '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'vup\.to', 'VUp'),  # domain not found
         (r'wolfstream\.tv', 'WolfStream'),
-        (r'xvideosharing\.com', 'XVideoSharing'),
+        (r'xvideosharing\.com', 'XVideoSharing'),  # just started showing 'maintenance mode'
     )
 
-    IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
+    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]+)'
                   % '|'.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'>The file was removed by administrator<',
     )
+    _TITLE_REGEXES = (
+        r'style="z-index: [0-9]+;">([^<]+)</span>',
+        r'<td nowrap>([^<]+)</td>',
+        r'h4-fine[^>]*>([^<]+)<',
+        r'>Watch (.+)[ <]',
+        r'<h2 class="video-page-head">([^<]+)</h2>',
+        r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to (dead)
+        r'title\s*:\s*"([^"]+)"',  # govid.me
+    )
+    _SOURCE_URL_REGEXES = (
+        r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
+        r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
+        r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
+        r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
+    )
+    _THUMBNAIL_REGEXES = (
+        r'<video[^>]+poster="([^"]+)"',
+        r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
+    )
 
     _TESTS = [{
-        'url': 'http://xvideosharing.com/fq65f94nd2ve',
-        'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
+        'note': 'link in `sources`',
+        'url': 'https://uqload.to/dcsu06gdb45o',
+        'md5': '7f8db187b254379440bf4fcad094ae86',
         'info_dict': {
-            'id': 'fq65f94nd2ve',
+            'id': 'dcsu06gdb45o',
             'ext': 'mp4',
-            'title': 'sample',
-            'thumbnail': r're:http://.*\.jpg',
+            'title': 'f2e31015957e74c8c8427982e161c3fc mp4',
+            'thumbnail': r're:https://.*\.jpg'
+        },
+        'params': {
+            'nocheckcertificate': True,
+        },
+        'expected_warnings': ['Unable to extract JWPlayer data'],
+    }, {
+        'note': 'link in decoded `sources`',
+        'url': 'https://xvideosharing.com/1tlg6agrrdgc',
+        'md5': '2608ce41932c1657ae56258a64e647d9',
+        'info_dict': {
+            'id': '1tlg6agrrdgc',
+            'ext': 'mp4',
+            'title': '0121',
+            'thumbnail': r're:https?://.*\.jpg',
+        },
+        'skip': 'This server is in maintenance mode.',
+    }, {
+        'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
+        'url': 'https://filemoon.sx/e/dw40rxrzruqz',
+        'md5': '5a713742f57ac4aef29b74733e8dda01',
+        'info_dict': {
+            'id': 'dw40rxrzruqz',
+            'title': 'dw40rxrzruqz',
+            'ext': 'mp4'
+        },
+    }, {
+        'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
+        'url': 'https://vadbam.net/6lnbkci96wly.html',
+        'md5': 'a1616800076177e2ac769203957c54bc',
+        'info_dict': {
+            'id': '6lnbkci96wly',
+            'title': 'Heart Crime S01 E03 weciima autos',
+            'ext': 'mp4'
+        },
+    }, {
+        'note': 'JWPlayer link in clear',
+        'url': 'https://w1.viidshar.com/nnibe0xf0h79.html',
+        'md5': 'f0a580ce9df06cc61b4a5c979d672367',
+        'info_dict': {
+            'id': 'nnibe0xf0h79',
+            'title': 'JaGa 68ar',
+            'ext': 'mp4'
+        },
+        'params': {
+            '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://wolfstream.tv/nthme29v9u2x',
+        '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,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
-                % '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
-                webpage)]
+    @classmethod
+    def _extract_urls(cls, webpage):
+
+        def yield_urls():
+            for regex in cls._EMBED_REGEX:
+                for mobj in re.finditer(regex, webpage):
+                    yield mobj.group('url')
+
+        return list(yield_urls())
 
     def _real_extract(self, url):
-        host, video_id = re.match(self._VALID_URL, url).groups()
+        host, video_id = self._match_valid_url(url).group('host', 'id')
 
-        url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
+        url = 'https://%s/%s' % (
+            host,
+            'embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
         webpage = self._download_webpage(url, video_id)
-
-        if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
+        container_div = get_element_by_id('container', webpage) 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(
+                self._FILE_NOT_FOUND_REGEXES, container_div,
+                'missing video error', group=0, default=None):
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         fields = self._hidden_inputs(webpage)
@@ -122,59 +226,43 @@ class XFileShareIE(InfoExtractor):
                     'Content-type': 'application/x-www-form-urlencoded',
                 })
 
-        title = (self._search_regex(
-            (r'style="z-index: [0-9]+;">([^<]+)</span>',
-             r'<td nowrap>([^<]+)</td>',
-             r'h4-fine[^>]*>([^<]+)<',
-             r'>Watch (.+)[ <]',
-             r'<h2 class="video-page-head">([^<]+)</h2>',
-             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<',  # streamin.to
-             r'title\s*:\s*"([^"]+)"'),  # govid.me
-            webpage, 'title', default=None) or self._og_search_title(
-            webpage, default=None) or video_id).strip()
+        title = (
+            self._search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
+            or self._og_search_title(webpage, default=None)
+            or video_id).strip()
 
-        for regex, func in (
-                (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
-                (r'(ﾟ.+)', aa_decode)):
-            obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
-            if obf_code:
-                webpage = webpage.replace(obf_code, func(obf_code))
+        obf_code = True
+        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)
+                if obf_code:
+                    webpage = webpage.replace(obf_code, func(obf_code))
+                    break
 
-        formats = []
+        jwplayer_data = self._find_jwplayer_data(
+            webpage.replace(r'\'', '\''), video_id)
+        result = self._parse_jwplayer_data(
+            jwplayer_data, video_id, require_title=False,
+            m3u8_id='hls', mpd_id='dash')
 
-        jwplayer_data = self._search_regex(
-            [
-                r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
-                r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
-            ], webpage,
-            'jwplayer data', default=None)
-        if jwplayer_data:
-            jwplayer_data = self._parse_json(
-                jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
+        if not traverse_obj(result, 'formats'):
             if jwplayer_data:
-                formats = self._parse_jwplayer_data(
-                    jwplayer_data, video_id, False,
-                    m3u8_id='hls', mpd_id='dash')['formats']
-
-        if not formats:
-            urls = []
-            for regex in (
-                    r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
-                    r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
-                    r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
-                    r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
+                self.report_warning(
+                    'Failed to extract JWPlayer formats', video_id=video_id)
+            urls = set()
+            for regex in self._SOURCE_URL_REGEXES:
                 for mobj in re.finditer(regex, webpage):
-                    video_url = mobj.group('url')
-                    if video_url not in urls:
-                        urls.append(video_url)
+                    urls.add(mobj.group('url'))
 
             sources = self._search_regex(
                 r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
-            if sources:
-                urls.extend(self._parse_json(sources, video_id))
+            urls.update(traverse_obj(sources, (T(lambda s: self._parse_json(s, video_id)), Ellipsis)))
 
             formats = []
-            for video_url in urls:
+            for video_url in traverse_obj(urls, (Ellipsis, T(url_or_none))):
                 if determine_ext(video_url) == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
                         video_url, video_id, 'mp4',
@@ -185,17 +273,19 @@ class XFileShareIE(InfoExtractor):
                         'url': video_url,
                         'format_id': 'sd',
                     })
-        self._sort_formats(formats)
+            result = {'formats': formats}
+
+        self._sort_formats(result['formats'])
 
         thumbnail = self._search_regex(
-            [
-                r'<video[^>]+poster="([^"]+)"',
-                r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
-            ], webpage, 'thumbnail', default=None)
+            self._THUMBNAIL_REGEXES, webpage, 'thumbnail', default=None)
 
-        return {
+        if not (title or result.get('title')):
+            title = self._generic_title(url) or video_id
+
+        return merge_dicts(result, {
             'id': video_id,
-            'title': title,
+            'title': title or None,
             'thumbnail': thumbnail,
-            'formats': formats,
-        }
+            'http_headers': {'Referer': url}
+        })

youtube_dl/extractor/youtube.py

@@ -1647,10 +1647,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         except JSInterpreter.Exception as e:
             self.report_warning(
                 '%s (%s %s)' % (
-                    self.__ie_msg(
-                        'Unable to decode n-parameter: download likely to be throttled'),
+                    'Unable to decode n-parameter: download likely to be throttled',
                     error_to_compat_str(e),
-                    traceback.format_exc()))
+                    traceback.format_exc()),
+                video_id=video_id)
             return
 
         self.write_debug('Decrypted nsig {0} => {1}'.format(n, ret))

youtube_dl/postprocessor/embedthumbnail.py

@@ -91,6 +91,25 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             os.remove(encodeFilename(filename))
             os.rename(encodeFilename(temp_filename), encodeFilename(filename))
 
+        elif info['ext'] in ['mkv', 'webm']:
+            os.rename(encodeFilename(thumbnail_filename), encodeFilename('cover.jpg'))
+            old_thumbnail_filename = thumbnail_filename
+            thumbnail_filename = 'cover.jpg'
+
+            options = [
+                '-c', 'copy', '-attach', thumbnail_filename, '-metadata:s:t', 'mimetype=image/jpeg']
+
+            self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
+
+            self.run_ffmpeg_multiple_files([filename], temp_filename, options)
+
+            if not self._already_have_thumbnail:
+                os.remove(encodeFilename(thumbnail_filename))
+            else:
+                os.rename(encodeFilename(thumbnail_filename), encodeFilename(old_thumbnail_filename))
+            os.remove(encodeFilename(filename))
+            os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
         elif info['ext'] in ['m4a', 'mp4']:
             atomicparsley = next((x
                                   for x in ['AtomicParsley', 'atomicparsley']

youtube_dl/postprocessor/ffmpeg.py

@@ -74,8 +74,11 @@ class FFmpegPostProcessor(PostProcessor):
         return FFmpegPostProcessor(downloader)._versions
 
     def _determine_executables(self):
-        programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
+        # ordered to match prefer_ffmpeg!
+        convs = ['ffmpeg', 'avconv']
+        probes = ['ffprobe', 'avprobe']
         prefer_ffmpeg = True
+        programs = convs + probes
 
         def get_ffmpeg_version(path):
             ver = get_exe_version(path, args=['-version'])
@@ -96,6 +99,7 @@ class FFmpegPostProcessor(PostProcessor):
 
         self._paths = None
         self._versions = None
+        location = None
         if self._downloader:
             prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', True)
             location = self._downloader.params.get('ffmpeg_location')
@@ -118,33 +122,21 @@ class FFmpegPostProcessor(PostProcessor):
                     location = os.path.dirname(os.path.abspath(location))
                     if basename in ('ffmpeg', 'ffprobe'):
                         prefer_ffmpeg = True
+        self._paths = dict(
+            (p, p if location is None else os.path.join(location, p))
+            for p in programs)
+        self._versions = dict(
+            x for x in (
+                (p, get_ffmpeg_version(self._paths[p])) for p in programs)
+            if x[1] is not None)
 
-                self._paths = dict(
-                    (p, os.path.join(location, p)) for p in programs)
-                self._versions = dict(
-                    (p, get_ffmpeg_version(self._paths[p])) for p in programs)
-        if self._versions is None:
-            self._versions = dict(
-                (p, get_ffmpeg_version(p)) for p in programs)
-            self._paths = dict((p, p) for p in programs)
-
-        if prefer_ffmpeg is False:
-            prefs = ('avconv', 'ffmpeg')
-        else:
-            prefs = ('ffmpeg', 'avconv')
-        for p in prefs:
-            if self._versions[p]:
-                self.basename = p
-                break
-
-        if prefer_ffmpeg is False:
-            prefs = ('avprobe', 'ffprobe')
-        else:
-            prefs = ('ffprobe', 'avprobe')
-        for p in prefs:
-            if self._versions[p]:
-                self.probe_basename = p
-                break
+        basenames = [None, None]
+        for i, progs in enumerate((convs, probes)):
+            for p in progs[::-1 if prefer_ffmpeg is False else 1]:
+                if self._versions.get(p):
+                    basenames[i] = p
+                    break
+        self.basename, self.probe_basename = basenames
 
     @property
     def available(self):

youtube_dl/utils.py

@@ -45,6 +45,7 @@ from .compat import (
     compat_casefold,
     compat_chr,
     compat_collections_abc,
+    compat_contextlib_suppress,
     compat_cookiejar,
     compat_ctypes_WINFUNCTYPE,
     compat_datetime_timedelta_total_seconds,
@@ -1855,25 +1856,18 @@ def write_json_file(obj, fn):
     try:
         with tf:
             json.dump(obj, tf)
-        if sys.platform == 'win32':
-            # Need to remove existing file on Windows, else os.rename raises
-            # WindowsError or FileExistsError.
-            try:
+        with compat_contextlib_suppress(OSError):
+            if sys.platform == 'win32':
+                # Need to remove existing file on Windows, else os.rename raises
+                # WindowsError or FileExistsError.
                 os.unlink(fn)
-            except OSError:
-                pass
-        try:
             mask = os.umask(0)
             os.umask(mask)
             os.chmod(tf.name, 0o666 & ~mask)
-        except OSError:
-            pass
         os.rename(tf.name, fn)
     except Exception:
-        try:
+        with compat_contextlib_suppress(OSError):
             os.remove(tf.name)
-        except OSError:
-            pass
         raise
 
 
@@ -2033,14 +2027,13 @@ def extract_attributes(html_element):
     NB HTMLParser is stricter in Python 2.6 & 3.2 than in later versions,
     but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
     """
-    parser = HTMLAttributeParser()
-    try:
-        parser.feed(html_element)
-        parser.close()
-    # Older Python may throw HTMLParseError in case of malformed HTML
-    except compat_HTMLParseError:
-        pass
-    return parser.attrs
+    ret = None
+    # Older Python may throw HTMLParseError in case of malformed HTML (and on .close()!)
+    with compat_contextlib_suppress(compat_HTMLParseError):
+        with contextlib.closing(HTMLAttributeParser()) as parser:
+            parser.feed(html_element)
+            ret = parser.attrs
+    return ret or {}
 
 
 def clean_html(html):
@@ -2182,8 +2175,28 @@ def sanitize_url(url):
     return url
 
 
+def extract_basic_auth(url):
+    parts = compat_urllib_parse.urlsplit(url)
+    if parts.username is None:
+        return url, None
+    url = compat_urllib_parse.urlunsplit(parts._replace(netloc=(
+        parts.hostname if parts.port is None
+        else '%s:%d' % (parts.hostname, parts.port))))
+    auth_payload = base64.b64encode(
+        ('%s:%s' % (parts.username, parts.password or '')).encode('utf-8'))
+    return url, 'Basic {0}'.format(auth_payload.decode('ascii'))
+
+
 def sanitized_Request(url, *args, **kwargs):
-    return compat_urllib_request.Request(escape_url(sanitize_url(url)), *args, **kwargs)
+    url, auth_header = extract_basic_auth(escape_url(sanitize_url(url)))
+    if auth_header is not None:
+        headers = args[1] if len(args) > 1 else kwargs.get('headers')
+        headers = headers or {}
+        headers['Authorization'] = auth_header
+        if len(args) <= 1 and kwargs.get('headers') is None:
+            kwargs['headers'] = headers
+            kwargs = compat_kwargs(kwargs)
+    return compat_urllib_request.Request(url, *args, **kwargs)
 
 
 def expand_path(s):
@@ -2221,7 +2234,8 @@ def _htmlentity_transform(entity_with_semicolon):
             numstr = '0%s' % numstr
         else:
             base = 10
-        # See https://github.com/ytdl-org/youtube-dl/issues/7518
+        # See https://github.com/ytdl-org/youtube-dl/issues/7518\
+        # Also, weirdly, compat_contextlib_suppress fails here in 2.6
         try:
             return compat_chr(int(numstr, base))
         except ValueError:
@@ -2328,11 +2342,9 @@ def make_HTTPS_handler(params, **kwargs):
         # Some servers may (wrongly) reject requests if ALPN extension is not sent. See:
         # https://github.com/python/cpython/issues/85140
         # https://github.com/yt-dlp/yt-dlp/issues/3878
-        try:
+        with compat_contextlib_suppress(AttributeError, NotImplementedError):
+            # fails for Python < 2.7.10, not ssl.HAS_ALPN
             ctx.set_alpn_protocols(ALPN_PROTOCOLS)
-        except (AttributeError, NotImplementedError):
-            # Python < 2.7.10, not ssl.HAS_ALPN
-            pass
 
     opts_no_check_certificate = params.get('nocheckcertificate', False)
     if hasattr(ssl, 'create_default_context'):  # Python >= 3.4 or 2.7.9
@@ -2342,12 +2354,10 @@ def make_HTTPS_handler(params, **kwargs):
             context.check_hostname = False
             context.verify_mode = ssl.CERT_NONE
 
-        try:
+        with compat_contextlib_suppress(TypeError):
+            # Fails with Python 2.7.8 (create_default_context present
+            # but HTTPSHandler has no context=)
             return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
-        except TypeError:
-            # Python 2.7.8
-            # (create_default_context present but HTTPSHandler has no context=)
-            pass
 
     if sys.version_info < (3, 2):
         return YoutubeDLHTTPSHandler(params, **kwargs)
@@ -2361,15 +2371,24 @@ def make_HTTPS_handler(params, **kwargs):
         return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
 
 
-def bug_reports_message():
+def bug_reports_message(before=';'):
     if ytdl_is_updateable():
         update_cmd = 'type  youtube-dl -U  to update'
     else:
-        update_cmd = 'see  https://yt-dl.org/update  on how to update'
-    msg = '; please report this issue on https://yt-dl.org/bug .'
-    msg += ' Make sure you are using the latest version; %s.' % update_cmd
-    msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
-    return msg
+        update_cmd = 'see  https://github.com/ytdl-org/youtube-dl/#user-content-installation  on how to update'
+
+    msg = (
+        'please report this issue on https://github.com/ytdl-org/youtube-dl/issues ,'
+        ' using the appropriate issue template.'
+        ' Make sure you are using the latest version; %s.'
+        ' Be sure to call youtube-dl with the --verbose option and include the complete output.'
+    ) % update_cmd
+
+    before = (before or '').rstrip()
+    if not before or before.endswith(('.', '!', '?')):
+        msg = msg[0].title() + msg[1:]
+
+    return (before + ' ' if before else '') + msg
 
 
 class YoutubeDLError(Exception):
@@ -3156,12 +3175,10 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
     if timezone is None:
         timezone, date_str = extract_timezone(date_str)
 
-    try:
+    with compat_contextlib_suppress(ValueError):
         date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
         dt = datetime.datetime.strptime(date_str, date_format) - timezone
         return calendar.timegm(dt.timetuple())
-    except ValueError:
-        pass
 
 
 def date_formats(day_first=True):
@@ -3181,17 +3198,13 @@ def unified_strdate(date_str, day_first=True):
     _, date_str = extract_timezone(date_str)
 
     for expression in date_formats(day_first):
-        try:
+        with compat_contextlib_suppress(ValueError):
             upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
-        except ValueError:
-            pass
     if upload_date is None:
         timetuple = email.utils.parsedate_tz(date_str)
         if timetuple:
-            try:
+            with compat_contextlib_suppress(ValueError):
                 upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
-            except ValueError:
-                pass
     if upload_date is not None:
         return compat_str(upload_date)
 
@@ -3220,11 +3233,9 @@ def unified_timestamp(date_str, day_first=True):
         date_str = m.group(1)
 
     for expression in date_formats(day_first):
-        try:
+        with compat_contextlib_suppress(ValueError):
             dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
             return calendar.timegm(dt.timetuple())
-        except ValueError:
-            pass
     timetuple = email.utils.parsedate_tz(date_str)
     if timetuple:
         return calendar.timegm(timetuple) + pm_delta * 3600 - compat_datetime_timedelta_total_seconds(timezone)
@@ -3832,14 +3843,15 @@ class PUTRequest(compat_urllib_request.Request):
         return 'PUT'
 
 
-def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
+def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1, base=None):
     if get_attr:
         if v is not None:
             v = getattr(v, get_attr, None)
     if v in (None, ''):
         return default
     try:
-        return int(v) * invscale // scale
+        # like int, raise if base is specified and v is not a string
+        return (int(v) if base is None else int(v, base=base)) * invscale // scale
     except (ValueError, TypeError, OverflowError):
         return default