[cleanup] Misc cleanup

README.md

@@ -71,7 +71,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 # NEW FEATURES
 
-* Based on **youtube-dl 2021.12.17 [commit/8a158a9](https://github.com/ytdl-org/youtube-dl/commit/8a158a936c8b002ef536e9e2b778ded02c09c0fa)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc 2020.11.11-3 [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
+* Merged with **youtube-dl v2021.12.17 [commit/8a158a9](https://github.com/ytdl-org/youtube-dl/commit/8a158a936c8b002ef536e9e2b778ded02c09c0fa)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc v2020.11.11-3 [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
 
 * **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
 
@@ -79,18 +79,13 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 * **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--write-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, playlist infojson etc. Note that the NicoNico livestreams are not available. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
 
-* **Youtube improvements**:
+* **YouTube improvements**:
-    * All Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`, `:ytnotif`) and private playlists supports downloading multiple pages of content
+    * Supports Clips, Stories (`ytstories:<channel UCID>`), Search (including filters)**\***, YouTube Music Search, Channel-specific search, Search prefixes (`ytsearch:`, `ytsearchdate:`)**\***, Mixes, YouTube Music Albums/Channels ([except self-uploaded music](https://github.com/yt-dlp/yt-dlp/issues/723)), and Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`, `:ytnotif`)
-    * Search (`ytsearch:`, `ytsearchdate:`), search URLs and in-channel search works
+    * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326) **\***
-    * Mixes supports downloading multiple pages of content
+    * Supports some (but not all) age-gated content without cookies
-    * Some (but not all) age-gated content can be downloaded without cookies
+    * Download livestreams from the start using `--live-from-start` (*experimental*)
-    * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326)
+    * `255kbps` audio is extracted (if available) from YouTube Music when premium cookies are given
     * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
-    * `255kbps` audio is extracted (if available) from youtube music when premium cookies are given
-    * Youtube music Albums, channels etc can be downloaded ([except self-uploaded music](https://github.com/yt-dlp/yt-dlp/issues/723))
-    * Download livestreams from the start using `--live-from-start` (experimental)
-    * Support for downloading stories (`ytstories:<channel UCID>`) 
-    * Support for downloading clips
 
 * **Cookies from browser**: Cookies can be automatically extracted from all major web browsers using `--cookies-from-browser BROWSER[+KEYRING][:PROFILE]`
 
@@ -124,6 +119,8 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 See [changelog](Changelog.md) or [commits](https://github.com/yt-dlp/yt-dlp/commits) for the full list of changes
 
+Features marked with a **\*** have been back-ported to youtube-dl
+
 ### Differences in default behavior
 
 Some of yt-dlp's default options are different from that of youtube-dl and youtube-dlc:

requirements.txt

@@ -3,4 +3,4 @@ pycryptodomex
 websockets
 brotli; platform_python_implementation=='CPython'
 brotlicffi; platform_python_implementation!='CPython'
-certifi
+certifi

test/test_download.py

@@ -273,7 +273,11 @@ def batch_generator(name, num_tests):
 
     def test_template(self):
         for i in range(num_tests):
-            getattr(self, f'test_{name}_{i}' if i else f'test_{name}')()
+            test_name = f'test_{name}_{i}' if i else f'test_{name}'
+            try:
+                getattr(self, test_name)()
+            except unittest.SkipTest:
+                print(f'Skipped {test_name}')
 
     return test_template
 

yt_dlp/YoutubeDL.py

@@ -3531,7 +3531,7 @@ class YoutubeDL:
                     'none', '' if f.get('vcodec') == 'none'
                             else self._format_out('video only', self.Styles.SUPPRESS)),
                 format_field(f, 'abr', '\t%dk'),
-                format_field(f, 'asr', '\t%dHz'),
+                format_field(f, 'asr', '\t%s', func=format_decimal_suffix),
                 join_nonempty(
                     self._format_out('UNSUPPORTED', 'light red') if f.get('ext') in ('f4f', 'f4m') else None,
                     format_field(f, 'language', '[%s]'),

yt_dlp/compat/_legacy.py

@@ -44,14 +44,26 @@ def compat_setenv(key, value, env=os.environ):
 
 
 compat_basestring = str
+compat_chr = chr
 compat_collections_abc = collections.abc
+compat_cookiejar = http.cookiejar
+compat_cookiejar_Cookie = http.cookiejar.Cookie
 compat_cookies = http.cookies
+compat_cookies_SimpleCookie = http.cookies.SimpleCookie
 compat_etree_Element = etree.Element
 compat_etree_register_namespace = etree.register_namespace
 compat_filter = filter
+compat_get_terminal_size = shutil.get_terminal_size
 compat_getenv = os.getenv
+compat_getpass = getpass.getpass
+compat_html_entities = html.entities
+compat_html_entities_html5 = html.entities.html5
+compat_HTMLParser = html.parser.HTMLParser
+compat_http_client = http.client
+compat_http_server = http.server
 compat_input = input
 compat_integer_types = (int, )
+compat_itertools_count = itertools.count
 compat_kwargs = lambda kwargs: kwargs
 compat_map = map
 compat_numeric_types = (int, float, complex)
@@ -59,34 +71,22 @@ compat_print = print
 compat_shlex_split = shlex.split
 compat_socket_create_connection = socket.create_connection
 compat_Struct = struct.Struct
+compat_struct_pack = struct.pack
+compat_struct_unpack = struct.unpack
 compat_subprocess_get_DEVNULL = lambda: DEVNULL
+compat_tokenize_tokenize = tokenize.tokenize
+compat_urllib_error = urllib.error
+compat_urllib_parse = urllib.parse
 compat_urllib_parse_quote = urllib.parse.quote
 compat_urllib_parse_quote_plus = urllib.parse.quote_plus
+compat_urllib_parse_unquote_plus = urllib.parse.unquote_plus
 compat_urllib_parse_unquote_to_bytes = urllib.parse.unquote_to_bytes
 compat_urllib_parse_urlunparse = urllib.parse.urlunparse
-compat_urllib_request_DataHandler = urllib.request.DataHandler
 compat_urllib_request = urllib.request
+compat_urllib_request_DataHandler = urllib.request.DataHandler
 compat_urllib_response = urllib.response
 compat_urlretrieve = urllib.request.urlretrieve
 compat_xml_parse_error = etree.ParseError
 compat_xpath = lambda xpath: xpath
 compat_zip = zip
 workaround_optparse_bug9161 = lambda: None
-compat_getpass = getpass.getpass
-compat_chr = chr
-compat_urllib_parse = urllib.parse
-compat_itertools_count = itertools.count
-compat_cookiejar = http.cookiejar
-compat_cookiejar_Cookie = http.cookiejar.Cookie
-compat_cookies_SimpleCookie = http.cookies.SimpleCookie
-compat_get_terminal_size = shutil.get_terminal_size
-compat_html_entities = html.entities
-compat_html_entities_html5 = html.entities.html5
-compat_tokenize_tokenize = tokenize.tokenize
-compat_HTMLParser = html.parser.HTMLParser
-compat_http_client = http.client
-compat_http_server = http.server
-compat_struct_pack = struct.pack
-compat_struct_unpack = struct.unpack
-compat_urllib_error = urllib.error
-compat_urllib_parse_unquote_plus = urllib.parse.unquote_plus

yt_dlp/downloader/__init__.py

@@ -59,10 +59,11 @@ PROTOCOL_MAP = {
 
 def shorten_protocol_name(proto, simplify=False):
     short_protocol_names = {
-        'm3u8_native': 'm3u8_n',
+        'm3u8_native': 'm3u8',
-        'rtmp_ffmpeg': 'rtmp_f',
+        'm3u8': 'm3u8F',
+        'rtmp_ffmpeg': 'rtmpF',
         'http_dash_segments': 'dash',
-        'http_dash_segments_generator': 'dash_g',
+        'http_dash_segments_generator': 'dashG',
         'niconico_dmc': 'dmc',
         'websocket_frag': 'WSfrag',
     }
@@ -70,6 +71,7 @@ def shorten_protocol_name(proto, simplify=False):
         short_protocol_names.update({
             'https': 'http',
             'ftps': 'ftp',
+            'm3u8': 'm3u8',  # Reverse above m3u8 mapping
             'm3u8_native': 'm3u8',
             'http_dash_segments_generator': 'dash',
             'rtmp_ffmpeg': 'rtmp',

yt_dlp/downloader/hls.py

@@ -69,7 +69,7 @@ class HlsFD(FragmentFD):
             elif no_crypto:
                 message = ('The stream has AES-128 encryption and neither ffmpeg nor pycryptodomex are available; '
                            'Decryption will be performed natively, but will be extremely slow')
-            elif re.search(r'#EXT-X-MEDIA-SEQUENCE:(?!0$)', s):
+            elif info_dict.get('extractor_key') == 'Generic' and re.search(r'(?m)#EXT-X-MEDIA-SEQUENCE:(?!0$)', s):
                 install_ffmpeg = '' if has_ffmpeg else 'install ffmpeg and '
                 message = ('Live HLS streams are not supported by the native downloader. If this is a livestream, '
                            f'please {install_ffmpeg}add "--downloader ffmpeg --hls-use-mpegts" to your command')

yt_dlp/extractor/generic.py

@@ -2825,12 +2825,22 @@ class GenericIE(InfoExtractor):
                         new_url, {'force_videoid': force_videoid})
                 return self.url_result(new_url)
 
+        def request_webpage():
+            request = sanitized_Request(url)
+            # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
+            # making it impossible to download only chunk of the file (yet we need only 512kB to
+            # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
+            # that will always result in downloading the whole file that is not desirable.
+            # Therefore for extraction pass we have to override Accept-Encoding to any in order
+            # to accept raw bytes and being able to download only a chunk.
+            # It may probably better to solve this by checking Content-Type for application/octet-stream
+            # after HEAD request finishes, but not sure if we can rely on this.
+            request.add_header('Accept-Encoding', '*')
+            return self._request_webpage(request, video_id)
+
         full_response = None
         if head_response is False:
-            request = sanitized_Request(url)
+            head_response = full_response = request_webpage()
-            request.add_header('Accept-Encoding', '*')
-            full_response = self._request_webpage(request, video_id)
-            head_response = full_response
 
         info_dict = {
             'id': video_id,
@@ -2868,19 +2878,7 @@ class GenericIE(InfoExtractor):
             self.report_warning(
                 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
 
-        if not full_response:
+        full_response = full_response or request_webpage()
-            request = sanitized_Request(url)
-            # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
-            # making it impossible to download only chunk of the file (yet we need only 512kB to
-            # test whether it's HTML or not). According to yt-dlp default Accept-Encoding
-            # that will always result in downloading the whole file that is not desirable.
-            # Therefore for extraction pass we have to override Accept-Encoding to any in order
-            # to accept raw bytes and being able to download only a chunk.
-            # It may probably better to solve this by checking Content-Type for application/octet-stream
-            # after HEAD request finishes, but not sure if we can rely on this.
-            request.add_header('Accept-Encoding', '*')
-            full_response = self._request_webpage(request, video_id)
-
         first_bytes = full_response.read(512)
 
         # Is it an M3U playlist?

yt_dlp/extractor/youtube.py

@@ -2467,6 +2467,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
         assert os.path.basename(func_id) == func_id
 
+        self.write_debug(f'Extracting signature function {func_id}')
         cache_spec = self.cache.load('youtube-sigfuncs', func_id)
         if cache_spec is not None:
             return lambda s: ''.join(s[i] for i in cache_spec)
@@ -2714,10 +2715,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     @classmethod
     def extract_id(cls, url):
-        mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
+        video_id = cls.get_temp_id(url)
-        if mobj is None:
+        if not video_id:
-            raise ExtractorError('Invalid URL: %s' % url)
+            raise ExtractorError(f'Invalid URL: {url}')
-        return mobj.group('id')
+        return video_id
 
     def _extract_chapters_from_json(self, data, duration):
         chapter_list = traverse_obj(

yt_dlp/utils.py

@@ -234,7 +234,7 @@ DATE_FORMATS_MONTH_FIRST.extend([
 ])
 
 PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
-JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
+JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>\s*(?P<json_ld>{.+?})\s*</script>'
 
 NUMBER_RE = r'\d+(?:\.\d+)?'
 
@@ -673,8 +673,8 @@ def sanitize_filename(s, restricted=False, is_id=NO_DEFAULT):
     s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)  # Handle timestamps
     result = ''.join(map(replace_insane, s))
     if is_id is NO_DEFAULT:
-        result = re.sub('(\0.)(?:(?=\\1)..)+', r'\1', result)  # Remove repeated substitute chars
+        result = re.sub(r'(\0.)(?:(?=\1)..)+', r'\1', result)  # Remove repeated substitute chars
-        STRIP_RE = '(?:\0.|[ _-])*'
+        STRIP_RE = r'(?:\0.|[ _-])*'
         result = re.sub(f'^\0.{STRIP_RE}|{STRIP_RE}\0.$', '', result)  # Remove substitute chars from start/end
     result = result.replace('\0', '') or '_'
 
@@ -2400,8 +2400,7 @@ def remove_quotes(s):
 
 
 def get_domain(url):
-    domain = re.match(r'(?:https?:\/\/)?(?:www\.)?(?P<domain>[^\n\/]+\.[^\n\/]+)(?:\/(.*))?', url)
+    return '.'.join(urllib.parse.urlparse(url).netloc.rsplit('.', 2)[-2:])
-    return domain.group('domain') if domain else None
 
 
 def url_basename(url):