[cleanup] Lint and misc cleanup

yt_dlp/extractor/acfun.py

@@ -161,7 +161,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         ac_idx = parse_qs(url).get('ac', [None])[-1]
-        video_id = f'{video_id}{format_field(ac_idx, template="__%s")}'
+        video_id = f'{video_id}{format_field(ac_idx, None, "__%s")}'
 
         webpage = self._download_webpage(url, video_id)
         json_bangumi_data = self._search_json(r'window.bangumiData\s*=', webpage, 'bangumiData', video_id)

yt_dlp/extractor/bilibili.py

@@ -368,7 +368,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
                 or '正在观看预览，大会员免费看全片' in webpage):
             self.raise_login_required('This video is for premium members only')
 
-        play_info = self._search_json(r'window\.__playinfo__\s*=\s*', webpage, 'play info', video_id)['data']
+        play_info = self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id)['data']
         formats = self.extract_formats(play_info)
         if (not formats and '成为大会员抢先看' in webpage
                 and play_info.get('durl') and not play_info.get('dash')):

yt_dlp/extractor/common.py

@@ -3725,7 +3725,8 @@ class InfoExtractor:
         if not cls.working():
             desc += ' (**Currently broken**)' if markdown else ' (Currently broken)'
 
-        name = f' - **{cls.IE_NAME}**' if markdown else cls.IE_NAME
+        # Escape emojis. Ref: https://github.com/github/markup/issues/1153
+        name = (' - **%s**' % re.sub(r':(\w+:)', ':\u200B\\g<1>', cls.IE_NAME)) if markdown else cls.IE_NAME
         return f'{name}:{desc}' if desc else name
 
     def extract_subtitles(self, *args, **kwargs):

yt_dlp/extractor/manyvids.py

@@ -68,7 +68,7 @@ class ManyVidsIE(InfoExtractor):
         )
 
         def txt_or_none(s, default=None):
-            return (s.strip() or default) if isinstance(s, compat_str) else default
+            return (s.strip() or default) if isinstance(s, str) else default
 
         uploader = txt_or_none(info.get('data-meta-author'))
 

yt_dlp/extractor/neteasemusic.py

@@ -1,3 +1,4 @@
+import itertools
 import json
 import re
 import time
@@ -39,8 +40,7 @@ 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):
+    def make_player_api_request_data_and_headers(self, song_id, bitrate):
         KEY = b'e82ckenh8dichen8'
         URL = '/api/song/enhance/player/url'
         now = int(time.time() * 1000)

yt_dlp/extractor/yandexvideo.py

@@ -255,7 +255,7 @@ class ZenYandexIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        redirect = self._search_json(r'var it\s*=\s*', webpage, 'redirect', id, default={}).get('retpath')
+        redirect = self._search_json(r'var it\s*=', webpage, 'redirect', id, default={}).get('retpath')
         if redirect:
             video_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, video_id, note='Redirecting')
@@ -373,7 +373,7 @@ class ZenYandexChannelIE(InfoExtractor):
         item_id = self._match_id(url)
         webpage = self._download_webpage(url, item_id)
         redirect = self._search_json(
-            r'var it\s*=\s*', webpage, 'redirect', item_id, default={}).get('retpath')
+            r'var it\s*=', webpage, 'redirect', item_id, default={}).get('retpath')
         if redirect:
             item_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, item_id, note='Redirecting')

yt_dlp/options.py

@@ -294,9 +294,10 @@ def create_parser():
 
         aliases = (x if x.startswith('-') else f'--{x}' for x in map(str.strip, aliases.split(',')))
         try:
+            args = [f'ARG{i}' for i in range(nargs)]
             alias_group.add_option(
-                *aliases, help=opts, nargs=nargs, dest=parser.ALIAS_DEST, type='str' if nargs else None,
-                metavar=' '.join(f'ARG{i}' for i in range(nargs)), action='callback',
+                *aliases, nargs=nargs, dest=parser.ALIAS_DEST, type='str' if nargs else None,
+                metavar=' '.join(args), help=opts.format(*args), action='callback',
                 callback=_alias_callback, callback_kwargs={'opts': opts, 'nargs': nargs})
         except Exception as err:
             raise optparse.OptionValueError(f'wrong {opt_str} formatting; {err}')
@@ -549,11 +550,11 @@ def create_parser():
     selection.add_option(
         '--min-filesize',
         metavar='SIZE', dest='min_filesize', default=None,
-        help='Do not download any videos smaller than SIZE, e.g. 50k or 44.6M')
+        help='Abort download if filesize is smaller than SIZE, e.g. 50k or 44.6M')
     selection.add_option(
         '--max-filesize',
         metavar='SIZE', dest='max_filesize', default=None,
-        help='Do not download any videos larger than SIZE, e.g. 50k or 44.6M')
+        help='Abort download if filesize if larger than SIZE, e.g. 50k or 44.6M')
     selection.add_option(
         '--date',
         metavar='DATE', dest='date', default=None,

yt_dlp/utils.py

@@ -480,6 +480,7 @@ class HTMLBreakOnClosingTagParser(html.parser.HTMLParser):
             raise self.HTMLBreakOnClosingTagException()
 
 
+# XXX: This should be far less strict
 def get_element_text_and_html_by_tag(tag, html):
     """
     For the first element with the specified tag in the passed HTML document