Merge branch 'ytdl-org:master' into df-bitchute-ovrhaul

youtube_dl/YoutubeDL.py

@@ -73,6 +73,7 @@ from .utils import (
     PostProcessingError,
     preferredencoding,
     prepend_extension,
+    process_communicate_or_kill,
     register_socks_protocols,
     render_table,
     replace_extension,
@@ -720,7 +721,7 @@ class YoutubeDL(object):
                 filename = encodeFilename(filename, True).decode(preferredencoding())
             return sanitize_path(filename)
         except ValueError as err:
-            self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
+            self.report_error('Error in output template: ' + error_to_compat_str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
     def _match_entry(self, info_dict, incomplete):
@@ -1569,9 +1570,6 @@ class YoutubeDL(object):
         else:
             formats = info_dict['formats']
 
-        if not formats:
-            raise ExtractorError('No video formats found!')
-
         def is_wellformed(f):
             url = f.get('url')
             if not url:
@@ -1584,7 +1582,10 @@ class YoutubeDL(object):
             return True
 
         # Filter out malformed formats for better extraction robustness
-        formats = list(filter(is_wellformed, formats))
+        formats = list(filter(is_wellformed, formats or []))
+
+        if not formats:
+            raise ExtractorError('No video formats found!')
 
         formats_dict = {}
 
@@ -1778,10 +1779,9 @@ class YoutubeDL(object):
 
         assert info_dict.get('_type', 'video') == 'video'
 
-        max_downloads = self.params.get('max_downloads')
-        if max_downloads is not None:
-            if self._num_downloads >= int(max_downloads):
-                raise MaxDownloadsReached()
+        max_downloads = int_or_none(self.params.get('max_downloads')) or float('inf')
+        if self._num_downloads >= max_downloads:
+            raise MaxDownloadsReached()
 
         # TODO: backward compatibility, to be removed
         info_dict['fulltitle'] = info_dict['title']
@@ -2058,9 +2058,12 @@ class YoutubeDL(object):
                 try:
                     self.post_process(filename, info_dict)
                 except (PostProcessingError) as err:
-                    self.report_error('postprocessing: %s' % str(err))
+                    self.report_error('postprocessing: %s' % error_to_compat_str(err))
                     return
                 self.record_download_archive(info_dict)
+                # avoid possible nugatory search for further items (PR #26638)
+                if self._num_downloads >= max_downloads:
+                    raise MaxDownloadsReached()
 
     def download(self, url_list):
         """Download a given list of URLs."""
@@ -2323,7 +2326,7 @@ class YoutubeDL(object):
                 ['git', 'rev-parse', '--short', 'HEAD'],
                 stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                 cwd=os.path.dirname(os.path.abspath(__file__)))
-            out, err = sp.communicate()
+            out, err = process_communicate_or_kill(sp)
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
                 self._write_string('[debug] Git HEAD: ' + out + '\n')

youtube_dl/aes.py

@@ -8,6 +8,18 @@ from .utils import bytes_to_intlist, intlist_to_bytes
 BLOCK_SIZE_BYTES = 16
 
 
+def pkcs7_padding(data):
+    """
+    PKCS#7 padding
+
+    @param {int[]} data        cleartext
+    @returns {int[]}           padding data
+    """
+
+    remaining_length = BLOCK_SIZE_BYTES - len(data) % BLOCK_SIZE_BYTES
+    return data + [remaining_length] * remaining_length
+
+
 def aes_ctr_decrypt(data, key, counter):
     """
     Decrypt with aes in counter mode
@@ -76,8 +88,7 @@ def aes_cbc_encrypt(data, key, iv):
     previous_cipher_block = iv
     for i in range(block_count):
         block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        remaining_length = BLOCK_SIZE_BYTES - len(block)
-        block += [remaining_length] * remaining_length
+        block = pkcs7_padding(block)
         mixed_block = xor(block, previous_cipher_block)
 
         encrypted_block = aes_encrypt(mixed_block, expanded_key)
@@ -88,6 +99,28 @@ def aes_cbc_encrypt(data, key, iv):
     return encrypted_data
 
 
+def aes_ecb_encrypt(data, key):
+    """
+    Encrypt with aes in ECB mode. Using PKCS#7 padding
+
+    @param {int[]} data        cleartext
+    @param {int[]} key         16/24/32-Byte cipher key
+    @returns {int[]}           encrypted data
+    """
+    expanded_key = key_expansion(key)
+    block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
+
+    encrypted_data = []
+    for i in range(block_count):
+        block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
+        block = pkcs7_padding(block)
+
+        encrypted_block = aes_encrypt(block, expanded_key)
+        encrypted_data += encrypted_block
+
+    return encrypted_data
+
+
 def key_expansion(data):
     """
     Generate key schedule
@@ -303,7 +336,7 @@ def xor(data1, data2):
 
 
 def rijndael_mul(a, b):
-    if(a == 0 or b == 0):
+    if (a == 0 or b == 0):
         return 0
     return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
 

youtube_dl/cache.py

@@ -10,12 +10,21 @@ import traceback
 
 from .compat import compat_getenv
 from .utils import (
+    error_to_compat_str,
     expand_path,
+    is_outdated_version,
+    try_get,
     write_json_file,
 )
+from .version import __version__
 
 
 class Cache(object):
+
+    _YTDL_DIR = 'youtube-dl'
+    _VERSION_KEY = _YTDL_DIR + '_version'
+    _DEFAULT_VERSION = '2021.12.17'
+
     def __init__(self, ydl):
         self._ydl = ydl
 
@@ -23,7 +32,7 @@ class Cache(object):
         res = self._ydl.params.get('cachedir')
         if res is None:
             cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
-            res = os.path.join(cache_root, 'youtube-dl')
+            res = os.path.join(cache_root, self._YTDL_DIR)
         return expand_path(res)
 
     def _get_cache_fn(self, section, key, dtype):
@@ -50,13 +59,22 @@ class Cache(object):
             except OSError as ose:
                 if ose.errno != errno.EEXIST:
                     raise
-            write_json_file(data, fn)
+            write_json_file({self._VERSION_KEY: __version__, 'data': data}, fn)
         except Exception:
             tb = traceback.format_exc()
             self._ydl.report_warning(
                 'Writing cache to %r failed: %s' % (fn, tb))
 
-    def load(self, section, key, dtype='json', default=None):
+    def _validate(self, data, min_ver):
+        version = try_get(data, lambda x: x[self._VERSION_KEY])
+        if not version:  # Backward compatibility
+            data, version = {'data': data}, self._DEFAULT_VERSION
+        if not is_outdated_version(version, min_ver or '0', assume_new=False):
+            return data['data']
+        self._ydl.to_screen(
+            'Discarding old cache from version {version} (needs {min_ver})'.format(**locals()))
+
+    def load(self, section, key, dtype='json', default=None, min_ver=None):
         assert dtype in ('json',)
 
         if not self.enabled:
@@ -66,12 +84,12 @@ class Cache(object):
         try:
             try:
                 with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
-                    return json.load(cachef)
+                    return self._validate(json.load(cachef), min_ver)
             except ValueError:
                 try:
                     file_size = os.path.getsize(cache_fn)
                 except (OSError, IOError) as oe:
-                    file_size = str(oe)
+                    file_size = error_to_compat_str(oe)
                 self._ydl.report_warning(
                     'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
         except IOError:

youtube_dl/compat.py

@@ -21,6 +21,19 @@ import subprocess
 import sys
 import xml.etree.ElementTree
 
+# deal with critical unicode/str things first
+try:
+    # Python 2
+    compat_str, compat_basestring, compat_chr = (
+        unicode, basestring, unichr
+    )
+    from .casefold import casefold as compat_casefold
+except NameError:
+    compat_str, compat_basestring, compat_chr = (
+        str, str, chr
+    )
+    compat_casefold = lambda s: s.casefold()
+
 try:
     import collections.abc as compat_collections_abc
 except ImportError:
@@ -2373,11 +2386,6 @@ try:
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
-try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
-
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
@@ -2508,22 +2516,11 @@ except ImportError:  # Python < 3.4
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
-try:
-    compat_basestring = basestring  # Python 2
-except NameError:
-    compat_basestring = str
-
-try:
-    compat_chr = unichr  # Python 2
-except NameError:
-    compat_chr = chr
-
 try:
     from xml.etree.ElementTree import ParseError as compat_xml_parse_error
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 
-
 etree = xml.etree.ElementTree
 
 
@@ -2890,6 +2887,7 @@ else:
     _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
 
     def compat_get_terminal_size(fallback=(80, 24)):
+        from .utils import process_communicate_or_kill
         columns = compat_getenv('COLUMNS')
         if columns:
             columns = int(columns)
@@ -2906,7 +2904,7 @@ else:
                 sp = subprocess.Popen(
                     ['stty', 'size'],
                     stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-                out, err = sp.communicate()
+                out, err = process_communicate_or_kill(sp)
                 _lines, _columns = map(int, out.split())
             except Exception:
                 _columns, _lines = _terminal_size(*fallback)
@@ -2984,7 +2982,6 @@ except ImportError:
     except ImportError:
         compat_filter = filter
 
-
 try:
     from future_builtins import zip as compat_zip
 except ImportError:  # not 2.6+ or is 3.x
@@ -2994,6 +2991,82 @@ except ImportError:  # not 2.6+ or is 3.x
         compat_zip = zip
 
 
+# method renamed between Py2/3
+try:
+    from itertools import zip_longest as compat_itertools_zip_longest
+except ImportError:
+    from itertools import izip_longest as compat_itertools_zip_longest
+
+
+# new class in collections
+try:
+    from collections import ChainMap as compat_collections_chain_map
+    # Py3.3's ChainMap is deficient
+    if sys.version_info < (3, 4):
+        raise ImportError
+except ImportError:
+    # Py <= 3.3
+    class compat_collections_chain_map(compat_collections_abc.MutableMapping):
+
+        maps = [{}]
+
+        def __init__(self, *maps):
+            self.maps = list(maps) or [{}]
+
+        def __getitem__(self, k):
+            for m in self.maps:
+                if k in m:
+                    return m[k]
+            raise KeyError(k)
+
+        def __setitem__(self, k, v):
+            self.maps[0].__setitem__(k, v)
+            return
+
+        def __contains__(self, k):
+            return any((k in m) for m in self.maps)
+
+        def __delitem(self, k):
+            if k in self.maps[0]:
+                del self.maps[0][k]
+                return
+            raise KeyError(k)
+
+        def __delitem__(self, k):
+            self.__delitem(k)
+
+        def __iter__(self):
+            return itertools.chain(*reversed(self.maps))
+
+        def __len__(self):
+            return len(iter(self))
+
+        # to match Py3, don't del directly
+        def pop(self, k, *args):
+            if self.__contains__(k):
+                off = self.__getitem__(k)
+                self.__delitem(k)
+                return off
+            elif len(args) > 0:
+                return args[0]
+            raise KeyError(k)
+
+        def new_child(self, m=None, **kwargs):
+            m = m or {}
+            m.update(kwargs)
+            return compat_collections_chain_map(m, *self.maps)
+
+        @property
+        def parents(self):
+            return compat_collections_chain_map(*(self.maps[1:]))
+
+
+# Pythons disagree on the type of a pattern (RegexObject, _sre.SRE_Pattern, Pattern, ...?)
+compat_re_Pattern = type(re.compile(''))
+# and on the type of a match
+compat_re_Match = type(re.match('a', 'a'))
+
+
 if sys.version_info < (3, 3):
     def compat_b64decode(s, *args, **kwargs):
         if isinstance(s, compat_str):
@@ -3028,8 +3101,10 @@ __all__ = [
     'compat_Struct',
     'compat_b64decode',
     'compat_basestring',
+    'compat_casefold',
     'compat_chr',
     'compat_collections_abc',
+    'compat_collections_chain_map',
     'compat_cookiejar',
     'compat_cookiejar_Cookie',
     'compat_cookies',
@@ -3050,6 +3125,7 @@ __all__ = [
     'compat_input',
     'compat_integer_types',
     'compat_itertools_count',
+    'compat_itertools_zip_longest',
     'compat_kwargs',
     'compat_map',
     'compat_numeric_types',
@@ -3057,6 +3133,8 @@ __all__ = [
     'compat_os_name',
     'compat_parse_qs',
     'compat_print',
+    'compat_re_Match',
+    'compat_re_Pattern',
     'compat_realpath',
     'compat_setenv',
     'compat_shlex_quote',

youtube_dl/downloader/external.py

@@ -22,6 +22,7 @@ from ..utils import (
     handle_youtubedl_headers,
     check_executable,
     is_outdated_version,
+    process_communicate_or_kill,
 )
 
 
@@ -104,7 +105,7 @@ class ExternalFD(FileDownloader):
 
         p = subprocess.Popen(
             cmd, stderr=subprocess.PIPE)
-        _, stderr = p.communicate()
+        _, stderr = process_communicate_or_kill(p)
         if p.returncode != 0:
             self.to_stderr(stderr.decode('utf-8', 'replace'))
         return p.returncode
@@ -141,7 +142,7 @@ class CurlFD(ExternalFD):
 
         # curl writes the progress to stderr so don't capture it.
         p = subprocess.Popen(cmd)
-        p.communicate()
+        process_communicate_or_kill(p)
         return p.returncode
 
 
@@ -336,14 +337,17 @@ class FFmpegFD(ExternalFD):
         proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
         try:
             retval = proc.wait()
-        except KeyboardInterrupt:
-            # subprocces.run would send the SIGKILL signal to ffmpeg and the
+        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 sys.platform != 'win32':
-                proc.communicate(b'q')
+            if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
+                process_communicate_or_kill(proc, b'q')
+            else:
+                proc.kill()
+                proc.wait()
             raise
         return retval
 

youtube_dl/downloader/rtmp.py

@@ -89,11 +89,13 @@ class RtmpFD(FileDownloader):
                                 self.to_screen('')
                             cursor_in_new_line = True
                             self.to_screen('[rtmpdump] ' + line)
-            finally:
+                if not cursor_in_new_line:
+                    self.to_screen('')
+                return proc.wait()
+            except BaseException:  # Including KeyboardInterrupt
+                proc.kill()
                 proc.wait()
-            if not cursor_in_new_line:
-                self.to_screen('')
-            return proc.returncode
+                raise
 
         url = info_dict['url']
         player_url = info_dict.get('player_url')

youtube_dl/extractor/adn.py

@@ -31,30 +31,34 @@ from ..utils import (
 
 
 class ADNIE(InfoExtractor):
-    IE_DESC = 'Anime Digital Network'
-    _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
-        'md5': '0319c99885ff5547565cacb4f3f9348d',
+    IE_DESC = 'Animation Digital Network'
+    _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
+        'md5': '1c9ef066ceb302c86f80c2b371615261',
         'info_dict': {
-            'id': '7778',
+            'id': '9841',
             'ext': 'mp4',
-            'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
-            'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
-            'series': 'Blue Exorcist - Kyôto Saga',
-            'duration': 1467,
-            'release_date': '20170106',
+            'title': 'Fruits Basket - Episode 1',
+            'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
+            'series': 'Fruits Basket',
+            'duration': 1437,
+            'release_date': '20190405',
             'comment_count': int,
             'average_rating': float,
-            'season_number': 2,
-            'episode': 'Début des hostilités',
+            'season_number': 1,
+            'episode': 'À ce soir !',
             'episode_number': 1,
-        }
-    }
+        },
+        'skip': 'Only available in region (FR, ...)',
+    }, {
+        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'only_matching': True,
+    }]
 
-    _NETRC_MACHINE = 'animedigitalnetwork'
-    _BASE_URL = 'http://animedigitalnetwork.fr'
-    _API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
+    _NETRC_MACHINE = 'animationdigitalnetwork'
+    _BASE = 'animationdigitalnetwork.fr'
+    _API_BASE_URL = 'https://gw.api.' + _BASE + '/'
     _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
     _HEADERS = {}
     _LOGIN_ERR_MESSAGE = 'Unable to log in'
@@ -82,14 +86,14 @@ class ADNIE(InfoExtractor):
         if subtitle_location:
             enc_subtitles = self._download_webpage(
                 subtitle_location, video_id, 'Downloading subtitles data',
-                fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
+                fatal=False, headers={'Origin': 'https://' + self._BASE})
         if not enc_subtitles:
             return None
 
-        # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
+        # http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(binascii.unhexlify(self._K + 'ab9f52f5baae7c72')),
+            bytes_to_intlist(binascii.unhexlify(self._K + '7fac1178830cfe0c')),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(
@@ -138,9 +142,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
         if not username:
             return
         try:
+            url = self._API_BASE_URL + 'authentication/login'
             access_token = (self._download_json(
-                self._API_BASE_URL + 'authentication/login', None,
-                'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
+                url, None, 'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
                 data=urlencode_postdata({
                     'password': password,
                     'rememberMe': False,
@@ -153,7 +157,8 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
             message = None
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
                 resp = self._parse_json(
-                    e.cause.read().decode(), None, fatal=False) or {}
+                    self._webpage_read_content(e.cause, url, username),
+                    username, fatal=False) or {}
                 message = resp.get('message') or resp.get('code')
             self.report_warning(message or self._LOGIN_ERR_MESSAGE)
 
@@ -211,7 +216,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                     # This usually goes away with a different random pkcs1pad, so retry
                     continue
 
-                error = self._parse_json(e.cause.read(), video_id)
+                error = self._parse_json(
+                    self._webpage_read_content(e.cause, links_url, video_id),
+                    video_id, fatal=False) or {}
                 message = error.get('message')
                 if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
                     self.raise_geo_restricted(msg=message)

youtube_dl/extractor/aenetworks.py

@@ -20,8 +20,8 @@ class AENetworksBaseIE(ThePlatformIE):
             (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
             fyi\.tv
         )/'''
-    _THEPLATFORM_KEY = 'crazyjava'
-    _THEPLATFORM_SECRET = 's3cr3t'
+    _THEPLATFORM_KEY = '43jXaGRQud'
+    _THEPLATFORM_SECRET = 'S10BPXHMlb'
     _DOMAIN_MAP = {
         'history.com': ('HISTORY', 'history'),
         'aetv.com': ('AETV', 'aetv'),

youtube_dl/extractor/americastestkitchen.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class AmericasTestKitchenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?:cooks(?:country|illustrated)/)?(?P<resource_type>episode|videos)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
         'md5': 'b861c3e365ac38ad319cfd509c30577f',
@@ -23,15 +23,20 @@ class AmericasTestKitchenIE(InfoExtractor):
             'id': '5b400b9ee338f922cb06450c',
             'title': 'Japanese Suppers',
             'ext': 'mp4',
+            'display_id': 'weeknight-japanese-suppers',
             'description': 'md5:64e606bfee910627efc4b5f050de92b3',
-            'thumbnail': r're:^https?://',
-            'timestamp': 1523318400,
-            'upload_date': '20180410',
-            'release_date': '20180410',
+            'timestamp': 1523304000,
+            'upload_date': '20180409',
+            'release_date': '20180409',
             'series': "America's Test Kitchen",
+            'season': 'Season 18',
             'season_number': 18,
             'episode': 'Japanese Suppers',
             'episode_number': 15,
+            'duration': 1376,
+            'thumbnail': r're:^https?://',
+            'average_rating': 0,
+            'view_count': int,
         },
         'params': {
             'skip_download': True,
@@ -44,15 +49,20 @@ class AmericasTestKitchenIE(InfoExtractor):
             'id': '5fbe8c61bda2010001c6763b',
             'title': 'Simple Chicken Dinner',
             'ext': 'mp4',
+            'display_id': 'atktv_2103_simple-chicken-dinner_full-episode_web-mp4',
             'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
-            'thumbnail': r're:^https?://',
-            'timestamp': 1610755200,
-            'upload_date': '20210116',
-            'release_date': '20210116',
+            'timestamp': 1610737200,
+            'upload_date': '20210115',
+            'release_date': '20210115',
             'series': "America's Test Kitchen",
+            'season': 'Season 21',
             'season_number': 21,
             'episode': 'Simple Chicken Dinner',
             'episode_number': 3,
+            'duration': 1397,
+            'thumbnail': r're:^https?://',
+            'view_count': int,
+            'average_rating': 0,
         },
         'params': {
             'skip_download': True,
@@ -60,6 +70,12 @@ class AmericasTestKitchenIE(InfoExtractor):
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cookscountry/episode/564-when-only-chocolate-will-do',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cooksillustrated/videos/4478-beef-wellington',
+        'only_matching': True,
     }, {
         'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
         'only_matching': True,
@@ -94,7 +110,7 @@ class AmericasTestKitchenIE(InfoExtractor):
 
 
 class AmericasTestKitchenSeasonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|(?P<cooks>cooks(?:country|illustrated)))\.com(?:(?:/(?P<show2>cooks(?:country|illustrated)))?(?:/?$|(?<!ated)(?<!ated\.com)/episodes/browse/season_(?P<season>\d+)))'
     _TESTS = [{
         # ATK Season
         'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
@@ -105,48 +121,93 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
         'playlist_count': 13,
     }, {
         # Cooks Country Season
-        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'url': 'https://www.americastestkitchen.com/cookscountry/episodes/browse/season_12',
         'info_dict': {
             'id': 'season_12',
             'title': 'Season 12',
         },
         'playlist_count': 13,
+    }, {
+        # America's Test Kitchen Series
+        'url': 'https://www.americastestkitchen.com/',
+        'info_dict': {
+            'id': 'americastestkitchen',
+            'title': 'America\'s Test Kitchen',
+        },
+        'playlist_count': 558,
+    }, {
+        # Cooks Country Series
+        'url': 'https://www.americastestkitchen.com/cookscountry',
+        'info_dict': {
+            'id': 'cookscountry',
+            'title': 'Cook\'s Country',
+        },
+        'playlist_count': 199,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cookscountry/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.americastestkitchen.com/cooksillustrated/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cooksillustrated.com',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        show_name, season_number = re.match(self._VALID_URL, url).groups()
-        season_number = int(season_number)
+        match = re.match(self._VALID_URL, url).groupdict()
+        show = match.get('show2')
+        show_path = ('/' + show) if show else ''
+        show = show or match['show']
+        season_number = int_or_none(match.get('season'))
 
-        slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
+        slug, title = {
+            'americastestkitchen': ('atk', 'America\'s Test Kitchen'),
+            'cookscountry': ('cco', 'Cook\'s Country'),
+            'cooksillustrated': ('cio', 'Cook\'s Illustrated'),
+        }[show]
 
-        season = 'Season %d' % season_number
+        facet_filters = [
+            'search_document_klass:episode',
+            'search_show_slug:' + slug,
+        ]
+
+        if season_number:
+            playlist_id = 'season_%d' % season_number
+            playlist_title = 'Season %d' % season_number
+            facet_filters.append('search_season_list:' + playlist_title)
+        else:
+            playlist_id = show
+            playlist_title = title
 
         season_search = self._download_json(
             'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
-            season, headers={
-                'Origin': 'https://www.%s.com' % show_name,
+            playlist_id, headers={
+                'Origin': 'https://www.americastestkitchen.com',
                 'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
                 'X-Algolia-Application-Id': 'Y1FNZXUI30',
             }, query={
-                'facetFilters': json.dumps([
-                    'search_season_list:' + season,
-                    'search_document_klass:episode',
-                    'search_show_slug:' + slug,
-                ]),
-                'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
+                'facetFilters': json.dumps(facet_filters),
+                'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title,search_atk_episode_season' % slug,
                 'attributesToHighlight': '',
                 'hitsPerPage': 1000,
             })
 
         def entries():
             for episode in (season_search.get('hits') or []):
-                search_url = episode.get('search_url')
+                search_url = episode.get('search_url')  # always formatted like '/episode/123-title-of-episode'
                 if not search_url:
                     continue
                 yield {
                     '_type': 'url',
-                    'url': 'https://www.%s.com%s' % (show_name, search_url),
-                    'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
+                    'url': 'https://www.americastestkitchen.com%s%s' % (show_path, search_url),
+                    'id': try_get(episode, lambda e: e['objectID'].rsplit('_', 1)[-1]),
                     'title': episode.get('title'),
                     'description': episode.get('description'),
                     'timestamp': unified_timestamp(episode.get('search_document_date')),
@@ -156,4 +217,4 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
                 }
 
         return self.playlist_result(
-            entries(), 'season_%d' % season_number, season)
+            entries(), playlist_id, playlist_title)

youtube_dl/extractor/blerp.py

@@ -0,0 +1,173 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from ..utils import (
+    strip_or_none,
+    traverse_obj,
+)
+from .common import InfoExtractor
+
+
+class BlerpIE(InfoExtractor):
+    IE_NAME = 'blerp'
+    _VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
+        'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
+        'info_dict': {
+            'id': '6320fe8745636cb4dd677a5a',
+            'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
+            'uploader': 'luminousaj',
+            'uploader_id': '5fb81e51aa66ae000c395478',
+            'ext': 'mp3',
+            'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
+        }
+    }, {
+        'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
+        'info_dict': {
+            'id': '5bc94ef4796001000498429f',
+            'title': 'Yee',
+            'uploader': '179617322678353920',
+            'uploader_id': '5ba99cf71386730004552c42',
+            'ext': 'mp3',
+            'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
+        }
+    }]
+
+    _GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
+    _GRAPHQL_QUERY = (
+        '''query webBitePageGetBite($_id: MongoID!) {
+            web {
+                biteById(_id: $_id) {
+                    ...bitePageFrag
+                    __typename
+                }
+                __typename
+            }
+        }
+
+        fragment bitePageFrag on Bite {
+            _id
+            title
+            userKeywords
+            keywords
+            color
+            visibility
+            isPremium
+            owned
+            price
+            extraReview
+            isAudioExists
+            image {
+                filename
+                original {
+                    url
+                    __typename
+                }
+                __typename
+            }
+            userReactions {
+                _id
+                reactions
+                createdAt
+                __typename
+            }
+            topReactions
+            totalSaveCount
+            saved
+            blerpLibraryType
+            license
+            licenseMetaData
+            playCount
+            totalShareCount
+            totalFavoriteCount
+            totalAddedToBoardCount
+            userCategory
+            userAudioQuality
+            audioCreationState
+            transcription
+            userTranscription
+            description
+            createdAt
+            updatedAt
+            author
+            listingType
+            ownerObject {
+                _id
+                username
+                profileImage {
+                    filename
+                    original {
+                        url
+                        __typename
+                    }
+                    __typename
+                }
+                __typename
+            }
+            transcription
+            favorited
+            visibility
+            isCurated
+            sourceUrl
+            audienceRating
+            strictAudienceRating
+            ownerId
+            reportObject {
+                reportedContentStatus
+                __typename
+            }
+            giphy {
+                mp4
+                gif
+                __typename
+            }
+            audio {
+                filename
+                original {
+                    url
+                    __typename
+                }
+                mp3 {
+                    url
+                    __typename
+                }
+                __typename
+            }
+            __typename
+        }
+
+        ''')
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        data = {
+            'operationName': self._GRAPHQL_OPERATIONNAME,
+            'query': self._GRAPHQL_QUERY,
+            'variables': {
+                '_id': audio_id
+            }
+        }
+
+        headers = {
+            'Content-Type': 'application/json'
+        }
+
+        json_result = self._download_json('https://api.blerp.com/graphql',
+                                          audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
+
+        bite_json = json_result['data']['web']['biteById']
+
+        info_dict = {
+            'id': bite_json['_id'],
+            'url': bite_json['audio']['mp3']['url'],
+            'title': bite_json['title'],
+            'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
+            'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
+            'ext': 'mp3',
+            'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
+        }
+
+        return info_dict

youtube_dl/extractor/bongacams.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -12,13 +13,28 @@ from ..utils import (
 
 
 class BongaCamsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.com)/(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://de.bongacams.com/azumi-8',
         'only_matching': True,
     }, {
         'url': 'https://cn.bongacams.com/azumi-8',
         'only_matching': True,
+    }, {
+        'url': 'https://de.bongacams.net/claireashton',
+        'info_dict': {
+            'id': 'claireashton',
+            'ext': 'mp4',
+            'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'age_limit': 18,
+            'uploader_id': 'ClaireAshton',
+            'uploader': 'ClaireAshton',
+            'like_count': int,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/callin.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    traverse_obj,
+    try_get,
+)
+
+
+class CallinIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?:[^/#?-]+-)*(?P<id>[^/#?-]+)'
+    _TESTS = [{
+        'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW',
+        'md5': '14ede27ee2c957b7e4db93140fc0745c',
+        'info_dict': {
+            'id': 'PrumRdSQJW',
+            'ext': 'mp4',
+            'title': 'FCC Commissioner Brendan Carr on Elon’s Starlink',
+            'description': 'Or, why the government doesn’t like SpaceX',
+            'channel': 'The Pull Request',
+            'channel_url': 'https://callin.com/show/the-pull-request-ucnDJmEKAa',
+        }
+    }, {
+        'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA',
+        'md5': '16f704ddbf82a27e3930533b12062f07',
+        'info_dict': {
+            'id': 'lzxMidUnjA',
+            'ext': 'mp4',
+            'title': 'Episode 81- Elites MELT DOWN over Student Debt Victory? Rumble in NYC?',
+            'description': 'Let’s talk todays episode about the primary election shake up in NYC and the elites melting down over student debt cancelation.',
+            'channel': 'The DEBRIEF With Briahna Joy Gray',
+            'channel_url': 'https://callin.com/show/the-debrief-with-briahna-joy-gray-siiFDzGegm',
+        }
+    }]
+
+    def _search_nextjs_data(self, webpage, video_id, transform_source=None, fatal=True, **kw):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
+                webpage, 'next.js data', fatal=fatal, **kw),
+            video_id, transform_source=transform_source, fatal=fatal)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        next_data = self._search_nextjs_data(webpage, video_id)
+        episode = traverse_obj(next_data, ('props', 'pageProps', 'episode'), expected_type=dict)
+        if not episode:
+            raise ExtractorError('Failed to find episode data')
+
+        title = episode.get('title') or self._og_search_title(webpage)
+        description = episode.get('description') or self._og_search_description(webpage)
+
+        formats = []
+        formats.extend(self._extract_m3u8_formats(
+            episode.get('m3u8'), video_id, 'mp4',
+            entry_protocol='m3u8_native', fatal=False))
+        self._sort_formats(formats)
+
+        channel = try_get(episode, lambda x: x['show']['title'], compat_str)
+        channel_url = try_get(episode, lambda x: x['show']['linkObj']['resourceUrl'], compat_str)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'channel': channel,
+            'channel_url': channel_url,
+        }

youtube_dl/extractor/cammodels.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     int_or_none,
     url_or_none,
 )
@@ -20,32 +19,11 @@ class CamModelsIE(InfoExtractor):
     def _real_extract(self, url):
         user_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            url, user_id, headers=self.geo_verification_headers())
-
-        manifest_root = self._html_search_regex(
-            r'manifestUrlRoot=([^&\']+)', webpage, 'manifest', default=None)
-
-        if not manifest_root:
-            ERRORS = (
-                ("I'm offline, but let's stay connected", 'This user is currently offline'),
-                ('in a private show', 'This user is in a private show'),
-                ('is currently performing LIVE', 'This model is currently performing live'),
-            )
-            for pattern, message in ERRORS:
-                if pattern in webpage:
-                    error = message
-                    expected = True
-                    break
-            else:
-                error = 'Unable to find manifest URL root'
-                expected = False
-            raise ExtractorError(error, expected=expected)
-
         manifest = self._download_json(
-            '%s%s.json' % (manifest_root, user_id), user_id)
+            'https://manifest-server.naiadsystems.com/live/s:%s.json' % user_id, user_id)
 
         formats = []
+        thumbnails = []
         for format_id, format_dict in manifest['formats'].items():
             if not isinstance(format_dict, dict):
                 continue
@@ -85,6 +63,13 @@ class CamModelsIE(InfoExtractor):
                         'preference': -1,
                     })
                 else:
+                    if format_id == 'jpeg':
+                        thumbnails.append({
+                            'url': f['url'],
+                            'width': f['width'],
+                            'height': f['height'],
+                            'format_id': f['format_id'],
+                        })
                     continue
                 formats.append(f)
         self._sort_formats(formats)
@@ -92,6 +77,7 @@ class CamModelsIE(InfoExtractor):
         return {
             'id': user_id,
             'title': self._live_title(user_id),
+            'thumbnails': thumbnails,
             'is_live': True,
             'formats': formats,
             'age_limit': 18

youtube_dl/extractor/ceskatelevize.py

@@ -12,35 +12,21 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
-    unescapeHTML,
-    update_url_query,
+    str_or_none,
+    traverse_obj,
     urlencode_postdata,
     USER_AGENTS,
 )
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
     _TESTS = [{
-        'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
-        'info_dict': {
-            'id': '61924494877246241',
-            'ext': 'mp4',
-            'title': 'Hyde Park Civilizace: Život v Grónsku',
-            'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
-            'thumbnail': r're:^https?://.*\.jpg',
-            'duration': 3350,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
         'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
         'info_dict': {
             'id': '61924494877028507',
             'ext': 'mp4',
-            'title': 'Hyde Park Civilizace: Bonus 01 - En',
+            'title': 'Bonus 01 - En - Hyde Park Civilizace',
             'description': 'English Subtittles',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 81.3,
@@ -51,31 +37,111 @@ class CeskaTelevizeIE(InfoExtractor):
         },
     }, {
         # live stream
-        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'url': 'http://www.ceskatelevize.cz/zive/ct1/',
         'info_dict': {
-            'id': 402,
+            'id': '102',
             'ext': 'mp4',
-            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'title': r'ČT1 - živé vysílání online',
+            'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
             'is_live': True,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
-        'skip': 'Georestricted to Czech Republic',
+    }, {
+        # another
+        'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
+        'only_matching': True,
+        'info_dict': {
+            'id': 402,
+            'ext': 'mp4',
+            'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'is_live': True,
+        },
+        # 'skip': 'Georestricted to Czech Republic',
     }, {
         'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
         'only_matching': True,
+    }, {
+        # video with 18+ caution trailer
+        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
+        'info_dict': {
+            'id': '215562210900007-bogotart',
+            'title': 'Bogotart - Queer',
+            'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '61924494877311053',
+                'ext': 'mp4',
+                'title': 'Bogotart - Queer (Varování 18+)',
+                'duration': 11.9,
+            },
+        }, {
+            'info_dict': {
+                'id': '61924494877068022',
+                'ext': 'mp4',
+                'title': 'Bogotart - Queer (Queer)',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'duration': 1558.3,
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # iframe embed
+        'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
+        'only_matching': True,
     }]
 
+    def _search_nextjs_data(self, webpage, video_id, **kw):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
+                webpage, 'next.js data', **kw),
+            video_id, **kw)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
+        webpage, urlh = self._download_webpage_handle(url, playlist_id)
+        parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
+        site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
+        playlist_title = self._og_search_title(webpage, default=None)
+        if site_name and playlist_title:
+            playlist_title = re.split(r'\s*[—|]\s*%s' % (site_name, ), playlist_title, 1)[0]
+        playlist_description = self._og_search_description(webpage, default=None)
+        if playlist_description:
+            playlist_description = playlist_description.replace('\xa0', ' ')
 
-        webpage = self._download_webpage(url, playlist_id)
+        type_ = 'IDEC'
+        if re.search(r'(^/porady|/zive)/', parsed_url.path):
+            next_data = self._search_nextjs_data(webpage, playlist_id)
+            if '/zive/' in parsed_url.path:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
+            else:
+                idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
+                if not idec:
+                    idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
+                    if idec:
+                        type_ = 'bonus'
+            if not idec:
+                raise ExtractorError('Failed to find IDEC id')
+            iframe_hash = self._download_webpage(
+                'https://www.ceskatelevize.cz/v-api/iframe-hash/',
+                playlist_id, note='Getting IFRAME hash')
+            query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec, }
+            webpage = self._download_webpage(
+                'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
+                playlist_id, note='Downloading player', query=query)
 
         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
-            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+            self.raise_geo_restricted(NOT_AVAILABLE_STRING)
+        if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen', )):
+            raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
 
         type_ = None
         episode_id = None
@@ -100,7 +166,7 @@ class CeskaTelevizeIE(InfoExtractor):
         data = {
             'playlist[0][type]': type_,
             'playlist[0][id]': episode_id,
-            'requestUrl': compat_urllib_parse_urlparse(url).path,
+            'requestUrl': parsed_url.path,
             'requestSource': 'iVysilani',
         }
 
@@ -108,7 +174,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(
-                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
                 data=urlencode_postdata(data))
 
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
@@ -130,9 +196,6 @@ class CeskaTelevizeIE(InfoExtractor):
             req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
             req.add_header('Referer', url)
 
-            playlist_title = self._og_search_title(webpage, default=None)
-            playlist_description = self._og_search_description(webpage, default=None)
-
             playlist = self._download_json(req, playlist_id, fatal=False)
             if not playlist:
                 continue
@@ -167,7 +230,7 @@ class CeskaTelevizeIE(InfoExtractor):
                     entries[num]['formats'].extend(formats)
                     continue
 
-                item_id = item.get('id') or item['assetId']
+                item_id = str_or_none(item.get('id') or item['assetId'])
                 title = item['title']
 
                 duration = float_or_none(item.get('duration'))
@@ -181,8 +244,6 @@ class CeskaTelevizeIE(InfoExtractor):
 
                 if playlist_len == 1:
                     final_title = playlist_title or title
-                    if is_live:
-                        final_title = self._live_title(final_title)
                 else:
                     final_title = '%s (%s)' % (playlist_title, title)
 
@@ -200,6 +261,8 @@ class CeskaTelevizeIE(InfoExtractor):
         for e in entries:
             self._sort_formats(e['formats'])
 
+        if len(entries) == 1:
+            return entries[0]
         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 
     def _get_subtitles(self, episode_id, subs):
@@ -236,54 +299,3 @@ class CeskaTelevizeIE(InfoExtractor):
                     yield line
 
         return '\r\n'.join(_fix_subtitle(subtitles))
-
-
-class CeskaTelevizePoradyIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
-    _TESTS = [{
-        # video with 18+ caution trailer
-        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
-        'info_dict': {
-            'id': '215562210900007-bogotart',
-            'title': 'Queer: Bogotart',
-            'description': 'Alternativní průvodce současným queer světem',
-        },
-        'playlist': [{
-            'info_dict': {
-                'id': '61924494876844842',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Varování 18+)',
-                'duration': 10.2,
-            },
-        }, {
-            'info_dict': {
-                'id': '61924494877068022',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Queer)',
-                'thumbnail': r're:^https?://.*\.jpg',
-                'duration': 1558.3,
-            },
-        }],
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }, {
-        # iframe embed
-        'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        data_url = update_url_query(unescapeHTML(self._search_regex(
-            (r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
-             r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
-            webpage, 'iframe player url', group='url')), query={
-                'autoStart': 'true',
-        })
-
-        return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

youtube_dl/extractor/common.py

@@ -70,6 +70,7 @@ from ..utils import (
     str_or_none,
     str_to_int,
     strip_or_none,
+    try_get,
     unescapeHTML,
     unified_strdate,
     unified_timestamp,
@@ -2713,7 +2714,7 @@ class InfoExtractor(object):
 
     def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
         mobj = re.search(
-            r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
+            r'''(?s)jwplayer\s*\(\s*(?P<q>'|")(?!(?P=q)).+(?P=q)\s*\)(?!</script>).*?\.\s*setup\s*\(\s*(?P<options>(?:\([^)]*\)|[^)])+)\s*\)''',
             webpage)
         if mobj:
             try:
@@ -2734,9 +2735,14 @@ class InfoExtractor(object):
 
     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):
+        flat_pl = try_get(jwplayer_data, lambda x: x.get('playlist') or True)
+        if flat_pl is None:
+            # not even a dict
+            return []
+
         # JWPlayer backward compatibility: flattened playlists
         # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
-        if 'playlist' not in jwplayer_data:
+        if flat_pl is True:
             jwplayer_data = {'playlist': [jwplayer_data]}
 
         entries = []
@@ -2784,6 +2790,13 @@ class InfoExtractor(object):
                 'timestamp': int_or_none(video_data.get('pubdate')),
                 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),
                 'subtitles': subtitles,
+                'alt_title': clean_html(video_data.get('subtitle')),  # attributes used e.g. by Tele5 ...
+                'genre': clean_html(video_data.get('genre')),
+                'channel': clean_html(dict_get(video_data, ('category', 'channel'))),
+                'season_number': int_or_none(video_data.get('season')),
+                'episode_number': int_or_none(video_data.get('episode')),
+                'release_year': int_or_none(video_data.get('releasedate')),
+                'age_limit': int_or_none(video_data.get('age_restriction')),
             }
             # https://github.com/jwplayer/jwplayer/blob/master/src/js/utils/validator.js#L32
             if len(formats) == 1 and re.search(r'^(?:http|//).*(?:youtube\.com|youtu\.be)/.+', formats[0]['url']):
@@ -2792,7 +2805,9 @@ class InfoExtractor(object):
                     'url': formats[0]['url'],
                 })
             else:
-                self._sort_formats(formats)
+                # avoid exception in case of only sttls
+                if formats:
+                    self._sort_formats(formats)
                 entry['formats'] = formats
             entries.append(entry)
         if len(entries) == 1:
@@ -2802,7 +2817,7 @@ class InfoExtractor(object):
 
     def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
                                 m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
-        urls = []
+        urls = set()
         formats = []
         for source in jwplayer_sources_data:
             if not isinstance(source, dict):
@@ -2811,14 +2826,14 @@ class InfoExtractor(object):
                 base_url, self._proto_relative_url(source.get('file')))
             if not source_url or source_url in urls:
                 continue
-            urls.append(source_url)
+            urls.add(source_url)
             source_type = source.get('type') or ''
             ext = mimetype2ext(source_type) or determine_ext(source_url)
-            if source_type == 'hls' or ext == 'm3u8':
+            if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url:
                 formats.extend(self._extract_m3u8_formats(
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id=m3u8_id, fatal=False))
-            elif source_type == 'dash' or ext == 'mpd':
+            elif source_type == 'dash' or ext == 'mpd' or 'format=mpd-time-csf' in source_url:
                 formats.extend(self._extract_mpd_formats(
                     source_url, video_id, mpd_id=mpd_id, fatal=False))
             elif ext == 'smil':
@@ -2833,20 +2848,23 @@ class InfoExtractor(object):
                     'ext': ext,
                 })
             else:
+                format_id = str_or_none(source.get('label'))
                 height = int_or_none(source.get('height'))
-                if height is None:
+                if height is None and format_id:
                     # Often no height is provided but there is a label in
                     # format like "1080p", "720p SD", or 1080.
-                    height = int_or_none(self._search_regex(
-                        r'^(\d{3,4})[pP]?(?:\b|$)', compat_str(source.get('label') or ''),
-                        'height', default=None))
+                    height = parse_resolution(format_id).get('height')
                 a_format = {
                     'url': source_url,
                     'width': int_or_none(source.get('width')),
                     'height': height,
-                    'tbr': int_or_none(source.get('bitrate')),
+                    'tbr': int_or_none(source.get('bitrate'), scale=1000),
+                    'filesize': int_or_none(source.get('filesize')),
                     'ext': ext,
                 }
+                if format_id:
+                    a_format['format_id'] = format_id
+
                 if source_url.startswith('rtmp'):
                     a_format['ext'] = 'flv'
                     # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as

youtube_dl/extractor/extractors.py

@@ -139,6 +139,7 @@ from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
 )
+from .blerp import BlerpIE
 from .bloomberg import BloombergIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE
@@ -159,6 +160,7 @@ from .businessinsider import BusinessInsiderIE
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
+from .callin import CallinIE
 from .camdemy import (
     CamdemyIE,
     CamdemyFolderIE
@@ -209,10 +211,7 @@ from .ccc import (
 from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
-from .ceskatelevize import (
-    CeskaTelevizeIE,
-    CeskaTelevizePoradyIE,
-)
+from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
@@ -378,6 +377,7 @@ from .fc2 import (
     FC2EmbedIE,
 )
 from .fczenit import FczenitIE
+from .fifa import FifaIE
 from .filmon import (
     FilmOnIE,
     FilmOnChannelIE,
@@ -729,6 +729,7 @@ from .myvi import (
     MyviIE,
     MyviEmbedIE,
 )
+from .myvideoge import MyVideoGeIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import (
     NationalGeographicVideoIE,
@@ -913,6 +914,10 @@ from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
 from .pearvideo import PearVideoIE
+from .peekvids import (
+    PeekVidsIE,
+    PlayVidsIE,
+)
 from .peertube import PeerTubeIE
 from .people import PeopleIE
 from .performgroup import PerformGroupIE
@@ -1265,6 +1270,11 @@ from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
 from .thisoldhouse import ThisOldHouseIE
+from .thisvid import (
+    ThisVidIE,
+    ThisVidMemberIE,
+    ThisVidPlaylistIE,
+)
 from .threeqsdn import ThreeQSDNIE
 from .tiktok import (
     TikTokIE,
@@ -1662,3 +1672,7 @@ from .zingmp3 import (
 )
 from .zoom import ZoomIE
 from .zype import ZypeIE
+from .pr0gramm import (
+    Pr0grammIE,
+    Pr0grammStaticIE,
+)

youtube_dl/extractor/fifa.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    int_or_none,
+    traverse_obj,
+    unified_timestamp,
+)
+
+if not callable(getattr(InfoExtractor, '_match_valid_url', None)):
+
+    BaseInfoExtractor = InfoExtractor
+
+    import re
+
+    class InfoExtractor(BaseInfoExtractor):
+
+        @classmethod
+        def _match_valid_url(cls, url):
+            return re.match(cls._VALID_URL, url)
+
+
+class FifaIE(InfoExtractor):
+    _VALID_URL = r'https?://www.fifa.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
+        'info_dict': {
+            'id': '7on10qPcnyLajDDU3ntg6y',
+            'title': 'Italy v France | Final | 2006 FIFA World Cup Germany™ | Full Match Replay',
+            'description': 'md5:f4520d0ee80529c8ba4134a7d692ff8b',
+            'ext': 'mp4',
+            'categories': ['FIFA Tournaments'],
+            'thumbnail': 'https://digitalhub.fifa.com/transform/135e2656-3a51-407b-8810-6c34bec5b59b/FMR_2006_Italy_France_Final_Hero',
+            'duration': 8165,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.fifa.com/fifaplus/pt/watch/1cg5r5Qt6Qt12ilkDgb1sV',
+        'info_dict': {
+            'id': '1cg5r5Qt6Qt12ilkDgb1sV',
+            'title': 'Brazil v Germany | Semi-finals | 2014 FIFA World Cup Brazil™ | Extended Highlights',
+            'description': 'md5:d908c74ee66322b804ae2e521b02a855',
+            'ext': 'mp4',
+            'categories': ['FIFA Tournaments', 'Highlights'],
+            'thumbnail': 'https://digitalhub.fifa.com/transform/d8fe6f61-276d-4a73-a7fe-6878a35fd082/FIFAPLS_100EXTHL_2014BRAvGER_TMB',
+            'duration': 902,
+            'release_timestamp': 1404777600,
+            'release_date': '20140708',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.fifa.com/fifaplus/fr/watch/3C6gQH9C2DLwzNx7BMRQdp',
+        'info_dict': {
+            'id': '3C6gQH9C2DLwzNx7BMRQdp',
+            'title': 'Josimar goal against Northern Ireland | Classic Goals',
+            'description': 'md5:cbe7e7bb52f603c9f1fe9a4780fe983b',
+            'ext': 'mp4',
+            'categories': ['FIFA Tournaments', 'Goal'],
+            'duration': 28,
+            'thumbnail': 'https://digitalhub.fifa.com/transform/f9301391-f8d9-48b5-823e-c093ac5e3e11/CG_MEN_1986_JOSIMAR',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        video_id, locale = self._match_valid_url(url).group('id', 'locale')
+        webpage = self._download_webpage(url, video_id)
+
+        preconnect_link = self._search_regex(
+            r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"', webpage, 'Preconnect Link')
+
+        video_details = self._download_json(
+            '{preconnect_link}/sections/videoDetails/{video_id}'.format(**locals()), video_id, 'Downloading Video Details', fatal=False)
+
+        preplay_parameters = self._download_json(
+            '{preconnect_link}/videoPlayerData/{video_id}'.format(**locals()), video_id, 'Downloading Preplay Parameters')['preplayParameters']
+
+        content_data = self._download_json(
+            # 1. query string is expected to be sent as-is
+            # 2. `sig` must be appended
+            # 3. if absent, the call appears to work but the manifest is bad (404)
+            'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(**preplay_parameters),
+            video_id, 'Downloading Content Data')
+
+        # formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], video_id)
+        formats, subtitles = self._extract_m3u8_formats(content_data['playURL'], video_id, ext='mp4', entry_protocol='m3u8_native'), None
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_details['title'],
+            'description': video_details.get('description'),
+            'duration': int_or_none(video_details.get('duration')),
+            'release_timestamp': unified_timestamp(video_details.get('dateOfRelease')),
+            'categories': traverse_obj(video_details, (('videoCategory', 'videoSubcategory'),)),
+            'thumbnail': traverse_obj(video_details, ('backgroundImage', 'src')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/generic.py

@@ -28,6 +28,7 @@ from ..utils import (
     mimetype2ext,
     orderedSet,
     parse_duration,
+    parse_resolution,
     sanitized_Request,
     smuggle_url,
     unescapeHTML,
@@ -35,6 +36,7 @@ from ..utils import (
     unsmuggle_url,
     UnsupportedError,
     url_or_none,
+    urljoin,
     xpath_attr,
     xpath_text,
     xpath_with_ns,
@@ -2227,6 +2229,97 @@ class GenericIE(InfoExtractor):
             # Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
             'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
             'only_matching': True,
+        }, {
+            # KVS Player
+            'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
+            'info_dict': {
+                'id': '105',
+                'display_id': 'kelis-4th-of-july',
+                'ext': 'mp4',
+                'title': 'Kelis - 4th Of July',
+                'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://www.kvs-demo.com/embed/105/',
+            'info_dict': {
+                'id': '105',
+                'display_id': 'kelis-4th-of-july',
+                'ext': 'mp4',
+                'title': 'Kelis - 4th Of July / Embed Player',
+                'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        }, {
+            # KVS Player (tested also in thisvid.py)
+            'url': 'https://youix.com/video/leningrad-zoj/',
+            'md5': '94f96ba95706dc3880812b27b7d8a2b8',
+            'info_dict': {
+                'id': '18485',
+                'display_id': 'leningrad-zoj',
+                'ext': 'mp4',
+                'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
+                'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://youix.com/embed/18485',
+            'md5': '94f96ba95706dc3880812b27b7d8a2b8',
+            'info_dict': {
+                'id': '18485',
+                'display_id': 'leningrad-zoj',
+                'ext': 'mp4',
+                'title': 'Ленинград - ЗОЖ',
+                'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
+            },
+        }, {
+            # KVS Player
+            'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
+            'md5': '94166bdb26b4cb1fb9214319a629fc51',
+            'info_dict': {
+                'id': '21217',
+                'display_id': '40-nochey-2016',
+                'ext': 'mp4',
+                'title': '40 ночей (2016) - BogMedia.org',
+                'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
+                'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
+            },
+        }, {
+            # KVS Player (for sites that serve kt_player.js via non-https urls)
+            'url': 'http://www.camhub.world/embed/389508',
+            'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
+            'info_dict': {
+                'id': '389508',
+                'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
+                'ext': 'mp4',
+                'title': 'Syren De Mer  onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
+                'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
+            },
+        }, {
+            'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
+            'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
+            'info_dict': {
+                'id': '5',
+                'display_id': 'selena-gomez-pov-deep-fakes',
+                'ext': 'mp4',
+                'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
+                'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
+                'height': 720,
+                'age_limit': 18,
+            },
+        }, {
+            'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
+            'md5': 'e2f0a4c329f7986280b7328e24036d60',
+            'info_dict': {
+                'id': '284002',
+                'display_id': 'just-out-of-the-shower-joi',
+                'ext': 'mp4',
+                'title': 'Just Out Of The Shower JOI - Shooshtime',
+                'height': 720,
+                'age_limit': 18,
+            },
         },
     ]
 
@@ -2332,6 +2425,88 @@ class GenericIE(InfoExtractor):
             'title': title,
         }
 
+    def _extract_kvs(self, url, webpage, video_id):
+
+        def getlicensetoken(license):
+            modlicense = license.replace('$', '').replace('0', '1')
+            center = int(len(modlicense) / 2)
+            fronthalf = int(modlicense[:center + 1])
+            backhalf = int(modlicense[center:])
+
+            modlicense = compat_str(4 * abs(fronthalf - backhalf))
+
+            def parts():
+                for o in range(0, center + 1):
+                    for i in range(1, 5):
+                        yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
+
+            return ''.join(parts())
+
+        def getrealurl(video_url, license_code):
+            if not video_url.startswith('function/0/'):
+                return video_url  # not obfuscated
+
+            url_path, _, url_query = video_url.partition('?')
+            urlparts = url_path.split('/')[2:]
+            license = getlicensetoken(license_code)
+            newmagic = urlparts[5][:32]
+
+            def spells(x, o):
+                l = (o + sum(int(n) for n in license[o:])) % 32
+                for i in range(0, len(x)):
+                    yield {l: x[o], o: x[l]}.get(i, x[i])
+
+            for o in range(len(newmagic) - 1, -1, -1):
+                newmagic = ''.join(spells(newmagic, o))
+
+            urlparts[5] = newmagic + urlparts[5][32:]
+            return '/'.join(urlparts) + '?' + url_query
+
+        flashvars = self._search_regex(
+            r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
+            webpage, 'flashvars')
+        flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
+
+        # extract the part after the last / as the display_id from the
+        # canonical URL.
+        display_id = self._search_regex(
+            r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
+            r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
+            webpage, 'display_id', fatal=False
+        )
+        title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
+
+        thumbnail = flashvars['preview_url']
+        if thumbnail.startswith('//'):
+            protocol, _, _ = url.partition('/')
+            thumbnail = protocol + thumbnail
+
+        url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
+        formats = []
+        for key in url_keys:
+            if '/get_file/' not in flashvars[key]:
+                continue
+            format_id = flashvars.get(key + '_text', key)
+            formats.append(merge_dicts(
+                parse_resolution(format_id) or parse_resolution(flashvars[key]), {
+                    'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
+                    'format_id': format_id,
+                    'ext': 'mp4',
+                    'http_headers': {'Referer': url},
+                }))
+            if not formats[-1].get('height'):
+                formats[-1]['quality'] = 1
+
+        self._sort_formats(formats)
+
+        return {
+            'id': flashvars['video_id'],
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
+
     def _real_extract(self, url):
         if url.startswith('//'):
             return self.url_result(self.http_scheme() + url)
@@ -2540,9 +2715,16 @@ class GenericIE(InfoExtractor):
         # but actually don't.
         AGE_LIMIT_MARKERS = [
             r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
+            r'>[^<]*you acknowledge you are at least (\d+) years old',
+            r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
         ]
-        if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
-            age_limit = 18
+        for marker in AGE_LIMIT_MARKERS:
+            m = re.search(marker, webpage)
+            if not m:
+                continue
+            age_limit = max(
+                age_limit or 0,
+                int_or_none(m.groups() and m.group(1), default=18))
 
         # video uploader is domain name
         video_uploader = self._search_regex(
@@ -3389,6 +3571,20 @@ class GenericIE(InfoExtractor):
                 info_dict['formats'] = formats
                 return info_dict
 
+        # Look for generic KVS player (before ld+json for tests)
+        found = self._search_regex(
+            (r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>\d+(?:\.\d+)+)\1[^>]*>',
+             # kt_player('kt_player', 'https://i.shoosh.co/player/kt_player.swf?v=5.5.1', ...
+             r'kt_player\s*\(\s*(["\'])(?:(?!\1)[\w\W])+\1\s*,\s*(["\'])https?://(?:\S+?/)+kt_player\.swf\?v=(?P<ver>\d+(?:\.\d+)+)\2\s*,',
+             ), webpage, 'KVS player', group='ver', default=False)
+        if found:
+            self.report_extraction('%s: KVS Player' % (video_id, ))
+            if found.split('.')[0] not in ('4', '5', '6'):
+                self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
+            return merge_dicts(
+                self._extract_kvs(url, webpage, video_id),
+                info_dict)
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/infoq.py

@@ -1,6 +1,9 @@
 # coding: utf-8
 
 from __future__ import unicode_literals
+from ..utils import (
+    ExtractorError,
+)
 
 from ..compat import (
     compat_b64decode,
@@ -90,7 +93,11 @@ class InfoQIE(BokeCCBaseIE):
         }]
 
     def _extract_http_audio(self, webpage, video_id):
-        fields = self._form_hidden_inputs('mp3Form', webpage)
+        try:
+            fields = self._form_hidden_inputs('mp3Form', webpage)
+        except ExtractorError:
+            fields = {}
+
         http_audio_url = fields.get('filename')
         if not http_audio_url:
             return []

youtube_dl/extractor/itv.py

@@ -3,123 +3,266 @@ from __future__ import unicode_literals
 
 import json
 import re
+import sys
 
 from .common import InfoExtractor
 from .brightcove import BrightcoveNewIE
+from ..compat import (
+    compat_HTTPError,
+    compat_integer_types,
+    compat_kwargs,
+    compat_urlparse,
+)
 from ..utils import (
     clean_html,
     determine_ext,
+    error_to_compat_str,
     extract_attributes,
-    get_element_by_class,
-    JSON_LD_RE,
+    ExtractorError,
+    get_element_by_attribute,
+    int_or_none,
     merge_dicts,
     parse_duration,
+    parse_iso8601,
+    remove_start,
     smuggle_url,
+    strip_or_none,
+    traverse_obj,
     url_or_none,
+    urljoin,
 )
 
 
-class ITVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
-    _GEO_COUNTRIES = ['GB']
+class ITVBaseIE(InfoExtractor):
+
+    def _search_nextjs_data(self, webpage, video_id, **kw):
+        transform_source = kw.pop('transform_source', None)
+        fatal = kw.pop('fatal', True)
+        return self._parse_json(
+            self._search_regex(
+                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
+                webpage, 'next.js data', group='js', fatal=fatal, **kw),
+            video_id, transform_source=transform_source, fatal=fatal)
+
+    def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
+        if errnote is False:
+            return False
+        if errnote is None:
+            errnote = 'Unable to download webpage'
+
+        errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
+        if fatal:
+            raise ExtractorError(errmsg, sys.exc_info()[2], cause=err, video_id=video_id)
+        else:
+            self._downloader.report_warning(errmsg)
+            return False
+
+    @staticmethod
+    def _vanilla_ua_header():
+        return {'User-agent': 'Mozilla/5.0'}
+
+    def _download_webpage_handle(self, url, video_id, *args, **kwargs):
+        # specialised to (a) use vanilla UA (b) detect geo-block
+        params = self._downloader.params
+        nkwargs = {}
+        if (
+                'user_agent' not in params
+                and not any(re.match(r'(?i)user-agent\s*:', h)
+                            for h in (params.get('headers') or []))
+                and 'User-agent' not in (kwargs.get('headers') or {})):
+
+            kwargs.setdefault('headers', {})
+            kwargs['headers'] = self._vanilla_ua_header()
+            nkwargs = kwargs
+        if kwargs.get('expected_status') is not None:
+            exp = kwargs['expected_status']
+            if isinstance(exp, compat_integer_types):
+                exp = [exp]
+            if isinstance(exp, (list, tuple)) and 403 not in exp:
+                kwargs['expected_status'] = [403]
+                kwargs['expected_status'].extend(exp)
+                nkwargs = kwargs
+        else:
+            kwargs['expected_status'] = 403
+            nkwargs = kwargs
+
+        if nkwargs:
+            kwargs = compat_kwargs(kwargs)
+
+        ret = super(ITVBaseIE, self)._download_webpage_handle(url, video_id, *args, **kwargs)
+        if ret is False:
+            return ret
+        webpage, urlh = ret
+
+        if urlh.getcode() == 403:
+            # geo-block error is like this, with an unnecessary 'Of':
+            # '{\n  "Message" : "Request Originated Outside Of Allowed Geographic Region",\
+            # \n  "TransactionId" : "oas-magni-475082-xbYF0W"\n}'
+            if '"Request Originated Outside Of Allowed Geographic Region"' in webpage:
+                self.raise_geo_restricted(countries=['GB'])
+            ret = self.__handle_request_webpage_error(
+                compat_HTTPError(urlh.geturl(), 403, 'HTTP Error 403: Forbidden', urlh.headers, urlh),
+                fatal=kwargs.get('fatal'))
+
+        return ret
+
+
+class ITVIE(ITVBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
+    _IE_DESC = 'ITVX'
     _TESTS = [{
+        'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
-        'info_dict': {
-            'id': '2a4547a0012',
-            'ext': 'mp4',
-            'title': 'Liar - Series 2 - Episode 6',
-            'description': 'md5:d0f91536569dec79ea184f0a44cca089',
-            'series': 'Liar',
-            'season_number': 2,
-            'episode_number': 6,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
+        'only_matching': True,
     }, {
-        # unavailable via data-playlist-url
+        'note': 'Hub page unavailable via data-playlist-url (404 now)',
         'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
         'only_matching': True,
     }, {
-        # InvalidVodcrid
+        'note': 'Hub page with InvalidVodcrid (404 now)',
         'url': 'https://www.itv.com/hub/james-martins-saturday-morning/2a5159a0034',
         'only_matching': True,
     }, {
-        # ContentUnavailable
+        'note': 'Hub page with ContentUnavailable (404 now)',
         'url': 'https://www.itv.com/hub/whos-doing-the-dishes/2a2898a0024',
         'only_matching': True,
-    }]
+    }, {
+        'note': 'ITVX, or itvX, show',
+        'url': 'https://www.itv.com/watch/vera/1a7314/1a7314a0014',
+        'md5': 'bd0ad666b2c058fffe7d036785880064',
+        'info_dict': {
+            'id': '1a7314a0014',
+            'ext': 'mp4',
+            'title': 'Vera - Series 3 - Episode 4 - Prodigal Son',
+            'description': 'Vera and her team investigate the fatal stabbing of an ex-Met police officer outside a busy Newcastle nightclub - but there aren\'t many clues.',
+            'timestamp': 1653591600,
+            'upload_date': '20220526',
+            'uploader': 'ITVX',
+            'thumbnail': r're:https://\w+\.itv\.com/images/(?:\w+/)+\d+x\d+\?',
+            'duration': 5340.8,
+            'age_limit': 16,
+            'series': 'Vera',
+            'series_number': 3,
+            'episode': 'Prodigal Son',
+            'episode_number': 4,
+            'channel': 'ITV3',
+            'categories': list,
+        },
+        'params': {
+            # m3u8 download
+            # 'skip_download': True,
+        },
+        'skip': 'only available in UK',
+    }, {
+        'note': 'Latest ITV news bulletin: details change daily',
+        'url': 'https://www.itv.com/watch/news/varies-but-is-not-checked/6js5d0f',
+        'info_dict': {
+            'id': '6js5d0f',
+            'ext': 'mp4',
+            'title': r're:The latest ITV News headlines - \S.+',
+            'description': r'''re:.* today's top stories from the ITV News team.$''',
+            'timestamp': int,
+            'upload_date': r're:2\d\d\d(?:0[1-9]|1[0-2])(?:[012][1-9]|3[01])',
+            'uploader': 'ITVX',
+            'thumbnail': r're:https://images\.ctfassets\.net/(?:\w+/)+[\w.]+\.(?:jpg|png)',
+            'duration': float,
+            'age_limit': None,
+        },
+        'params': {
+            # variable download
+            # 'skip_download': True,
+        },
+        'skip': 'only available in UK',
+    }
+    ]
+
+    def _og_extract(self, webpage, require_title=False):
+        return {
+            'title': self._og_search_title(webpage, fatal=require_title),
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'uploader': self._og_search_property('site_name', webpage, default=None),
+        }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        params = extract_attributes(self._search_regex(
-            r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
 
-        ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
-        hmac = params['data-video-hmac']
+        webpage = self._download_webpage(url, video_id)
+
+        # now quite different params!
+        params = extract_attributes(self._search_regex(
+            r'''(<[^>]+\b(?:class|data-testid)\s*=\s*("|')genie-container\2[^>]*>)''',
+            webpage, 'params'))
+
+        ios_playlist_url = traverse_obj(
+            params, 'data-video-id', 'data-video-playlist',
+            get_all=False, expected_type=url_or_none)
+
         headers = self.geo_verification_headers()
         headers.update({
             'Accept': 'application/vnd.itv.vod.playlist.v2+json',
             'Content-Type': 'application/json',
-            'hmac': hmac.upper(),
         })
         ios_playlist = self._download_json(
             ios_playlist_url, video_id, data=json.dumps({
                 'user': {
-                    'itvUserId': '',
                     'entitlements': [],
-                    'token': ''
                 },
                 'device': {
-                    'manufacturer': 'Safari',
-                    'model': '5',
+                    'manufacturer': 'Mobile Safari',
+                    'model': '5.1',
                     'os': {
-                        'name': 'Windows NT',
-                        'version': '6.1',
-                        'type': 'desktop'
+                        'name': 'iOS',
+                        'version': '5.0',
+                        'type': ' mobile'
                     }
                 },
                 'client': {
                     'version': '4.1',
-                    'id': 'browser'
+                    'id': 'browser',
+                    'supportsAdPods': True,
+                    'service': 'itv.x',
+                    'appversion': '2.43.28',
                 },
                 'variantAvailability': {
+                    'player': 'hls',
                     'featureset': {
                         'min': ['hls', 'aes', 'outband-webvtt'],
                         'max': ['hls', 'aes', 'outband-webvtt']
                     },
-                    'platformTag': 'dotcom'
+                    'platformTag': 'mobile'
                 }
             }).encode(), headers=headers)
         video_data = ios_playlist['Playlist']['Video']
-        ios_base_url = video_data.get('Base')
+        ios_base_url = traverse_obj(video_data, 'Base', expected_type=url_or_none)
+
+        media_url = (
+            (lambda u: url_or_none(urljoin(ios_base_url, u)))
+            if ios_base_url else url_or_none)
 
         formats = []
-        for media_file in (video_data.get('MediaFiles') or []):
-            href = media_file.get('Href')
+        for media_file in traverse_obj(video_data, 'MediaFiles', expected_type=list) or []:
+            href = traverse_obj(media_file, 'Href', expected_type=media_url)
             if not href:
                 continue
-            if ios_base_url:
-                href = ios_base_url + href
             ext = determine_ext(href)
             if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
-                    href, video_id, 'mp4', entry_protocol='m3u8_native',
+                    href, video_id, 'mp4', entry_protocol='m3u8',
                     m3u8_id='hls', fatal=False))
+
             else:
                 formats.append({
                     'url': href,
                 })
         self._sort_formats(formats)
+        for f in formats:
+            f.setdefault('http_headers', {})
+            f['http_headers'].update(self._vanilla_ua_header())
 
         subtitles = {}
-        subs = video_data.get('Subtitles') or []
-        for sub in subs:
-            if not isinstance(sub, dict):
-                continue
-            href = url_or_none(sub.get('Href'))
+        for sub in traverse_obj(video_data, 'Subtitles', expected_type=list) or []:
+            href = traverse_obj(sub, 'Href', expected_type=url_or_none)
             if not href:
                 continue
             subtitles.setdefault('en', []).append({
@@ -127,59 +270,132 @@ class ITVIE(InfoExtractor):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        info = self._search_json_ld(webpage, video_id, default={})
-        if not info:
-            json_ld = self._parse_json(self._search_regex(
-                JSON_LD_RE, webpage, 'JSON-LD', '{}',
-                group='json_ld'), video_id, fatal=False)
-            if json_ld and json_ld.get('@type') == 'BreadcrumbList':
-                for ile in (json_ld.get('itemListElement:') or []):
-                    item = ile.get('item:') or {}
-                    if item.get('@type') == 'TVEpisode':
-                        item['@context'] = 'http://schema.org'
-                        info = self._json_ld(item, video_id, fatal=False) or {}
-                        break
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
+        title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
+        info = self._og_extract(webpage, require_title=not title)
+        tn = info.pop('thumbnail', None)
+        if tn:
+            info['thumbnails'] = [{'url': tn}]
+
+        # num. episode title
+        num_ep_title = video_data.get('numberedEpisodeTitle')
+        if not num_ep_title:
+            num_ep_title = clean_html(get_element_by_attribute('data-testid', 'episode-hero-description-strong', webpage))
+            num_ep_title = num_ep_title and num_ep_title.rstrip(' -')
+        ep_title = strip_or_none(
+            video_data.get('episodeTitle')
+            or (num_ep_title.split('.', 1)[-1] if num_ep_title else None))
+        title = title or re.sub(r'\s+-\s+ITVX$', '', info['title'])
+        if ep_title and ep_title != title:
+            title = title + ' - ' + ep_title
+
+        def get_thumbnails():
+            tns = []
+            for w, x in (traverse_obj(video_data, ('imagePresets'), expected_type=dict) or {}).items():
+                if isinstance(x, dict):
+                    for y, z in x.items():
+                        tns.append({'id': w + '_' + y, 'url': z})
+            return tns or None
+
+        video_str = lambda *x: traverse_obj(
+            video_data, *x, get_all=False, expected_type=strip_or_none)
 
         return merge_dicts({
             'id': video_id,
-            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'title': title,
             'formats': formats,
             'subtitles': subtitles,
-            'duration': parse_duration(video_data.get('Duration')),
-            'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
+            # parsing hh:mm:ss:nnn not yet patched
+            'duration': parse_duration(re.sub(r'(\d{2})(:)(\d{3}$)', r'\1.\3', video_data.get('Duration') or '')),
+            'description': video_str('synopsis'),
+            'timestamp': traverse_obj(video_data, 'broadcastDateTime', 'dateTime', expected_type=parse_iso8601),
+            'thumbnails': get_thumbnails(),
+            'series': video_str('showTitle', 'programmeTitle'),
+            'series_number': int_or_none(video_data.get('seriesNumber')),
+            'episode': ep_title,
+            'episode_number': int_or_none((num_ep_title or '').split('.')[0]),
+            'channel': video_str('channel'),
+            'categories': traverse_obj(video_data, ('categories', 'formatted'), expected_type=list),
+            'age_limit': {False: 16, True: 0}.get(video_data.get('isChildrenCategory')),
         }, info)
 
 
-class ITVBTCCIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
+class ITVBTCCIE(ITVBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
+    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    _TESTS = [{
+        'note': 'British Touring Car Championship',
+        'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',
         'info_dict': {
             'id': 'btcc-2018-all-the-action-from-brands-hatch',
             'title': 'BTCC 2018: All the action from Brands Hatch',
         },
         'playlist_mincount': 9,
-    }
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s'
+    }, {
+        'note': 'redirects to /btcc/articles/...',
+        'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
+        'only_matching': True,
+    }, {
+        'note': 'news article',
+        'url': 'https://www.itv.com/news/wales/2020-07-23/sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
+        'info_dict': {
+            'id': 'sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
+            'title': '''Sean Fletcher on why Wales' coastline should be your 'staycation' destination | ITV News''',
+        },
+        'playlist_mincount': 1,
+    }]
+
+    # should really be a class var of the BC IE
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
+    BRIGHTCOVE_ACCOUNT = '1582188683001'
+    BRIGHTCOVE_PLAYER = 'HkiHLnNRx'
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, playlist_id)
+        webpage, urlh = self._download_webpage_handle(url, playlist_id)
+        link = compat_urlparse.urlparse(urlh.geturl()).path.strip('/')
 
-        entries = [
-            self.url_result(
-                smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {
-                    # ITV does not like some GB IP ranges, so here are some
-                    # IP blocks it accepts
-                    'geo_ip_blocks': [
-                        '193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
-                    ],
-                    'referrer': url,
-                }),
-                ie=BrightcoveNewIE.ie_key(), video_id=video_id)
-            for video_id in re.findall(r'data-video-id=["\'](\d+)', webpage)]
+        next_data = self._search_nextjs_data(webpage, playlist_id, fatal=False, default='{}')
+        path_prefix = compat_urlparse.urlparse(next_data.get('assetPrefix') or '').path.strip('/')
+        link = remove_start(link, path_prefix).strip('/')
+
+        content = traverse_obj(
+            next_data, ('props', 'pageProps', Ellipsis),
+            expected_type=lambda x: x if x['link'] == link else None,
+            get_all=False, default={})
+        content = traverse_obj(
+            content, ('body', 'content', Ellipsis, 'data'),
+            expected_type=lambda x: x if x.get('name') == 'Brightcove' or x.get('type') == 'Brightcove' else None)
+
+        contraband = {
+            # ITV does not like some GB IP ranges, so here are some
+            # IP blocks it accepts
+            'geo_ip_blocks': [
+                '193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
+            ],
+            'referrer': urlh.geturl(),
+        }
+
+        def entries():
+
+            for data in content or []:
+                video_id = data.get('id')
+                if not video_id:
+                    continue
+                account = data.get('accountId') or self.BRIGHTCOVE_ACCOUNT
+                player = data.get('playerId') or self.BRIGHTCOVE_PLAYER
+                yield self.url_result(
+                    smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account, player, video_id), contraband),
+                    ie=BrightcoveNewIE.ie_key(), video_id=video_id)
+
+            # obsolete ?
+            for video_id in re.findall(r'''data-video-id=["'](\d+)''', webpage):
+                yield self.url_result(
+                    smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (self.BRIGHTCOVE_ACCOUNT, self.BRIGHTCOVE_PLAYER, video_id), contraband),
+                    ie=BrightcoveNewIE.ie_key(), video_id=video_id)
 
         title = self._og_search_title(webpage, fatal=False)
 
-        return self.playlist_result(entries, playlist_id, title)
+        return self.playlist_result(entries(), playlist_id, title)

youtube_dl/extractor/manyvids.py

@@ -1,11 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     determine_ext,
+    extract_attributes,
     int_or_none,
     str_to_int,
+    url_or_none,
     urlencode_postdata,
 )
 
@@ -20,17 +25,20 @@ class ManyVidsIE(InfoExtractor):
             'id': '133957',
             'ext': 'mp4',
             'title': 'everthing about me (Preview)',
+            'uploader': 'ellyxxix',
             'view_count': int,
             'like_count': int,
         },
     }, {
         # full video
         'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
-        'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
+        'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
         'info_dict': {
             'id': '935718',
             'ext': 'mp4',
             'title': 'MY FACE REVEAL',
+            'description': 'md5:ec5901d41808b3746fed90face161612',
+            'uploader': 'Sarah Calanthe',
             'view_count': int,
             'like_count': int,
         },
@@ -39,17 +47,50 @@ class ManyVidsIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        real_url = 'https://www.manyvids.com/video/%s/gtm.js' % (video_id, )
+        try:
+            webpage = self._download_webpage(real_url, video_id)
+        except Exception:
+            # probably useless fallback
+            webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(
-            r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
-            webpage, 'video URL', group='url')
+        info = self._search_regex(
+            r'''(<div\b[^>]*\bid\s*=\s*(['"])pageMetaDetails\2[^>]*>)''',
+            webpage, 'meta details', default='')
+        info = extract_attributes(info)
 
-        title = self._html_search_regex(
-            (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
-             r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
-            webpage, 'title', default=None) or self._html_search_meta(
-            'twitter:title', webpage, 'title', fatal=True)
+        player = self._search_regex(
+            r'''(<div\b[^>]*\bid\s*=\s*(['"])rmpPlayerStream\2[^>]*>)''',
+            webpage, 'player details', default='')
+        player = extract_attributes(player)
+
+        video_urls_and_ids = (
+            (info.get('data-meta-video'), 'video'),
+            (player.get('data-video-transcoded'), 'transcoded'),
+            (player.get('data-video-filepath'), 'filepath'),
+            (self._og_search_video_url(webpage, secure=False, default=None), 'og_video'),
+        )
+
+        def txt_or_none(s, default=None):
+            return (s.strip() or default) if isinstance(s, compat_str) else default
+
+        uploader = txt_or_none(info.get('data-meta-author'))
+
+        def mung_title(s):
+            if uploader:
+                s = re.sub(r'^\s*%s\s+[|-]' % (re.escape(uploader), ), '', s)
+            return txt_or_none(s)
+
+        title = (
+            mung_title(info.get('data-meta-title'))
+            or self._html_search_regex(
+                (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
+                 r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
+                webpage, 'title', default=None)
+            or self._html_search_meta(
+                'twitter:title', webpage, 'title', fatal=True))
+
+        title = re.sub(r'\s*[|-]\s+ManyVids\s*$', '', title) or title
 
         if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
             title += ' (Preview)'
@@ -62,7 +103,8 @@ class ManyVidsIE(InfoExtractor):
             # Sets some cookies
             self._download_webpage(
                 'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
-                video_id, fatal=False, data=urlencode_postdata({
+                video_id, note='Setting format cookies', fatal=False,
+                data=urlencode_postdata({
                     'mvtoken': mv_token,
                     'vid': video_id,
                 }), headers={
@@ -70,23 +112,56 @@ class ManyVidsIE(InfoExtractor):
                     'X-Requested-With': 'XMLHttpRequest'
                 })
 
-        if determine_ext(video_url) == 'm3u8':
-            formats = self._extract_m3u8_formats(
-                video_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                m3u8_id='hls')
-        else:
-            formats = [{'url': video_url}]
+        formats = []
+        for v_url, fmt in video_urls_and_ids:
+            v_url = url_or_none(v_url)
+            if not v_url:
+                continue
+            if determine_ext(v_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    v_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': v_url,
+                    'format_id': fmt,
+                })
 
-        like_count = int_or_none(self._search_regex(
-            r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
-        view_count = str_to_int(self._html_search_regex(
-            r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
-            'view count', default=None))
+        self._remove_duplicate_formats(formats)
+
+        for f in formats:
+            if f.get('height') is None:
+                f['height'] = int_or_none(
+                    self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
+            if '/preview/' in f['url']:
+                f['format_id'] = '_'.join(filter(None, (f.get('format_id'), 'preview')))
+                f['preference'] = -10
+            if 'transcoded' in f['format_id']:
+                f['preference'] = f.get('preference', -1) - 1
+
+        self._sort_formats(formats)
+
+        def get_likes():
+            likes = self._search_regex(
+                r'''(<a\b[^>]*\bdata-id\s*=\s*(['"])%s\2[^>]*>)''' % (video_id, ),
+                webpage, 'likes', default='')
+            likes = extract_attributes(likes)
+            return int_or_none(likes.get('data-likes'))
+
+        def get_views():
+            return str_to_int(self._html_search_regex(
+                r'''(?s)<span\b[^>]*\bclass\s*=["']views-wrapper\b[^>]+>.+?<span\b[^>]+>\s*(\d[\d,.]*)\s*</span>''',
+                webpage, 'view count', default=None))
 
         return {
             'id': video_id,
             'title': title,
-            'view_count': view_count,
-            'like_count': like_count,
             'formats': formats,
+            'description': txt_or_none(info.get('data-meta-description')),
+            'uploader': txt_or_none(info.get('data-meta-author')),
+            'thumbnail': (
+                url_or_none(info.get('data-meta-image'))
+                or url_or_none(player.get('data-video-screenshot'))),
+            'view_count': get_views(),
+            'like_count': get_likes(),
         }

youtube_dl/extractor/mediaset.py

@@ -24,7 +24,7 @@ class MediasetIE(ThePlatformBaseIE):
                             (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
                             (?:
                                 (?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
-                                player/index\.html\?.*?\bprogramGuid=
+                                player(?:/v\d+)?/index\.html\?.*?\bprogramGuid=
                             )
                     )(?P<id>[0-9A-Z]{16,})
                     '''
@@ -73,6 +73,10 @@ class MediasetIE(ThePlatformBaseIE):
         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
         'only_matching': True,
+    }, {
+        # embedUrl (from https://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/)
+        'url': 'https://static3.mediasetplay.mediaset.it/player/v2/index.html?partnerId=wittytv&configId=&programGuid=FD00000000153323&autoplay=true&purl=http://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/',
+        'only_matching': True,
     }, {
         'url': 'mediaset:FAFU000000665924',
         'only_matching': True,

youtube_dl/extractor/minds.py

@@ -78,7 +78,7 @@ class MindsIE(MindsBaseIE):
             else:
                 return self.url_result(entity['perma_url'])
         else:
-            assert(entity['subtype'] == 'video')
+            assert (entity['subtype'] == 'video')
             video_id = entity_id
         # 1080p and webm formats available only on the sources array
         video = self._call_api(

youtube_dl/extractor/motherless.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import datetime
@@ -71,7 +72,7 @@ class MotherlessIE(InfoExtractor):
             'title': 'a/ Hot Teens',
             'categories': list,
             'upload_date': '20210104',
-            'uploader_id': 'yonbiw',
+            'uploader_id': 'anonymous',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
         },
@@ -125,9 +126,10 @@ class MotherlessIE(InfoExtractor):
                 kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
                 upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
 
-        comment_count = webpage.count('class="media-comment-contents"')
+        comment_count = len(re.findall(r'''class\s*=\s*['"]media-comment-contents\b''', webpage))
         uploader_id = self._html_search_regex(
-            r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
+            (r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
+             r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
             webpage, 'uploader_id')
 
         categories = self._html_search_meta('keywords', webpage, default=None)
@@ -169,7 +171,18 @@ class MotherlessGroupIE(InfoExtractor):
             'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
                            'any kind!'
         },
-        'playlist_mincount': 9,
+        'playlist_mincount': 0,
+        'expected_warnings': [
+            'This group has no videos.',
+        ]
+    }, {
+        'url': 'https://motherless.com/g/beautiful_cock',
+        'info_dict': {
+            'id': 'beautiful_cock',
+            'title': 'Beautiful Cock',
+            'description': 'Group for lovely cocks yours, mine, a friends anything human',
+        },
+        'playlist_mincount': 2500,
     }]
 
     @classmethod
@@ -208,16 +221,23 @@ class MotherlessGroupIE(InfoExtractor):
             r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
         description = self._html_search_meta(
             'description', webpage, fatal=False)
-        page_count = self._int(self._search_regex(
-            r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
-            webpage, 'page_count'), 'page_count')
+        page_count = str_to_int(self._search_regex(
+            r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
+            webpage, 'page_count', default=0))
+        if not page_count:
+            message = self._search_regex(
+                r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
+                webpage, 'error_msg', default=None) or 'This group has no videos.'
+            self.report_warning(message, group_id)
+            page_count = 1
         PAGE_SIZE = 80
 
         def _get_page(idx):
-            webpage = self._download_webpage(
-                page_url, group_id, query={'page': idx + 1},
-                note='Downloading page %d/%d' % (idx + 1, page_count)
-            )
+            if idx > 0:
+                webpage = self._download_webpage(
+                    page_url, group_id, query={'page': idx + 1},
+                    note='Downloading page %d/%d' % (idx + 1, page_count)
+                )
             for entry in self._extract_entries(webpage, url):
                 yield entry
 

youtube_dl/extractor/myvideoge.py

@@ -0,0 +1,87 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    get_element_by_id,
+    get_element_by_class,
+    int_or_none,
+    js_to_json,
+    MONTH_NAMES,
+    qualities,
+    unified_strdate,
+)
+
+
+class MyVideoGeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?myvideo\.ge/v/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.myvideo.ge/v/3941048',
+        'md5': '8c192a7d2b15454ba4f29dc9c9a52ea9',
+        'info_dict': {
+            'id': '3941048',
+            'ext': 'mp4',
+            'title': 'The best prikol',
+            'upload_date': '20200611',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'chixa33',
+            'description': 'md5:5b067801318e33c2e6eea4ab90b1fdd3',
+        },
+        # working from local dev system
+        'skip': 'site blocks CI servers',
+    }
+    _MONTH_NAMES_KA = ['იანვარი', 'თებერვალი', 'მარტი', 'აპრილი', 'მაისი', 'ივნისი', 'ივლისი', 'აგვისტო', 'სექტემბერი', 'ოქტომბერი', 'ნოემბერი', 'დეკემბერი']
+
+    _quality = staticmethod(qualities(('SD', 'HD')))
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = (
+            self._og_search_title(webpage, default=None)
+            or clean_html(get_element_by_class('my_video_title', webpage))
+            or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title'))
+
+        jwplayer_sources = self._parse_json(
+            self._search_regex(
+                r'''(?s)jwplayer\s*\(\s*['"]mvplayer['"]\s*\)\s*\.\s*setup\s*\(.*?\bsources\s*:\s*(\[.*?])\s*[,});]''', webpage, 'jwplayer sources', fatal=False)
+            or '',
+            video_id, transform_source=js_to_json, fatal=False)
+
+        formats = self._parse_jwplayer_formats(jwplayer_sources or [], video_id)
+        for f in formats or []:
+            f['preference'] = self._quality(f['format_id'])
+        self._sort_formats(formats)
+
+        description = (
+            self._og_search_description(webpage)
+            or get_element_by_id('long_desc_holder', webpage)
+            or self._html_search_meta('description', webpage))
+
+        uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
+
+        upload_date = get_element_by_class('mv_vid_upl_date', webpage)
+        # as ka locale may not be present roll a local date conversion
+        upload_date = (unified_strdate(
+            # translate any ka month to an en one
+            re.sub('|'.join(self._MONTH_NAMES_KA),
+                   lambda m: MONTH_NAMES['en'][self._MONTH_NAMES_KA.index(m.group(0))],
+                   upload_date, re.I))
+            if upload_date else None)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'formats': formats,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'upload_date': upload_date,
+            'view_count': int_or_none(get_element_by_class('mv_vid_views', webpage)),
+            'like_count': int_or_none(get_element_by_id('likes_count', webpage)),
+            'dislike_count': int_or_none(get_element_by_id('dislikes_count', webpage)),
+        }

youtube_dl/extractor/neteasemusic.py

@@ -1,20 +1,32 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from hashlib import md5
 from base64 import b64encode
+from binascii import hexlify
 from datetime import datetime
+from hashlib import md5
+from random import randint
+import json
 import re
+import time
 
 from .common import InfoExtractor
+from ..aes import aes_ecb_encrypt, pkcs7_padding
 from ..compat import (
     compat_urllib_parse_urlencode,
     compat_str,
     compat_itertools_count,
 )
 from ..utils import (
-    sanitized_Request,
+    ExtractorError,
+    bytes_to_intlist,
+    error_to_compat_str,
     float_or_none,
+    int_or_none,
+    intlist_to_bytes,
+    sanitized_Request,
+    std_headers,
+    try_get,
 )
 
 
@@ -35,32 +47,106 @@ class NetEaseMusicBaseIE(InfoExtractor):
         result = b64encode(m.digest()).decode('ascii')
         return result.replace('/', '_').replace('+', '-')
 
+    @classmethod
+    def make_player_api_request_data_and_headers(cls, song_id, bitrate):
+        KEY = b'e82ckenh8dichen8'
+        URL = '/api/song/enhance/player/url'
+        now = int(time.time() * 1000)
+        rand = randint(0, 1000)
+        cookie = {
+            'osver': None,
+            'deviceId': None,
+            'appver': '8.0.0',
+            'versioncode': '140',
+            'mobilename': None,
+            'buildver': '1623435496',
+            'resolution': '1920x1080',
+            '__csrf': '',
+            'os': 'pc',
+            'channel': None,
+            'requestId': '{0}_{1:04}'.format(now, rand),
+        }
+        request_text = json.dumps(
+            {'ids': '[{0}]'.format(song_id), 'br': bitrate, 'header': cookie},
+            separators=(',', ':'))
+        message = 'nobody{0}use{1}md5forencrypt'.format(
+            URL, request_text).encode('latin1')
+        msg_digest = md5(message).hexdigest()
+
+        data = '{0}-36cd479b6b5-{1}-36cd479b6b5-{2}'.format(
+            URL, request_text, msg_digest)
+        data = pkcs7_padding(bytes_to_intlist(data))
+        encrypted = intlist_to_bytes(aes_ecb_encrypt(data, bytes_to_intlist(KEY)))
+        encrypted_params = hexlify(encrypted).decode('ascii').upper()
+
+        cookie = '; '.join(
+            ['{0}={1}'.format(k, v if v is not None else 'undefined')
+             for [k, v] in cookie.items()])
+
+        headers = {
+            'User-Agent': std_headers['User-Agent'],
+            'Content-Type': 'application/x-www-form-urlencoded',
+            'Referer': 'https://music.163.com',
+            'Cookie': cookie,
+        }
+        return ('params={0}'.format(encrypted_params), headers)
+
+    def _call_player_api(self, song_id, bitrate):
+        url = 'https://interface3.music.163.com/eapi/song/enhance/player/url'
+        data, headers = self.make_player_api_request_data_and_headers(song_id, bitrate)
+        try:
+            msg = 'empty result'
+            result = self._download_json(
+                url, song_id, data=data.encode('ascii'), headers=headers)
+            if result:
+                return result
+        except ExtractorError as e:
+            if type(e.cause) in (ValueError, TypeError):
+                # JSON load failure
+                raise
+        except Exception as e:
+            msg = error_to_compat_str(e)
+            self.report_warning('%s API call (%s) failed: %s' % (
+                song_id, bitrate, msg))
+        return {}
+
     def extract_formats(self, info):
+        err = 0
         formats = []
+        song_id = info['id']
         for song_format in self._FORMATS:
             details = info.get(song_format)
             if not details:
                 continue
-            song_file_path = '/%s/%s.%s' % (
-                self._encrypt(details['dfsId']), details['dfsId'], details['extension'])
 
-            # 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
-            # from NetEase's CDN provider that can be used if m5.music.126.net does not
-            # work, especially for users outside of Mainland China
-            # via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
-            for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
-                         'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
-                song_url = host + song_file_path
+            bitrate = int_or_none(details.get('bitrate')) or 999000
+            data = self._call_player_api(song_id, bitrate)
+            for song in try_get(data, lambda x: x['data'], list) or []:
+                song_url = try_get(song, lambda x: x['url'])
+                if not song_url:
+                    continue
                 if self._is_valid_url(song_url, info['id'], 'song'):
                     formats.append({
                         'url': song_url,
                         'ext': details.get('extension'),
-                        'abr': float_or_none(details.get('bitrate'), scale=1000),
+                        'abr': float_or_none(song.get('br'), scale=1000),
                         'format_id': song_format,
-                        'filesize': details.get('size'),
-                        'asr': details.get('sr')
+                        'filesize': int_or_none(song.get('size')),
+                        'asr': int_or_none(details.get('sr')),
                     })
-                    break
+                elif err == 0:
+                    err = try_get(song, lambda x: x['code'], int)
+
+        if not formats:
+            msg = 'No media links found'
+            if err != 0 and (err < 200 or err >= 400):
+                raise ExtractorError(
+                    '%s (site code %d)' % (msg, err, ), expected=True)
+            else:
+                self.raise_geo_restricted(
+                    msg + ': probably this video is not available from your location due to geo restriction.',
+                    countries=['CN'])
+
         return formats
 
     @classmethod
@@ -76,33 +162,19 @@ class NetEaseMusicBaseIE(InfoExtractor):
 class NetEaseMusicIE(NetEaseMusicBaseIE):
     IE_NAME = 'netease:song'
     IE_DESC = '网易云音乐'
-    _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'http://music.163.com/#/song?id=32102397',
-        'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
+        'md5': '3e909614ce09b1ccef4a3eb205441190',
         'info_dict': {
             'id': '32102397',
             'ext': 'mp3',
-            'title': 'Bad Blood (feat. Kendrick Lamar)',
+            'title': 'Bad Blood',
             'creator': 'Taylor Swift / Kendrick Lamar',
-            'upload_date': '20150517',
-            'timestamp': 1431878400,
-            'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
+            'upload_date': '20150516',
+            'timestamp': 1431792000,
+            'description': 'md5:25fc5f27e47aad975aa6d36382c7833c',
         },
-        'skip': 'Blocked outside Mainland China',
-    }, {
-        'note': 'No lyrics translation.',
-        'url': 'http://music.163.com/#/song?id=29822014',
-        'info_dict': {
-            'id': '29822014',
-            'ext': 'mp3',
-            'title': '听见下雨的声音',
-            'creator': '周杰伦',
-            'upload_date': '20141225',
-            'timestamp': 1419523200,
-            'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
-        },
-        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'No lyrics.',
         'url': 'http://music.163.com/song?id=17241424',
@@ -112,9 +184,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'title': 'Opus 28',
             'creator': 'Dustin O\'Halloran',
             'upload_date': '20080211',
+            'description': 'md5:f12945b0f6e0365e3b73c5032e1b0ff4',
             'timestamp': 1202745600,
         },
-        'skip': 'Blocked outside Mainland China',
     }, {
         'note': 'Has translated name.',
         'url': 'http://music.163.com/#/song?id=22735043',
@@ -128,7 +200,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
             'timestamp': 1264608000,
             'alt_title': '说出愿望吧(Genie)',
         },
-        'skip': 'Blocked outside Mainland China',
+    }, {
+        'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
+        'md5': '95826c73ea50b1c288b22180ec9e754d',
+        'info_dict': {
+            'id': '95670',
+            'ext': 'mp3',
+            'title': '国际歌',
+            'creator': '马备',
+            'upload_date': '19911130',
+            'timestamp': 691516800,
+            'description': 'md5:1ba2f911a2b0aa398479f595224f2141',
+        },
     }]
 
     def _process_lyrics(self, lyrics_info):

youtube_dl/extractor/nhk.py

@@ -8,7 +8,7 @@ from ..utils import urljoin
 
 
 class NhkBaseIE(InfoExtractor):
-    _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/%s/%s/%s/all%s.json'
+    _API_URL_TEMPLATE = 'https://nwapi.nhk.jp/nhkworld/%sod%slist/v7b/%s/%s/%s/all%s.json'
     _BASE_URL_REGEX = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand'
     _TYPE_REGEX = r'/(?P<type>video|audio)/'
 

youtube_dl/extractor/nrk.py

@@ -60,8 +60,7 @@ class NRKBaseIE(InfoExtractor):
         return self._download_json(
             urljoin('https://psapi.nrk.no/', path),
             video_id, note or 'Downloading %s JSON' % item,
-            fatal=fatal, query=query,
-            headers={'Accept-Encoding': 'gzip, deflate, br'})
+            fatal=fatal, query=query)
 
 
 class NRKIE(NRKBaseIE):

youtube_dl/extractor/openload.py

@@ -16,6 +16,7 @@ from ..utils import (
     ExtractorError,
     get_exe_version,
     is_outdated_version,
+    process_communicate_or_kill,
     std_headers,
 )
 
@@ -226,7 +227,7 @@ class PhantomJSwrapper(object):
             self.exe, '--ssl-protocol=any',
             self._TMP_FILES['script'].name
         ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-        out, err = p.communicate()
+        out, err = process_communicate_or_kill(p)
         if p.returncode != 0:
             raise ExtractorError(
                 'Executing JS failed\n:' + encodeArgument(err))

youtube_dl/extractor/peekvids.py

@@ -0,0 +1,193 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    get_element_by_class,
+    int_or_none,
+    merge_dicts,
+    url_or_none,
+)
+
+
+class PeekVidsIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?peekvids\.com/
+        (?:(?:[^/?#]+/){2}|embed/?\?(?:[^#]*&)?v=)
+        (?P<id>[^/?&#]*)
+    '''
+    _TESTS = [{
+        'url': 'https://peekvids.com/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp/BSyLMbN0YCd',
+        'md5': '2ff6a357a9717dc9dc9894b51307e9a2',
+        'info_dict': {
+            'id': '1262717',
+            'display_id': 'BSyLMbN0YCd',
+            'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
+            'ext': 'mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
+            'timestamp': 1642579329,
+            'upload_date': '20220119',
+            'duration': 416,
+            'view_count': int,
+            'age_limit': 18,
+            'uploader': 'SEXYhub.com',
+            'categories': list,
+            'tags': list,
+        },
+    }]
+    _DOMAIN = 'www.peekvids.com'
+
+    def _get_detail(self, html):
+        return get_element_by_class('detail-video-block', html)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, expected_status=429)
+        if '>Rate Limit Exceeded' in webpage:
+            raise ExtractorError(
+                '[%s] %s: %s' % (self.IE_NAME, video_id, 'You are suspected as a bot. Wait, or pass the captcha test on the site and provide --cookies.'),
+                expected=True)
+
+        title = self._html_search_regex(r'(?s)<h1\b[^>]*>(.+?)</h1>', webpage, 'title')
+
+        display_id = video_id
+        video_id = self._search_regex(r'(?s)<video\b[^>]+\bdata-id\s*=\s*["\']?([\w-]+)', webpage, 'short video ID')
+        srcs = self._download_json(
+            'https://%s/v-alt/%s' % (self._DOMAIN, video_id), video_id,
+            note='Downloading list of source files')
+        formats = [{
+            'url': f_url,
+            'format_id': f_id,
+            'height': int_or_none(f_id),
+        } for f_url, f_id in (
+            (url_or_none(f_v), f_match.group(1))
+            for f_v, f_match in (
+                (v, re.match(r'^data-src(\d{3,})$', k))
+                for k, v in srcs.items() if v) if f_match)
+            if f_url
+        ]
+        if not formats:
+            formats = [{'url': url} for url in srcs.values()]
+        self._sort_formats(formats)
+
+        info = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
+        info.pop('url', None)
+        # may not have found the thumbnail if it was in a list in the ld+json
+        info.setdefault('thumbnail', self._og_search_thumbnail(webpage))
+        detail = self._get_detail(webpage) or ''
+        info['description'] = self._html_search_regex(
+            r'(?s)(.+?)(?:%s\s*<|<ul\b)' % (re.escape(info.get('description', '')), ),
+            detail, 'description', default=None) or None
+        info['title'] = re.sub(r'\s*[,-][^,-]+$', '', info.get('title') or title) or self._generic_title(url)
+
+        def cat_tags(name, html):
+            l = self._html_search_regex(
+                r'(?s)<span\b[^>]*>\s*%s\s*:\s*</span>(.+?)</li>' % (re.escape(name), ),
+                html, name, default='')
+            return [x for x in re.split(r'\s+', l) if x]
+
+        return merge_dicts({
+            'id': video_id,
+            'display_id': display_id,
+            'age_limit': 18,
+            'formats': formats,
+            'categories': cat_tags('Categories', detail),
+            'tags': cat_tags('Tags', detail),
+            'uploader': self._html_search_regex(r'[Uu]ploaded\s+by\s(.+?)"', webpage, 'uploader', default=None),
+        }, info)
+
+
+class PlayVidsIE(PeekVidsIE):
+    _VALID_URL = r'https?://(?:www\.)?playvids\.com/(?:embed/|\w\w?/)?(?P<id>[^/?#]*)'
+    _TESTS = [{
+        'url': 'https://www.playvids.com/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
+        'md5': '2f12e50213dd65f142175da633c4564c',
+        'info_dict': {
+            'id': '1978030',
+            'display_id': 'U3pBrYhsjXM',
+            'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
+            'ext': 'mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
+            'timestamp': 1640435839,
+            'upload_date': '20211225',
+            'duration': 416,
+            'view_count': int,
+            'age_limit': 18,
+            'uploader': 'SEXYhub.com',
+            'categories': list,
+            'tags': list,
+        },
+    }, {
+        'url': 'https://www.playvids.com/es/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.playvids.com/embed/U3pBrYhsjXM',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.playvids.com/bKmGLe3IwjZ/sv/brazzers-800-phone-sex-madison-ivy-always-on-the-line',
+        'md5': 'e783986e596cafbf46411a174ab42ba6',
+        'info_dict': {
+            'id': '762385',
+            'display_id': 'bKmGLe3IwjZ',
+            'ext': 'mp4',
+            'title': 'Brazzers - 1 800 Phone Sex: Madison Ivy Always On The Line 6',
+            'description': 'md5:bdcd2db2b8ad85831a491d7c8605dcef',
+            'timestamp': 1516958544,
+            'upload_date': '20180126',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 480,
+            'uploader': 'Brazzers',
+            'age_limit': 18,
+            'view_count': int,
+            'age_limit': 18,
+            'categories': list,
+            'tags': list,
+        },
+    }, {
+        'url': 'https://www.playvids.com/v/47iUho33toY',
+        'md5': 'b056b5049d34b648c1e86497cf4febce',
+        'info_dict': {
+            'id': '700621',
+            'display_id': '47iUho33toY',
+            'ext': 'mp4',
+            'title': 'KATEE OWEN STRIPTIASE IN SEXY RED LINGERIE',
+            'description': None,
+            'timestamp': 1507052209,
+            'upload_date': '20171003',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 332,
+            'uploader': 'Cacerenele',
+            'age_limit': 18,
+            'view_count': int,
+            'categories': list,
+            'tags': list,
+        }
+    }, {
+        'url': 'https://www.playvids.com/z3_7iwWCmqt/sexy-teen-filipina-striptease-beautiful-pinay-bargirl-strips-and-dances',
+        'md5': 'efa09be9f031314b7b7e3bc6510cd0df',
+        'info_dict': {
+            'id': '1523518',
+            'display_id': 'z3_7iwWCmqt',
+            'ext': 'mp4',
+            'title': 'SEXY TEEN FILIPINA STRIPTEASE - Beautiful Pinay Bargirl Strips and Dances',
+            'description': None,
+            'timestamp': 1607470323,
+            'upload_date': '20201208',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 593,
+            'uploader': 'yorours',
+            'age_limit': 18,
+            'view_count': int,
+            'categories': list,
+            'tags': list,
+        },
+    }]
+    _DOMAIN = 'www.playvids.com'
+
+    def _get_detail(self, html):
+        return get_element_by_class('detail-block', html)

youtube_dl/extractor/pr0gramm.py

@@ -0,0 +1,105 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+import re
+from ..utils import (
+    merge_dicts,
+)
+
+
+class Pr0grammStaticIE(InfoExtractor):
+    # Possible urls:
+    # https://pr0gramm.com/static/5466437
+    _VALID_URL = r'https?://pr0gramm\.com/static/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://pr0gramm.com/static/5466437',
+        'md5': '52fa540d70d3edc286846f8ca85938aa',
+        'info_dict': {
+            'id': '5466437',
+            'ext': 'mp4',
+            'title': 'pr0gramm-5466437 by g11st',
+            'uploader': 'g11st',
+            'upload_date': '20221221',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Fetch media sources
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        media_info = entries[0]
+
+        # this raises if there are no formats
+        self._sort_formats(media_info.get('formats') or [])
+
+        # Fetch author
+        uploader = self._html_search_regex(r'by\W+([\w-]+)\W+', webpage, 'uploader')
+
+        # Fetch approx upload timestamp from filename
+        # Have None-defaults in case the extraction fails
+        uploadDay = None
+        uploadMon = None
+        uploadYear = None
+        uploadTimestr = None
+        # (//img.pr0gramm.com/2022/12/21/62ae8aa5e2da0ebf.mp4)
+        m = re.search(r'//img\.pr0gramm\.com/(?P<year>[\d]+)/(?P<mon>[\d]+)/(?P<day>[\d]+)/\w+\.\w{,4}', webpage)
+
+        if (m):
+            # Up to a day of accuracy should suffice...
+            uploadDay = m.groupdict().get('day')
+            uploadMon = m.groupdict().get('mon')
+            uploadYear = m.groupdict().get('year')
+            uploadTimestr = uploadYear + uploadMon + uploadDay
+
+        return merge_dicts({
+            'id': video_id,
+            'title': 'pr0gramm-%s%s' % (video_id, (' by ' + uploader) if uploader else ''),
+            'uploader': uploader,
+            'upload_date': uploadTimestr
+        }, media_info)
+
+
+# This extractor is for the primary url (used for sharing, and appears in the
+# location bar) Since this page loads the DOM via JS, yt-dl can't find any
+# video information here. So let's redirect to a compatibility version of
+# the site, which does contain the <video>-element  by itself,  without requiring
+# js to be ran.
+class Pr0grammIE(InfoExtractor):
+    # Possible urls:
+    # https://pr0gramm.com/new/546637
+    # https://pr0gramm.com/new/video/546637
+    # https://pr0gramm.com/top/546637
+    # https://pr0gramm.com/top/video/546637
+    # https://pr0gramm.com/user/g11st/uploads/5466437
+    # https://pr0gramm.com/user/froschler/dafur-ist-man-hier/5091290
+    # https://pr0gramm.com/user/froschler/reinziehen-1elf/5232030
+    # https://pr0gramm.com/user/froschler/1elf/5232030
+    # https://pr0gramm.com/new/5495710:comment62621020 <- this is not the id!
+    # https://pr0gramm.com/top/fruher war alles damals/5498175
+
+    _VALID_URL = r'https?:\/\/pr0gramm\.com\/(?!static/\d+).+?\/(?P<id>[\d]+)(:|$)'
+    _TEST = {
+        'url': 'https://pr0gramm.com/new/video/5466437',
+        'info_dict': {
+            'id': '5466437',
+            'ext': 'mp4',
+            'title': 'pr0gramm-5466437 by g11st',
+            'uploader': 'g11st',
+            'upload_date': '20221221',
+        }
+    }
+
+    def _generic_title():
+        return "oof"
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self.url_result(
+            'https://pr0gramm.com/static/' + video_id,
+            video_id=video_id,
+            ie=Pr0grammStaticIE.ie_key())

youtube_dl/extractor/telegraaf.py

@@ -34,7 +34,9 @@ class TelegraafIE(InfoExtractor):
         article_id = self._match_id(url)
 
         video_id = self._download_json(
-            'https://www.telegraaf.nl/graphql', article_id, query={
+            'https://app.telegraaf.nl/graphql', article_id,
+            headers={'User-Agent': 'De Telegraaf/6.8.11 (Android 11; en_US)'},
+            query={
                 'query': '''{
   article(uid: %s) {
     videos {

youtube_dl/extractor/thisvid.py

@@ -0,0 +1,218 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import itertools
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urlparse,
+)
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    int_or_none,
+    merge_dicts,
+    url_or_none,
+    urljoin,
+)
+
+
+class ThisVidIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?P<type>videos|embed)/(?P<id>[A-Za-z0-9-]+)'
+    _TESTS = [{
+        'url': 'https://thisvid.com/videos/sitting-on-ball-tight-jeans/',
+        'md5': '839becb572995687e11a69dc4358a386',
+        'info_dict': {
+            'id': '3533241',
+            'ext': 'mp4',
+            'title': 'Sitting on ball tight jeans',
+            'description': 'md5:372353bb995883d1b65fddf507489acd',
+            'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
+            'uploader_id': '150629',
+            'uploader': 'jeanslevisjeans',
+            'age_limit': 18,
+        }
+    }, {
+        'url': 'https://thisvid.com/embed/3533241/',
+        'md5': '839becb572995687e11a69dc4358a386',
+        'info_dict': {
+            'id': '3533241',
+            'ext': 'mp4',
+            'title': 'Sitting on ball tight jeans',
+            'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
+            'uploader_id': '150629',
+            'uploader': 'jeanslevisjeans',
+            'age_limit': 18,
+        }
+    }]
+
+    def _real_extract(self, url):
+        main_id, type_ = re.match(self._VALID_URL, url).group('id', 'type')
+        webpage = self._download_webpage(url, main_id)
+
+        title = self._html_search_regex(
+            r'<title\b[^>]*?>(?:Video:\s+)?(.+?)(?:\s+-\s+ThisVid(?:\.com| tube))?</title>',
+            webpage, 'title')
+
+        if type_ == 'embed':
+            # look for more metadata
+            video_alt_url = url_or_none(self._search_regex(
+                r'''video_alt_url\s*:\s+'(%s/)',''' % (self._VALID_URL, ),
+                webpage, 'video_alt_url', default=None))
+            if video_alt_url and video_alt_url != url:
+                webpage = self._download_webpage(
+                    video_alt_url, main_id,
+                    note='Redirecting embed to main page', fatal=False) or webpage
+
+        video_holder = get_element_by_class('video-holder', webpage) or ''
+        if '>This video is a private video' in video_holder:
+            self.raise_login_required(
+                (clean_html(video_holder) or 'Private video').split('\n', 1)[0])
+
+        uploader = self._html_search_regex(
+            r'''(?s)<span\b[^>]*>Added by:\s*</span><a\b[^>]+\bclass\s*=\s*["']author\b[^>]+\bhref\s*=\s*["']https://thisvid\.com/members/([0-9]+/.{3,}?)\s*</a>''',
+            webpage, 'uploader', default='')
+        uploader = re.split(r'''/["'][^>]*>\s*''', uploader)
+        if len(uploader) == 2:
+            # id must be non-empty, uploader could be ''
+            uploader_id, uploader = uploader
+            uploader = uploader or None
+        else:
+            uploader_id = uploader = None
+
+        return merge_dicts({
+            '_type': 'url_transparent',
+            'title': title,
+            'age_limit': 18,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+        }, self.url_result(url, ie='Generic'))
+
+
+class ThisVidMemberIE(InfoExtractor):
+    _VALID_URL = r'https?://thisvid\.com/members/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://thisvid.com/members/2140501/',
+        'info_dict': {
+            'id': '2140501',
+            'title': 'Rafflesia\'s Profile',
+        },
+        'playlist_mincount': 16,
+    }, {
+        'url': 'https://thisvid.com/members/2140501/favourite_videos/',
+        'info_dict': {
+            'id': '2140501',
+            'title': 'Rafflesia\'s Favourite Videos',
+        },
+        'playlist_mincount': 15,
+    }, {
+        'url': 'https://thisvid.com/members/636468/public_videos/',
+        'info_dict': {
+            'id': '636468',
+            'title': 'Happymouth\'s Public Videos',
+        },
+        'playlist_mincount': 196,
+    },
+    ]
+
+    def _urls(self, html):
+        for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (ThisVidIE._VALID_URL, ), html):
+            yield m.group('url')
+
+    def _real_extract(self, url):
+        pl_id = self._match_id(url)
+        webpage = self._download_webpage(url, pl_id)
+
+        title = re.split(
+            r'(?i)\s*\|\s*ThisVid\.com\s*$',
+            self._og_search_title(webpage, default=None) or self._html_search_regex(r'(?s)<title\b[^>]*>(.+?)</title', webpage, 'title', fatal=False) or '', 1)[0] or None
+
+        def entries(page_url, html=None):
+            for page in itertools.count(1):
+                if not html:
+                    html = self._download_webpage(
+                        page_url, pl_id, note='Downloading page %d' % (page, ),
+                        fatal=False) or ''
+                for u in self._urls(html):
+                    yield u
+                next_page = get_element_by_class('pagination-next', html) or ''
+                if next_page:
+                    # member list page
+                    next_page = urljoin(url, self._search_regex(
+                        r'''<a\b[^>]+\bhref\s*=\s*("|')(?P<url>(?!#)(?:(?!\1).)+)''',
+                        next_page, 'next page link', group='url', default=None))
+                # in case a member page should have pagination-next with empty link, not just `else:`
+                if next_page is None:
+                    # playlist page
+                    parsed_url = compat_urlparse.urlparse(page_url)
+                    base_path, num = parsed_url.path.rsplit('/', 1)
+                    num = int_or_none(num)
+                    if num is None:
+                        base_path, num = parsed_url.path.rstrip('/'), 1
+                    parsed_url = parsed_url._replace(path=base_path + ('/%d' % (num + 1, )))
+                    next_page = compat_urlparse.urlunparse(parsed_url)
+                    if page_url == next_page:
+                        next_page = None
+                if not next_page:
+                    break
+                page_url, html = next_page, None
+
+        return self.playlist_from_matches(
+            entries(url, webpage), playlist_id=pl_id, playlist_title=title, ie='ThisVid')
+
+
+class ThisVidPlaylistIE(ThisVidMemberIE):
+    _VALID_URL = r'https?://thisvid\.com/playlist/(?P<id>\d+)/video/(?P<video_id>[A-Za-z0-9-]+)'
+    _TESTS = [{
+        'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
+        'info_dict': {
+            'id': '6615',
+            'title': 'Underwear Stuff',
+        },
+        'playlist_mincount': 200,
+    }, {
+        'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
+        'info_dict': {
+            'id': '1072387',
+            'ext': 'mp4',
+            'title': 'Big Italian Booty 28',
+            'description': 'md5:1bccf7b13765e18fb27bf764dba7ede2',
+            'uploader_id': '367912',
+            'uploader': 'Jcmusclefun',
+            'age_limit': 18,
+        },
+        'params': {
+            'noplaylist': True,
+        },
+    }]
+
+    def _get_video_url(self, pl_url):
+        video_id = re.match(self._VALID_URL, pl_url).group('video_id')
+        return urljoin(pl_url, '/videos/%s/' % (video_id, ))
+
+    def _urls(self, html):
+        for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (self._VALID_URL, ), html):
+            yield self._get_video_url(m.group('url'))
+
+    def _real_extract(self, url):
+        pl_id = self._match_id(url)
+
+        if self._downloader.params.get('noplaylist'):
+            self.to_screen('Downloading just the featured video because of --no-playlist')
+            return self.url_result(self._get_video_url(url), 'ThisVid')
+
+        self.to_screen(
+            'Downloading playlist %s - add --no-playlist to download just the featured video' % (pl_id, ))
+        result = super(ThisVidPlaylistIE, self)._real_extract(url)
+
+        # rework title returned as `the title - the title`
+        title = result['title']
+        t_len = len(title)
+        if t_len > 5 and t_len % 2 != 0:
+            t_len = t_len // 2
+            if title[t_len] == '-':
+                title = [t.strip() for t in (title[:t_len], title[t_len + 1:])]
+                if title[0] and title[0] == title[1]:
+                    result['title'] = title[0]
+        return result

youtube_dl/extractor/uktvplay.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class UKTVPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
+    _VALID_URL = r'https?://uktvplay\.(?:uktv\.)?co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://uktvplay.uktv.co.uk/shows/world-at-war/c/200/watch-online/?video=2117008346001',
         'info_dict': {

youtube_dl/extractor/vimeo.py

@@ -663,7 +663,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
 
         if '//player.vimeo.com/video/' in url:
             config = self._parse_json(self._search_regex(
-                r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
+                r'\b(?:playerC|c)onfig\s*=\s*({.+?})\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/vvvvid.py

@@ -64,6 +64,18 @@ class VVVVIDIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # video_type == 'video/dash'
+        'url': 'https://www.vvvvid.it/show/683/made-in-abyss/1542/693786/nanachi',
+        'info_dict': {
+            'id': '693786',
+            'ext': 'mp4',
+            'title': 'Nanachi',
+        },
+        'params': {
+            'skip_download': True,
+            'format': 'mp4',
+        },
     }, {
         'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048',
         'only_matching': True
@@ -205,6 +217,9 @@ class VVVVIDIE(InfoExtractor):
                 })
                 is_youtube = True
                 break
+            elif video_type == 'video/dash':
+                formats.extend(self._extract_m3u8_formats(
+                    embed_code, video_id, 'mp4', m3u8_id='hls', fatal=False))
             else:
                 formats.extend(self._extract_wowza_formats(
                     'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))

youtube_dl/extractor/xhamster.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools
@@ -23,7 +24,7 @@ from ..utils import (
 
 
 class XHamsterIE(InfoExtractor):
-    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
+    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:.+?\.)?%s/
@@ -34,7 +35,7 @@ class XHamsterIE(InfoExtractor):
                     ''' % _DOMAINS
     _TESTS = [{
         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
-        'md5': '98b4687efb1ffd331c4197854dc09e8f',
+        'md5': '34e1ab926db5dc2750fed9e1f34304bb',
         'info_dict': {
             'id': '1509445',
             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
@@ -43,6 +44,7 @@ class XHamsterIE(InfoExtractor):
             'timestamp': 1350194821,
             'upload_date': '20121014',
             'uploader': 'Ruseful2011',
+            'uploader_id': 'ruseful2011',
             'duration': 893,
             'age_limit': 18,
         },
@@ -72,6 +74,7 @@ class XHamsterIE(InfoExtractor):
             'timestamp': 1454948101,
             'upload_date': '20160208',
             'uploader': 'parejafree',
+            'uploader_id': 'parejafree',
             'duration': 72,
             'age_limit': 18,
         },
@@ -117,6 +120,12 @@ class XHamsterIE(InfoExtractor):
     }, {
         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
         'only_matching': True,
+    }, {
+        'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -245,6 +254,7 @@ class XHamsterIE(InfoExtractor):
             else:
                 categories = None
 
+            uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
             return {
                 'id': video_id,
                 'display_id': display_id,
@@ -253,6 +263,8 @@ class XHamsterIE(InfoExtractor):
                 'timestamp': int_or_none(video.get('created')),
                 'uploader': try_get(
                     video, lambda x: x['author']['name'], compat_str),
+                'uploader_url': uploader_url,
+                'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
                 'thumbnail': video.get('thumbURL'),
                 'duration': int_or_none(video.get('duration')),
                 'view_count': int_or_none(video.get('views')),
@@ -261,7 +273,7 @@ class XHamsterIE(InfoExtractor):
                 'dislike_count': int_or_none(try_get(
                     video, lambda x: x['rating']['dislikes'], int)),
                 'comment_count': int_or_none(video.get('views')),
-                'age_limit': age_limit,
+                'age_limit': age_limit if age_limit is not None else 18,
                 'categories': categories,
                 'formats': formats,
             }
@@ -352,6 +364,7 @@ class XHamsterIE(InfoExtractor):
             'description': description,
             'upload_date': upload_date,
             'uploader': uploader,
+            'uploader_id': uploader.lower() if uploader else None,
             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,
@@ -420,6 +433,12 @@ class XHamsterUserIE(InfoExtractor):
             'id': 'firatkaan',
         },
         'playlist_mincount': 1,
+    }, {
+        'url': 'https://xhday.com/users/mobhunter',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhvid.com/users/pelushe21',
+        'only_matching': True,
     }]
 
     def _entries(self, user_id):

youtube_dl/extractor/youtube.py

@@ -315,7 +315,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         title = try_get(
             renderer,
             (lambda x: x['title']['runs'][0]['text'],
-             lambda x: x['title']['simpleText']), compat_str)
+             lambda x: x['title']['simpleText'],
+             lambda x: x['headline']['simpleText']), compat_str)
         description = try_get(
             renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
             compat_str)
@@ -499,7 +500,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
         r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
     )
-    _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
+    _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
 
     _GEO_BYPASS = False
 
@@ -1500,7 +1501,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return lambda s: jsi.extract_function_from_code(*func_code)([s])
 
     def _n_descramble(self, n_param, player_url, video_id):
-        """Compute the response to YT's "n" parameter challenge
+        """Compute the response to YT's "n" parameter challenge,
+           or None
 
         Args:
         n_param     -- challenge string that is the value of the
@@ -1518,7 +1520,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if player_id not in self._player_cache:
                 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
             func = self._player_cache[player_id]
-            self._player_cache[sig_id] = func(n_param)
+            ret = func(n_param)
+            if ret.startswith('enhanced_except_'):
+                raise ExtractorError('Unhandled exception in decode')
+            self._player_cache[sig_id] = ret
             if self._downloader.params.get('verbose', False):
                 self._downloader.to_screen('[debug] [%s] %s' % (self.IE_NAME, 'Decrypted nsig {0} => {1}'.format(n_param, self._player_cache[sig_id])))
             return self._player_cache[sig_id]
@@ -1539,10 +1544,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 continue
             n_param = n_param[-1]
             n_response = self._n_descramble(n_param, player_url, video_id)
-            if n_response:
-                qs['n'] = [n_response]
-                fmt['url'] = compat_urlparse.urlunparse(
-                    parsed_fmt_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
+            if n_response is None:
+                # give up if descrambling failed
+                break
+            qs['n'] = [n_response]
+            fmt['url'] = compat_urlparse.urlunparse(
+                parsed_fmt_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
 
     def _mark_watched(self, video_id, player_response):
         playback_url = url_or_none(try_get(
@@ -2201,6 +2208,24 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
     IE_NAME = 'youtube:tab'
 
     _TESTS = [{
+        # Shorts
+        'url': 'https://www.youtube.com/@SuperCooperShorts/shorts',
+        'playlist_mincount': 5,
+        'info_dict': {
+            'description': 'Short clips from Super Cooper Sundays!',
+            'id': 'UCKMA8kHZ8bPYpnMNaUSxfEQ',
+            'title': 'Super Cooper Shorts - Shorts',
+        }
+    }, {
+        # Channel that does not have a Shorts tab. Test should just download videos on Home tab instead
+        'url': 'https://www.youtube.com/@emergencyawesome/shorts',
+        'info_dict': {
+            'description': 'md5:592c080c06fef4de3c902c4a8eecd850',
+            'id': 'UCDiFRMQWpcp8_KD4vwIVicw',
+            'title': 'Emergency Awesome - Home',
+        },
+        'playlist_mincount': 5,
+    }, {
         # playlists, multipage
         'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
         'playlist_mincount': 94,
@@ -2674,7 +2699,11 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
 
     def _rich_grid_entries(self, contents):
         for content in contents:
-            video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
+            video_renderer = try_get(
+                content,
+                (lambda x: x['richItemRenderer']['content']['videoRenderer'],
+                 lambda x: x['richItemRenderer']['content']['reelItemRenderer']),
+                dict)
             if video_renderer:
                 entry = self._video_entry(video_renderer)
                 if entry:

youtube_dl/extractor/zdf.py

@@ -8,13 +8,14 @@ from ..compat import compat_str
 from ..utils import (
     determine_ext,
     ExtractorError,
+    extract_attributes,
     float_or_none,
     int_or_none,
     merge_dicts,
     NO_DEFAULT,
-    orderedSet,
     parse_codecs,
     qualities,
+    str_or_none,
     try_get,
     unified_timestamp,
     update_url_query,
@@ -57,28 +58,39 @@ class ZDFBaseIE(InfoExtractor):
         format_urls.add(format_url)
         mime_type = meta.get('mimeType')
         ext = determine_ext(format_url)
+
+        join_nonempty = lambda s, l: s.join(filter(None, l))
+        meta_map = lambda t: map(lambda x: str_or_none(meta.get(x)), t)
+
         if mime_type == 'application/x-mpegURL' or ext == 'm3u8':
-            formats.extend(self._extract_m3u8_formats(
+            new_formats = self._extract_m3u8_formats(
                 format_url, video_id, 'mp4', m3u8_id='hls',
-                entry_protocol='m3u8_native', fatal=False))
+                entry_protocol='m3u8_native', fatal=False)
         elif mime_type == 'application/f4m+xml' or ext == 'f4m':
-            formats.extend(self._extract_f4m_formats(
-                update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False))
+            new_formats = self._extract_f4m_formats(
+                update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False)
         else:
             f = parse_codecs(meta.get('mimeCodec'))
+            if not f:
+                data = meta.get('type', '').split('_')
+                if try_get(data, lambda x: x[2]) == ext:
+                    f = dict(zip(('vcodec', 'acodec'), data[1]))
+
             format_id = ['http']
-            for p in (meta.get('type'), meta.get('quality')):
-                if p and isinstance(p, compat_str):
-                    format_id.append(p)
+            format_id.extend(join_nonempty('-', meta_map(('type', 'quality'))))
             f.update({
                 'url': format_url,
                 'format_id': '-'.join(format_id),
-                'format_note': meta.get('quality'),
-                'language': meta.get('language'),
-                'quality': qualities(self._QUALITIES)(meta.get('quality')),
-                'preference': -10,
+                'tbr': int_or_none(self._search_regex(r'_(\d+)k_', format_url, 'tbr', default=None))
             })
-            formats.append(f)
+            new_formats = [f]
+
+        formats.extend(merge_dicts(f, {
+            'format_note': join_nonempty(',', meta_map(('quality', 'class'))),
+            'language': meta.get('language'),
+            'language_preference': 10 if meta.get('class') == 'main' else -10 if meta.get('class') == 'ad' else -1,
+            'quality': qualities(self._QUALITIES)(meta.get('quality')),
+        }) for f in new_formats)
 
     def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
         ptmd = self._call_api(
@@ -107,6 +119,7 @@ class ZDFBaseIE(InfoExtractor):
                                 'type': f.get('type'),
                                 'mimeType': f.get('mimeType'),
                                 'quality': quality.get('quality'),
+                                'class': track.get('class'),
                                 'language': track.get('language'),
                             })
         self._sort_formats(formats)
@@ -171,6 +184,20 @@ class ZDFIE(ZDFBaseIE):
             'duration': 2615,
             'timestamp': 1465021200,
             'upload_date': '20160604',
+            'thumbnail': 'https://www.zdf.de/assets/mauve-im-labor-100~768x432?cb=1464909117806',
+        },
+    }, {
+        'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
+        'md5': '1b93bdec7d02fc0b703c5e7687461628',
+        'info_dict': {
+            'ext': 'mp4',
+            'id': 'video_funk_1770473',
+            'duration': 1278,
+            'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
+            'title': 'Alles ist verzaubert',
+            'timestamp': 1635520560,
+            'upload_date': '20211029',
+            'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-100~1920x1080?cb=1636466431799',
         },
     }, {
         # Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
@@ -204,6 +231,19 @@ class ZDFIE(ZDFBaseIE):
             'timestamp': 1641355200,
             'upload_date': '20220105',
         },
+        'skip': 'No longer available "Diese Seite wurde leider nicht gefunden"'
+    }, {
+        'url': 'https://www.zdf.de/serien/soko-stuttgart/das-geld-anderer-leute-100.html',
+        'info_dict': {
+            'id': '191205_1800_sendung_sok8',
+            'ext': 'mp4',
+            'title': 'Das Geld anderer Leute',
+            'description': 'md5:cb6f660850dc5eb7d1ab776ea094959d',
+            'duration': 2581.0,
+            'timestamp': 1654790700,
+            'upload_date': '20220609',
+            'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=2400x1350',
+        },
     }]
 
     def _extract_entry(self, url, player, content, video_id):
@@ -265,15 +305,16 @@ class ZDFIE(ZDFBaseIE):
             'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
             video_id)
 
-        document = video['document']
-
-        title = document['titel']
-        content_id = document['basename']
-
         formats = []
-        format_urls = set()
-        for f in document['formitaeten']:
-            self._extract_format(content_id, formats, format_urls, f)
+        formitaeten = try_get(video, lambda x: x['document']['formitaeten'], list)
+        document = formitaeten and video['document']
+        if formitaeten:
+            title = document['titel']
+            content_id = document['basename']
+
+            format_urls = set()
+            for f in formitaeten or []:
+                self._extract_format(content_id, formats, format_urls, f)
         self._sort_formats(formats)
 
         thumbnails = []
@@ -320,9 +361,9 @@ class ZDFChannelIE(ZDFBaseIE):
         'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
         'info_dict': {
             'id': 'das-aktuelle-sportstudio',
-            'title': 'das aktuelle sportstudio | ZDF',
+            'title': 'das aktuelle sportstudio',
         },
-        'playlist_mincount': 23,
+        'playlist_mincount': 18,
     }, {
         'url': 'https://www.zdf.de/dokumentation/planet-e',
         'info_dict': {
@@ -330,6 +371,14 @@ class ZDFChannelIE(ZDFBaseIE):
             'title': 'planet e.',
         },
         'playlist_mincount': 50,
+    }, {
+        'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
+        'info_dict': {
+            'id': 'aktenzeichen-xy-ungeloest',
+            'title': 'Aktenzeichen XY... ungelöst',
+            'entries': "lambda x: not any('xy580-fall1-kindermoerder-gesucht-100' in e['url'] for e in x)",
+        },
+        'playlist_mincount': 2,
     }, {
         'url': 'https://www.zdf.de/filme/taunuskrimi/',
         'only_matching': True,
@@ -339,60 +388,36 @@ class ZDFChannelIE(ZDFBaseIE):
     def suitable(cls, url):
         return False if ZDFIE.suitable(url) else super(ZDFChannelIE, cls).suitable(url)
 
+    def _og_search_title(self, webpage, fatal=False):
+        title = super(ZDFChannelIE, self)._og_search_title(webpage, fatal=fatal)
+        return re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', title or '')[0] or None
+
     def _real_extract(self, url):
         channel_id = self._match_id(url)
 
         webpage = self._download_webpage(url, channel_id)
 
-        entries = [
-            self.url_result(item_url, ie=ZDFIE.ie_key())
-            for item_url in orderedSet(re.findall(
-                r'data-plusbar-url=["\'](http.+?\.html)', webpage))]
+        matches = re.finditer(
+            r'''<div\b[^>]*?\sdata-plusbar-id\s*=\s*(["'])(?P<p_id>[\w-]+)\1[^>]*?\sdata-plusbar-url=\1(?P<url>%s)\1''' % ZDFIE._VALID_URL,
+            webpage)
 
-        return self.playlist_result(
-            entries, channel_id, self._og_search_title(webpage, fatal=False))
+        if self._downloader.params.get('noplaylist', False):
+            entry = next(
+                (self.url_result(m.group('url'), ie=ZDFIE.ie_key()) for m in matches),
+                None)
+            self.to_screen('Downloading just the main video because of --no-playlist')
+            if entry:
+                return entry
+        else:
+            self.to_screen('Downloading playlist %s - add --no-playlist to download just the main video' % (channel_id, ))
 
-        r"""
-        player = self._extract_player(webpage, channel_id)
+        def check_video(m):
+            v_ref = self._search_regex(
+                r'''(<a\b[^>]*?\shref\s*=[^>]+?\sdata-target-id\s*=\s*(["'])%s\2[^>]*>)''' % (m.group('p_id'), ),
+                webpage, 'check id', default='')
+            v_ref = extract_attributes(v_ref)
+            return v_ref.get('data-target-video-type') != 'novideo'
 
-        channel_id = self._search_regex(
-            r'docId\s*:\s*(["\'])(?P<id>(?!\1).+?)\1', webpage,
-            'channel id', group='id')
-
-        channel = self._call_api(
-            'https://api.zdf.de/content/documents/%s.json' % channel_id,
-            player, url, channel_id)
-
-        items = []
-        for module in channel['module']:
-            for teaser in try_get(module, lambda x: x['teaser'], list) or []:
-                t = try_get(
-                    teaser, lambda x: x['http://zdf.de/rels/target'], dict)
-                if not t:
-                    continue
-                items.extend(try_get(
-                    t,
-                    lambda x: x['resultsWithVideo']['http://zdf.de/rels/search/results'],
-                    list) or [])
-            items.extend(try_get(
-                module,
-                lambda x: x['filterRef']['resultsWithVideo']['http://zdf.de/rels/search/results'],
-                list) or [])
-
-        entries = []
-        entry_urls = set()
-        for item in items:
-            t = try_get(item, lambda x: x['http://zdf.de/rels/target'], dict)
-            if not t:
-                continue
-            sharing_url = t.get('http://zdf.de/rels/sharing-url')
-            if not sharing_url or not isinstance(sharing_url, compat_str):
-                continue
-            if sharing_url in entry_urls:
-                continue
-            entry_urls.add(sharing_url)
-            entries.append(self.url_result(
-                sharing_url, ie=ZDFIE.ie_key(), video_id=t.get('id')))
-
-        return self.playlist_result(entries, channel_id, channel.get('title'))
-        """
+        return self.playlist_from_matches(
+            (m.group('url') for m in matches if check_video(m)),
+            channel_id, self._og_search_title(webpage, fatal=False))

youtube_dl/options.py

@@ -270,11 +270,11 @@ def parseOpts(overrideArguments=None):
     selection.add_option(
         '--match-title',
         dest='matchtitle', metavar='REGEX',
-        help='Download only matching titles (case-insensitive regex or sub-string)')
+        help='Download only matching titles (case-insensitive regex or alphanumeric sub-string)')
     selection.add_option(
         '--reject-title',
         dest='rejecttitle', metavar='REGEX',
-        help='Skip download for matching titles (case-insensitive regex or sub-string)')
+        help='Skip download for matching titles (case-insensitive regex or alphanumeric sub-string)')
     selection.add_option(
         '--max-downloads',
         dest='max_downloads', metavar='NUMBER', type=int, default=None,
@@ -801,7 +801,7 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--postprocessor-args',
         dest='postprocessor_args', metavar='ARGS',
-        help='Give these arguments to the postprocessor')
+        help='Give these arguments to the postprocessor (if postprocessing is required)')
     postproc.add_option(
         '-k', '--keep-video',
         action='store_true', dest='keepvideo', default=False,

youtube_dl/postprocessor/embedthumbnail.py

@@ -13,8 +13,9 @@ from ..utils import (
     encodeFilename,
     PostProcessingError,
     prepend_extension,
+    process_communicate_or_kill,
     replace_extension,
-    shell_quote
+    shell_quote,
 )
 
 
@@ -109,7 +110,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
                 self._downloader.to_screen('[debug] AtomicParsley command line: %s' % shell_quote(cmd))
 
             p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            stdout, stderr = p.communicate()
+            stdout, stderr = process_communicate_or_kill(p)
 
             if p.returncode != 0:
                 msg = stderr.decode('utf-8', 'replace').strip()

youtube_dl/postprocessor/ffmpeg.py

@@ -16,6 +16,7 @@ from ..utils import (
     is_outdated_version,
     PostProcessingError,
     prepend_extension,
+    process_communicate_or_kill,
     shell_quote,
     subtitles_filename,
     dfxp2srt,
@@ -180,7 +181,7 @@ class FFmpegPostProcessor(PostProcessor):
             handle = subprocess.Popen(
                 cmd, stderr=subprocess.PIPE,
                 stdout=subprocess.PIPE, stdin=subprocess.PIPE)
-            stdout_data, stderr_data = handle.communicate()
+            stdout_data, stderr_data = process_communicate_or_kill(handle)
             expected_ret = 0 if self.probe_available else 1
             if handle.wait() != expected_ret:
                 return None
@@ -228,7 +229,7 @@ class FFmpegPostProcessor(PostProcessor):
         if self._downloader.params.get('verbose', False):
             self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
-        stdout, stderr = p.communicate()
+        stdout, stderr = process_communicate_or_kill(p)
         if p.returncode != 0:
             stderr = stderr.decode('utf-8', 'replace')
             msgs = stderr.strip().split('\n')

youtube_dl/postprocessor/metadatafromtitle.py

@@ -40,6 +40,8 @@ class MetadataFromTitlePP(PostProcessor):
                 % self._titleformat)
             return [], info
         for attribute, value in match.groupdict().items():
+            if value is None:
+                continue
             info[attribute] = value
             self._downloader.to_screen(
                 '[fromtitle] parsed %s: %s'

youtube_dl/utils.py

@@ -33,6 +33,7 @@ import sys
 import tempfile
 import time
 import traceback
+import unicodedata
 import xml.etree.ElementTree
 import zlib
 
@@ -42,6 +43,7 @@ from .compat import (
     compat_HTTPError,
     compat_basestring,
     compat_chr,
+    compat_collections_abc,
     compat_cookiejar,
     compat_ctypes_WINFUNCTYPE,
     compat_etree_fromstring,
@@ -1684,6 +1686,7 @@ USER_AGENTS = {
 
 
 NO_DEFAULT = object()
+IDENTITY = lambda x: x
 
 ENGLISH_MONTH_NAMES = [
     'January', 'February', 'March', 'April', 'May', 'June',
@@ -1696,6 +1699,17 @@ MONTH_NAMES = {
         'juillet', 'août', 'septembre', 'octobre', 'novembre', 'décembre'],
 }
 
+# Timezone names for RFC2822 obs-zone
+# From https://github.com/python/cpython/blob/3.11/Lib/email/_parseaddr.py#L36-L42
+TIMEZONE_NAMES = {
+    'UT': 0, 'UTC': 0, 'GMT': 0, 'Z': 0,
+    'AST': -4, 'ADT': -3,  # Atlantic (used in Canada)
+    'EST': -5, 'EDT': -4,  # Eastern
+    'CST': -6, 'CDT': -5,  # Central
+    'MST': -7, 'MDT': -6,  # Mountain
+    'PST': -8, 'PDT': -7   # Pacific
+}
+
 KNOWN_EXTENSIONS = (
     'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
     'flv', 'f4v', 'f4a', 'f4b',
@@ -1735,12 +1749,17 @@ DATE_FORMATS = (
     '%b %dth %Y %I:%M',
     '%Y %m %d',
     '%Y-%m-%d',
+    '%Y.%m.%d.',
     '%Y/%m/%d',
     '%Y/%m/%d %H:%M',
     '%Y/%m/%d %H:%M:%S',
+    '%Y%m%d%H%M',
+    '%Y%m%d%H%M%S',
+    '%Y%m%d',
     '%Y-%m-%d %H:%M',
     '%Y-%m-%d %H:%M:%S',
     '%Y-%m-%d %H:%M:%S.%f',
+    '%Y-%m-%d %H:%M:%S:%f',
     '%d.%m.%Y %H:%M',
     '%d.%m.%Y %H.%M',
     '%Y-%m-%dT%H:%M:%SZ',
@@ -1753,6 +1772,7 @@ DATE_FORMATS = (
     '%b %d %Y at %H:%M:%S',
     '%B %d %Y at %H:%M',
     '%B %d %Y at %H:%M:%S',
+    '%H:%M %d-%b-%Y',
 )
 
 DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
@@ -1763,6 +1783,7 @@ DATE_FORMATS_DAY_FIRST.extend([
     '%d/%m/%Y',
     '%d/%m/%y',
     '%d/%m/%Y %H:%M:%S',
+    '%d-%m-%Y %H:%M',
 ])
 
 DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
@@ -2100,6 +2121,9 @@ def sanitize_filename(s, restricted=False, is_id=False):
             return '_'
         return char
 
+    # Replace look-alike Unicode glyphs
+    if restricted and not is_id:
+        s = unicodedata.normalize('NFKC', s)
     # Handle timestamps
     s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
     result = ''.join(map(replace_insane, s))
@@ -2212,6 +2236,15 @@ def unescapeHTML(s):
         r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
 
 
+def process_communicate_or_kill(p, *args, **kwargs):
+    try:
+        return p.communicate(*args, **kwargs)
+    except BaseException:  # Including KeyboardInterrupt
+        p.kill()
+        p.wait()
+        raise
+
+
 def get_subprocess_encoding():
     if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
         # For subprocess calls, encode with locale encoding
@@ -2957,10 +2990,22 @@ class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
 
 def extract_timezone(date_str):
     m = re.search(
-        r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
-        date_str)
+        r'''(?x)
+            ^.{8,}?                                              # >=8 char non-TZ prefix, if present
+            (?P<tz>Z|                                            # just the UTC Z, or
+                (?:(?<=.\b\d{4}|\b\d{2}:\d\d)|                   # preceded by 4 digits or hh:mm or
+                   (?<!.\b[a-zA-Z]{3}|[a-zA-Z]{4}|..\b\d\d))     # not preceded by 3 alpha word or >= 4 alpha or 2 digits
+                   [ ]?                                          # optional space
+                (?P<sign>\+|-)                                   # +/-
+                (?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})       # hh[:]mm
+            $)
+        ''', date_str)
     if not m:
-        timezone = datetime.timedelta()
+        m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
+        timezone = TIMEZONE_NAMES.get(m and m.group('tz').strip())
+        if timezone is not None:
+            date_str = date_str[:-len(m.group('tz'))]
+        timezone = datetime.timedelta(hours=timezone or 0)
     else:
         date_str = date_str[:-len(m.group('tz'))]
         if not m.group('sign'):
@@ -3028,7 +3073,8 @@ def unified_timestamp(date_str, day_first=True):
     if date_str is None:
         return None
 
-    date_str = re.sub(r'[,|]', '', date_str)
+    date_str = re.sub(r'\s+', ' ', re.sub(
+        r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?)(day)?', '', date_str))
 
     pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
     timezone, date_str = extract_timezone(date_str)
@@ -3054,7 +3100,7 @@ def unified_timestamp(date_str, day_first=True):
             pass
     timetuple = email.utils.parsedate_tz(date_str)
     if timetuple:
-        return calendar.timegm(timetuple) + pm_delta * 3600
+        return calendar.timegm(timetuple) + pm_delta * 3600 - timezone.total_seconds()
 
 
 def determine_ext(url, default_ext='unknown_video'):
@@ -3664,13 +3710,11 @@ def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
     if get_attr:
         if v is not None:
             v = getattr(v, get_attr, None)
-    if v == '':
-        v = None
-    if v is None:
+    if v in (None, ''):
         return default
     try:
         return int(v) * invscale // scale
-    except (ValueError, TypeError):
+    except (ValueError, TypeError, OverflowError):
         return default
 
 
@@ -3788,7 +3832,8 @@ def check_executable(exe, args=[]):
     """ Checks if the given binary is installed somewhere in PATH, and returns its name.
     args can be a list of arguments for a short output (like -version) """
     try:
-        subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
+        process_communicate_or_kill(subprocess.Popen(
+            [exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
     except OSError:
         return False
     return exe
@@ -3802,10 +3847,10 @@ def get_exe_version(exe, args=['--version'],
         # STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
         # SIGTTOU if youtube-dl is run in the background.
         # See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656
-        out, _ = subprocess.Popen(
+        out, _ = process_communicate_or_kill(subprocess.Popen(
             [encodeArgument(exe)] + args,
             stdin=subprocess.PIPE,
-            stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
+            stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
     except OSError:
         return False
     if isinstance(out, bytes):  # Python 2.x
@@ -3824,6 +3869,105 @@ def detect_exe_version(output, version_re=None, unrecognized='present'):
         return unrecognized
 
 
+class LazyList(compat_collections_abc.Sequence):
+    """Lazy immutable list from an iterable
+    Note that slices of a LazyList are lists and not LazyList"""
+
+    class IndexError(IndexError):
+        def __init__(self, cause=None):
+            if cause:
+                # reproduce `raise from`
+                self.__cause__ = cause
+            super(IndexError, self).__init__()
+
+    def __init__(self, iterable, **kwargs):
+        # kwarg-only
+        reverse = kwargs.get('reverse', False)
+        _cache = kwargs.get('_cache')
+
+        self._iterable = iter(iterable)
+        self._cache = [] if _cache is None else _cache
+        self._reversed = reverse
+
+    def __iter__(self):
+        if self._reversed:
+            # We need to consume the entire iterable to iterate in reverse
+            for item in self.exhaust():
+                yield item
+            return
+        for item in self._cache:
+            yield item
+        for item in self._iterable:
+            self._cache.append(item)
+            yield item
+
+    def _exhaust(self):
+        self._cache.extend(self._iterable)
+        self._iterable = []  # Discard the emptied iterable to make it pickle-able
+        return self._cache
+
+    def exhaust(self):
+        """Evaluate the entire iterable"""
+        return self._exhaust()[::-1 if self._reversed else 1]
+
+    @staticmethod
+    def _reverse_index(x):
+        return None if x is None else ~x
+
+    def __getitem__(self, idx):
+        if isinstance(idx, slice):
+            if self._reversed:
+                idx = slice(self._reverse_index(idx.start), self._reverse_index(idx.stop), -(idx.step or 1))
+            start, stop, step = idx.start, idx.stop, idx.step or 1
+        elif isinstance(idx, int):
+            if self._reversed:
+                idx = self._reverse_index(idx)
+            start, stop, step = idx, idx, 0
+        else:
+            raise TypeError('indices must be integers or slices')
+        if ((start or 0) < 0 or (stop or 0) < 0
+                or (start is None and step < 0)
+                or (stop is None and step > 0)):
+            # We need to consume the entire iterable to be able to slice from the end
+            # Obviously, never use this with infinite iterables
+            self._exhaust()
+            try:
+                return self._cache[idx]
+            except IndexError as e:
+                raise self.IndexError(e)
+        n = max(start or 0, stop or 0) - len(self._cache) + 1
+        if n > 0:
+            self._cache.extend(itertools.islice(self._iterable, n))
+        try:
+            return self._cache[idx]
+        except IndexError as e:
+            raise self.IndexError(e)
+
+    def __bool__(self):
+        try:
+            self[-1] if self._reversed else self[0]
+        except self.IndexError:
+            return False
+        return True
+
+    def __len__(self):
+        self._exhaust()
+        return len(self._cache)
+
+    def __reversed__(self):
+        return type(self)(self._iterable, reverse=not self._reversed, _cache=self._cache)
+
+    def __copy__(self):
+        return type(self)(self._iterable, reverse=self._reversed, _cache=self._cache)
+
+    def __repr__(self):
+        # repr and str should mimic a list. So we exhaust the iterable
+        return repr(self.exhaust())
+
+    def __str__(self):
+        return repr(self.exhaust())
+
+
 class PagedList(object):
     def __len__(self):
         # This is only useful for tests
@@ -3931,7 +4075,8 @@ def escape_rfc3986(s):
     """Escape non-ASCII characters as suggested by RFC 3986"""
     if sys.version_info < (3, 0) and isinstance(s, compat_str):
         s = s.encode('utf-8')
-    return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
+    # ensure unicode: after quoting, it can always be converted
+    return compat_str(compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]"))
 
 
 def escape_url(url):
@@ -4048,6 +4193,10 @@ def multipart_encode(data, boundary=None):
     return out, content_type
 
 
+def variadic(x, allowed_types=(compat_str, bytes, dict)):
+    return x if isinstance(x, compat_collections_abc.Iterable) and not isinstance(x, allowed_types) else (x,)
+
+
 def dict_get(d, key_or_keys, default=None, skip_false_values=True):
     if isinstance(key_or_keys, (list, tuple)):
         for key in key_or_keys:
@@ -4058,6 +4207,23 @@ def dict_get(d, key_or_keys, default=None, skip_false_values=True):
     return d.get(key_or_keys, default)
 
 
+def try_call(*funcs, **kwargs):
+
+    # parameter defaults
+    expected_type = kwargs.get('expected_type')
+    fargs = kwargs.get('args', [])
+    fkwargs = kwargs.get('kwargs', {})
+
+    for f in funcs:
+        try:
+            val = f(*fargs, **fkwargs)
+        except (AttributeError, KeyError, TypeError, IndexError, ZeroDivisionError):
+            pass
+        else:
+            if expected_type is None or isinstance(val, expected_type):
+                return val
+
+
 def try_get(src, getter, expected_type=None):
     if not isinstance(getter, (list, tuple)):
         getter = [getter]
@@ -5744,7 +5910,7 @@ def write_xattr(path, key, value):
                         cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
                 except EnvironmentError as e:
                     raise XAttrMetadataError(e.errno, e.strerror)
-                stdout, stderr = p.communicate()
+                stdout, stderr = process_communicate_or_kill(p)
                 stderr = stderr.decode('utf-8', 'replace')
                 if p.returncode != 0:
                     raise XAttrMetadataError(p.returncode, stderr)
@@ -5791,3 +5957,220 @@ def clean_podcast_url(url):
                 st\.fm # https://podsights.com/docs/
             )/e
         )/''', '', url)
+
+
+def traverse_obj(obj, *paths, **kwargs):
+    """
+    Safely traverse nested `dict`s and `Sequence`s
+
+    >>> obj = [{}, {"key": "value"}]
+    >>> traverse_obj(obj, (1, "key"))
+    "value"
+
+    Each of the provided `paths` is tested and the first producing a valid result will be returned.
+    The next path will also be tested if the path branched but no results could be found.
+    Supported values for traversal are `Mapping`, `Sequence` and `re.Match`.
+    A value of None is treated as the absence of a value.
+
+    The paths will be wrapped in `variadic`, so that `'key'` is conveniently the same as `('key', )`.
+
+    The keys in the path can be one of:
+        - `None`:           Return the current object.
+        - `str`/`int`:      Return `obj[key]`. For `re.Match, return `obj.group(key)`.
+        - `slice`:          Branch out and return all values in `obj[key]`.
+        - `Ellipsis`:       Branch out and return a list of all values.
+        - `tuple`/`list`:   Branch out and return a list of all matching values.
+                            Read as: `[traverse_obj(obj, branch) for branch in branches]`.
+        - `function`:       Branch out and return values filtered by the function.
+                            Read as: `[value for key, value in obj if function(key, value)]`.
+                            For `Sequence`s, `key` is the index of the value.
+        - `dict`            Transform the current object and return a matching dict.
+                            Read as: `{key: traverse_obj(obj, path) for key, path in dct.items()}`.
+
+        `tuple`, `list`, and `dict` all support nested paths and branches.
+
+    @params paths           Paths which to traverse by.
+    Keyword arguments:
+    @param default          Value to return if the paths do not match.
+    @param expected_type    If a `type`, only accept final values of this type.
+                            If any other callable, try to call the function on each result.
+    @param get_all          If `False`, return the first matching result, otherwise all matching ones.
+    @param casesense        If `False`, consider string dictionary keys as case insensitive.
+
+    The following are only meant to be used by YoutubeDL.prepare_outtmpl and are not part of the API
+
+    @param _is_user_input    Whether the keys are generated from user input.
+                            If `True` strings get converted to `int`/`slice` if needed.
+    @param _traverse_string  Whether to traverse into objects as strings.
+                            If `True`, any non-compatible object will first be
+                            converted into a string and then traversed into.
+
+
+    @returns                The result of the object traversal.
+                            If successful, `get_all=True`, and the path branches at least once,
+                            then a list of results is returned instead.
+                            A list is always returned if the last path branches and no `default` is given.
+    """
+
+    # parameter defaults
+    default = kwargs.get('default', NO_DEFAULT)
+    expected_type = kwargs.get('expected_type')
+    get_all = kwargs.get('get_all', True)
+    casesense = kwargs.get('casesense', True)
+    _is_user_input = kwargs.get('_is_user_input', False)
+    _traverse_string = kwargs.get('_traverse_string', False)
+
+    # instant compat
+    str = compat_str
+
+    is_sequence = lambda x: isinstance(x, compat_collections_abc.Sequence) and not isinstance(x, (str, bytes))
+    # stand-in until compat_re_Match is added
+    compat_re_Match = type(re.match('a', 'a'))
+    # stand-in until casefold.py is added
+    try:
+        ''.casefold()
+        compat_casefold = lambda s: s.casefold()
+    except AttributeError:
+        compat_casefold = lambda s: s.lower()
+    casefold = lambda k: compat_casefold(k) if isinstance(k, str) else k
+
+    if isinstance(expected_type, type):
+        type_test = lambda val: val if isinstance(val, expected_type) else None
+    else:
+        type_test = lambda val: try_call(expected_type or IDENTITY, args=(val,))
+
+    def from_iterable(iterables):
+        # chain.from_iterable(['ABC', 'DEF']) --> A B C D E F
+        for it in iterables:
+            for item in it:
+                yield item
+
+    def apply_key(key, obj):
+        if obj is None:
+            return
+
+        elif key is None:
+            yield obj
+
+        elif isinstance(key, (list, tuple)):
+            for branch in key:
+                _, result = apply_path(obj, branch)
+                for item in result:
+                    yield item
+
+        elif key is Ellipsis:
+            result = []
+            if isinstance(obj, compat_collections_abc.Mapping):
+                result = obj.values()
+            elif is_sequence(obj):
+                result = obj
+            elif isinstance(obj, compat_re_Match):
+                result = obj.groups()
+            elif _traverse_string:
+                result = str(obj)
+            for item in result:
+                yield item
+
+        elif callable(key):
+            if is_sequence(obj):
+                iter_obj = enumerate(obj)
+            elif isinstance(obj, compat_collections_abc.Mapping):
+                iter_obj = obj.items()
+            elif isinstance(obj, compat_re_Match):
+                iter_obj = enumerate(itertools.chain([obj.group()], obj.groups()))
+            elif _traverse_string:
+                iter_obj = enumerate(str(obj))
+            else:
+                return
+            for item in (v for k, v in iter_obj if try_call(key, args=(k, v))):
+                yield item
+
+        elif isinstance(key, dict):
+            iter_obj = ((k, _traverse_obj(obj, v)) for k, v in key.items())
+            yield dict((k, v if v is not None else default) for k, v in iter_obj
+                       if v is not None or default is not NO_DEFAULT)
+
+        elif isinstance(obj, compat_collections_abc.Mapping):
+            yield (obj.get(key) if casesense or (key in obj)
+                   else next((v for k, v in obj.items() if casefold(k) == key), None))
+
+        elif isinstance(obj, compat_re_Match):
+            if isinstance(key, int) or casesense:
+                try:
+                    yield obj.group(key)
+                    return
+                except IndexError:
+                    pass
+            if not isinstance(key, str):
+                return
+
+            yield next((v for k, v in obj.groupdict().items() if casefold(k) == key), None)
+
+        else:
+            if _is_user_input:
+                key = (int_or_none(key) if ':' not in key
+                       else slice(*map(int_or_none, key.split(':'))))
+
+            if not isinstance(key, (int, slice)):
+                return
+
+            if not is_sequence(obj):
+                if not _traverse_string:
+                    return
+                obj = str(obj)
+
+            try:
+                yield obj[key]
+            except IndexError:
+                pass
+
+    def apply_path(start_obj, path):
+        objs = (start_obj,)
+        has_branched = False
+
+        for key in variadic(path):
+            if _is_user_input and key == ':':
+                key = Ellipsis
+
+            if not casesense and isinstance(key, str):
+                key = compat_casefold(key)
+
+            if key is Ellipsis or isinstance(key, (list, tuple)) or callable(key):
+                has_branched = True
+
+            key_func = functools.partial(apply_key, key)
+            objs = from_iterable(map(key_func, objs))
+
+        return has_branched, objs
+
+    def _traverse_obj(obj, path, use_list=True):
+        has_branched, results = apply_path(obj, path)
+        results = LazyList(x for x in map(type_test, results) if x is not None)
+
+        if get_all and has_branched:
+            return results.exhaust() if results or use_list else None
+
+        return results[0] if results else None
+
+    for index, path in enumerate(paths, 1):
+        use_list = default is NO_DEFAULT and index == len(paths)
+        result = _traverse_obj(obj, path, use_list)
+        if result is not None:
+            return result
+
+    return None if default is NO_DEFAULT else default
+
+
+def get_first(obj, keys, **kwargs):
+    return traverse_obj(obj, (Ellipsis,) + tuple(variadic(keys)), get_all=False, **kwargs)
+
+
+def join_nonempty(*values, **kwargs):
+
+    # parameter defaults
+    delim = kwargs.get('delim', '-')
+    from_dict = kwargs.get('from_dict')
+
+    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)))