[cleanup] Misc

Closes #5576, closes #5887

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,8 +2,6 @@
 
 ### Description of your *pull request* and other information
 
-</details>
-
 <!--
 
 Explanation of your *pull request* in arbitrary form goes here. Please **make sure the description explains the purpose and effect** of your *pull request* and is worded well enough to be understood. Provide as much **context and examples** as possible
@@ -41,3 +39,5 @@ ### What is the purpose of your *pull request*?
 - [ ] New extractor ([Piracy websites will not be accepted](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-website-primarily-used-for-piracy))
 - [ ] Core bug fix/improvement
 - [ ] New feature (It is strongly [recommended to open an issue first](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#adding-new-feature-or-making-overarching-changes))
+
+</details>

.gitignore

@@ -30,6 +30,7 @@ cookies
 *.f4v
 *.flac
 *.flv
+*.gif
 *.jpeg
 *.jpg
 *.m4a
@@ -120,5 +121,5 @@ yt-dlp.zip
 */extractor/lazy_extractors.py
 
 # Plugins
-ytdlp_plugins/*
-yt-dlp-plugins/*
+ytdlp_plugins/
+yt-dlp-plugins

Collaborators.md

@@ -42,7 +42,7 @@ ## [Ashish0804](https://github.com/Ashish0804) <sub><sup>[Inactive]</sup></sub>
 * Improved/fixed support for HiDive, HotStar, Hungama, LBRY, LinkedInLearning, Mxplayer, SonyLiv, TV2, Vimeo, VLive etc
 
 
-## [Lesmiscore](https://github.com/Lesmiscore) (nao20010128nao)
+## [Lesmiscore](https://github.com/Lesmiscore) <sup><sub>(nao20010128nao)</sup></sub>
 
 **Bitcoin**: bc1qfd02r007cutfdjwjmyy9w23rjvtls6ncve7r3s  
 **Monacoin**: mona1q3tf7dzvshrhfe3md379xtvt2n22duhglv5dskr

Makefile

@@ -17,8 +17,8 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
 clean-test:
 	rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
 	*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
-	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
-	*.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
+	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
+	*.mp4 *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
 clean-dist:
 	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
 	yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS .mailmap

README.md

@@ -10,7 +10,7 @@
 [![Discord](https://img.shields.io/discord/807245652072857610?color=blue&labelColor=555555&label=&logo=discord&style=for-the-badge)](https://discord.gg/H5MNcFW63r "Discord")
 [![Supported Sites](https://img.shields.io/badge/-Supported_Sites-brightgreen.svg?style=for-the-badge)](supportedsites.md "Supported Sites")
 [![License: Unlicense](https://img.shields.io/badge/-Unlicense-blue.svg?style=for-the-badge)](LICENSE "License")
-[![CI Status](https://img.shields.io/github/workflow/status/yt-dlp/yt-dlp/Core%20Tests/master?label=Tests&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/actions "CI Status")
+[![CI Status](https://img.shields.io/github/actions/workflow/status/yt-dlp/yt-dlp/core.yml?branch=master&label=Tests&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/actions "CI Status")
 [![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
 [![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge&display_timestamp=committer)](https://github.com/yt-dlp/yt-dlp/commits "Commit History")
 

yt_dlp/YoutubeDL.py

@@ -3392,6 +3392,7 @@ def sanitize_info(info_dict, remove_private_keys=False):
             reject = lambda k, v: v is None or k.startswith('__') or k in {
                 'requested_downloads', 'requested_formats', 'requested_subtitles', 'requested_entries',
                 'entries', 'filepath', '_filename', 'infojson_filename', 'original_url', 'playlist_autonumber',
+                '_format_sort_fields',
             }
         else:
             reject = lambda k, v: False

yt_dlp/__init__.py

@@ -332,7 +332,7 @@ def parse_chapters(name, value):
                     mobj = range_ != '-' and re.fullmatch(r'([^-]+)?\s*-\s*([^-]+)?', range_)
                     dur = mobj and (parse_timestamp(mobj.group(1) or '0'), parse_timestamp(mobj.group(2) or 'inf'))
                     if None in (dur or [None]):
-                        raise ValueError(f'invalid {name} time range "{regex}". Must be of the form *start-end')
+                        raise ValueError(f'invalid {name} time range "{regex}". Must be of the form "*start-end"')
                     ranges.append(dur)
                 continue
             try:

yt_dlp/extractor/bilibili.py

@@ -1013,7 +1013,7 @@ def _real_extract(self, url):
 
 
 class BiliIntlSeriesIE(BiliIntlBaseIE):
-    IE_NAME = 'biliintl:series'
+    IE_NAME = 'biliIntl:series'
     _VALID_URL = r'https?://(?:www\.)?bili(?:bili\.tv|intl\.com)/(?:[a-zA-Z]{2}/)?play/(?P<id>\d+)/?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://www.bilibili.tv/en/play/34613',

yt_dlp/extractor/common.py

@@ -1262,7 +1262,9 @@ def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=Tr
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
         res = self._search_regex(pattern, string, name, default, fatal, flags, group)
-        if res:
+        if isinstance(res, tuple):
+            return [clean_html(r).strip() for r in res]
+        elif res:
             return clean_html(res).strip()
         else:
             return res
@@ -3512,7 +3514,7 @@ def description(cls, *, markdown=True, search_examples=None):
         elif cls.IE_DESC:
             desc += f' {cls.IE_DESC}'
         if cls.SEARCH_KEY:
-            desc += f'; "{cls.SEARCH_KEY}:" prefix'
+            desc += f'{";" if cls.IE_DESC else ""} "{cls.SEARCH_KEY}:" prefix'
             if search_examples:
                 _COUNTS = ('', '5', '10', 'all')
                 desc += f' (e.g. "{cls.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(search_examples)}")'

yt_dlp/extractor/crunchyroll.py

@@ -182,7 +182,7 @@ def _real_extract(self, url):
             self.to_screen(
                 'To get all formats of a hardsub language, use '
                 '"--extractor-args crunchyrollbeta:hardsub=<language_code or all>". '
-                'See https://github.com/yt-dlp/yt-dlp#crunchyrollbeta for more info',
+                'See https://github.com/yt-dlp/yt-dlp#crunchyrollbeta-crunchyroll for more info',
                 only_once=True)
         else:
             full_format_langs = set(map(str.lower, available_formats))

yt_dlp/extractor/yandexvideo.py

@@ -270,9 +270,9 @@ def _real_extract(self, url):
         for s_url in stream_urls:
             ext = determine_ext(s_url)
             if ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(s_url, id, mpd_id='dash'))
+                formats.extend(self._extract_mpd_formats(s_url, video_id, mpd_id='dash'))
             elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(s_url, id, 'mp4'))
+                formats.extend(self._extract_m3u8_formats(s_url, video_id, 'mp4'))
         return {
             'id': video_id,
             'title': video_json.get('title') or self._og_search_title(webpage),

yt_dlp/extractor/youtube.py

@@ -292,7 +292,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
 
     _RESERVED_NAMES = (
-        r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
+        r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
         r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
         r'browse|oembed|get_video_info|iframe_api|s/player|source|'
         r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
@@ -3683,7 +3683,7 @@ def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, l
                 'url': fmt_url,
                 'width': int_or_none(fmt.get('width')),
                 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
-                                          'desc' if language_preference < -1 else ''),
+                                          'desc' if language_preference < -1 else '') or None,
                 'language_preference': language_preference,
                 # Strictly de-prioritize damaged and 3gp formats
                 'preference': -10 if is_damaged else -2 if itag == '17' else None,

yt_dlp/options.py

@@ -109,7 +109,7 @@ def load_configs():
     opts = optparse.Values({'verbose': True, 'print_help': False})
     try:
         try:
-            if overrideArguments:
+            if overrideArguments is not None:
                 root.append_config(overrideArguments, label='Override')
             else:
                 root.append_config(sys.argv[1:], label='Command-line')
@@ -904,11 +904,11 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
             'This option can be used multiple times to set the sleep for the different retry types, '
             'e.g. --retry-sleep linear=1::2 --retry-sleep fragment:exp=1:20'))
     downloader.add_option(
-        '--skip-unavailable-fragments', '--no-abort-on-unavailable-fragment',
+        '--skip-unavailable-fragments', '--no-abort-on-unavailable-fragments',
         action='store_true', dest='skip_unavailable_fragments', default=True,
-        help='Skip unavailable fragments for DASH, hlsnative and ISM downloads (default) (Alias: --no-abort-on-unavailable-fragment)')
+        help='Skip unavailable fragments for DASH, hlsnative and ISM downloads (default) (Alias: --no-abort-on-unavailable-fragments)')
     downloader.add_option(
-        '--abort-on-unavailable-fragment', '--no-skip-unavailable-fragments',
+        '--abort-on-unavailable-fragments', '--no-skip-unavailable-fragments',
         action='store_false', dest='skip_unavailable_fragments',
         help='Abort download if a fragment is unavailable (Alias: --no-skip-unavailable-fragments)')
     downloader.add_option(

yt_dlp/postprocessor/ffmpeg.py

@@ -407,7 +407,7 @@ def concat_files(self, in_files, out_file, concat_opts=None):
         """
         concat_file = f'{out_file}.concat'
         self.write_debug(f'Writing concat spec to {concat_file}')
-        with open(concat_file, 'wt', encoding='utf-8') as f:
+        with open(concat_file, 'w', encoding='utf-8') as f:
             f.writelines(self._concat_spec(in_files, concat_opts))
 
         out_flags = list(self.stream_copy_opts(ext=determine_ext(out_file)))
@@ -711,7 +711,7 @@ def run(self, info):
 
     @staticmethod
     def _get_chapter_opts(chapters, metadata_filename):
-        with open(metadata_filename, 'wt', encoding='utf-8') as f:
+        with open(metadata_filename, 'w', encoding='utf-8') as f:
             def ffmpeg_escape(text):
                 return re.sub(r'([\\=;#\n])', r'\\\1', text)
 
@@ -981,7 +981,7 @@ def run(self, info):
                 with open(dfxp_file, 'rb') as f:
                     srt_data = dfxp2srt(f.read())
 
-                with open(srt_file, 'wt', encoding='utf-8') as f:
+                with open(srt_file, 'w', encoding='utf-8') as f:
                     f.write(srt_data)
                 old_file = srt_file
 

yt_dlp/utils.py

@@ -3368,7 +3368,7 @@ def fix_kv(m):
             try:
                 if not strict:
                     json.loads(vars[v])
-            except json.decoder.JSONDecodeError:
+            except json.JSONDecodeError:
                 return json.dumps(vars[v])
             else:
                 return vars[v]