[cleanup] Misc cleanup

Closes #1942 #1976 #2020 #2058 #1984

yt_dlp/YoutubeDL.py

@@ -1495,7 +1495,7 @@ class YoutubeDL(object):
                 self.write_debug('Additional URLs: "%s"' % '", "'.join(additional_urls))
                 ie_result['additional_entries'] = [
                     self.extract_info(
-                        url, download, extra_info,
+                        url, download, extra_info=extra_info,
                         force_generic_extractor=self.params.get('force_generic_extractor'))
                     for url in additional_urls
                 ]
@@ -2474,10 +2474,7 @@ class YoutubeDL(object):
                     info_dict['id'], automatic_captions, 'automatic captions')
             self.list_subtitles(info_dict['id'], subtitles, 'subtitles')
         if self.params.get('listformats') or interactive_format_selection:
-            if not info_dict.get('formats') and not info_dict.get('url'):
-                self.to_screen('%s has no formats' % info_dict['id'])
-            else:
-                self.list_formats(info_dict)
+            self.list_formats(info_dict)
         if list_only:
             # Without this printing, -F --print-json will not work
             self.__forced_printings(info_dict, self.prepare_filename(info_dict), incomplete=True)
@@ -3361,6 +3358,11 @@ class YoutubeDL(object):
         return headers
 
     def list_formats(self, info_dict):
+        if not info_dict.get('formats') and not info_dict.get('url'):
+            self.to_screen('%s has no formats' % info_dict['id'])
+            return
+        self.to_screen('[info] Available formats for %s:' % info_dict['id'])
+
         formats = info_dict.get('formats', [info_dict])
         new_format = self.params.get('listformats_table', True) is not False
         if new_format:
@@ -3375,7 +3377,7 @@ class YoutubeDL(object):
                     delim,
                     format_field(f, 'filesize', ' \t%s', func=format_bytes) + format_field(f, 'filesize_approx', '~\t%s', func=format_bytes),
                     format_field(f, 'tbr', '\t%dk'),
-                    shorten_protocol_name(f.get('protocol', '').replace('native', 'n')),
+                    shorten_protocol_name(f.get('protocol', '')),
                     delim,
                     format_field(f, 'vcodec', default='unknown').replace(
                         'none',
@@ -3411,8 +3413,6 @@ class YoutubeDL(object):
                 if f.get('preference') is None or f['preference'] >= -1000]
             header_line = ['format code', 'extension', 'resolution', 'note']
 
-        self.to_screen(
-            '[info] Available formats for %s:' % info_dict['id'])
         self.to_stdout(render_table(
             header_line, table,
             extra_gap=(0 if new_format else 1),

yt_dlp/__init__.py

@@ -18,6 +18,7 @@ from .options import (
 )
 from .compat import (
     compat_getpass,
+    compat_os_name,
     compat_shlex_quote,
     workaround_optparse_bug9161,
 )
@@ -95,7 +96,8 @@ def _real_main(argv=None):
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
-                write_string('Reading URLs from stdin:\n')
+                write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
+                    'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
                 batchfd = sys.stdin
             else:
                 batchfd = io.open(
@@ -518,7 +520,7 @@ def _real_main(argv=None):
             if len(dur) == 2 and all(t is not None for t in dur):
                 remove_ranges.append(tuple(dur))
                 continue
-            parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form ?start-end')
+            parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
         try:
             remove_chapters_patterns.append(re.compile(regex))
         except re.error as err:

yt_dlp/downloader/common.py

@@ -397,6 +397,7 @@ class FileDownloader(object):
                     'status': 'finished',
                     'total_bytes': os.path.getsize(encodeFilename(filename)),
                 }, info_dict)
+                self._finish_multiline_status()
                 return True, False
 
         if subtitle is False:

yt_dlp/extractor/cbc.py

@@ -340,7 +340,7 @@ class CBCGemIE(InfoExtractor):
                 yield {
                     **base_format,
                     'format_id': join_nonempty('sec', height),
-                    'url': re.sub(r'(QualityLevels\()\d+(\))', fr'\<1>{bitrate}\2', base_url),
+                    'url': re.sub(r'(QualityLevels\()\d+(\))', fr'\1{bitrate}\2', base_url),
                     'width': int_or_none(video_quality.attrib.get('MaxWidth')),
                     'tbr': bitrate / 1000.0,
                     'height': height,

yt_dlp/extractor/common.py

@@ -616,7 +616,7 @@ class InfoExtractor(object):
             kwargs = {
                 'video_id': e.video_id or self.get_temp_id(url),
                 'ie': self.IE_NAME,
-                'tb': e.traceback,
+                'tb': e.traceback or sys.exc_info()[2],
                 'expected': e.expected,
                 'cause': e.cause
             }
@@ -1574,7 +1574,7 @@ class InfoExtractor(object):
             'vcodec': {'type': 'ordered', 'regex': True,
                        'order': ['av0?1', 'vp0?9.2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']},
             'acodec': {'type': 'ordered', 'regex': True,
-                       'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']},
+                       'order': ['[af]lac', 'wav|aiff', 'opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']},
             'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range',
                     'order': ['dv', '(hdr)?12', r'(hdr)?10\+', '(hdr)?10', 'hlg', '', 'sdr', None]},
             'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol',

yt_dlp/extractor/fancode.py

@@ -41,7 +41,7 @@ class FancodeVodIE(InfoExtractor):
     _ACCESS_TOKEN = None
     _NETRC_MACHINE = 'fancode'
 
-    _LOGIN_HINT = 'Use "--user refresh --password <refresh_token>" to login using a refresh token'
+    _LOGIN_HINT = 'Use "--username refresh --password <refresh_token>" to login using a refresh token'
 
     headers = {
         'content-type': 'application/json',

yt_dlp/extractor/pornhub.py

@@ -258,8 +258,7 @@ class PornHubIE(PornHubBaseIE):
             webpage)
 
     def _extract_count(self, pattern, webpage, name):
-        return str_to_int(self._search_regex(
-            pattern, webpage, '%s count' % name, fatal=False))
+        return str_to_int(self._search_regex(pattern, webpage, '%s count' % name, default=None))
 
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)

yt_dlp/extractor/roosterteeth.py

@@ -99,7 +99,7 @@ class RoosterTeethIE(RoosterTeethBaseIE):
             'series': 'Million Dollars, But...',
             'episode': 'Million Dollars, But... The Game Announcement',
         },
-        'skip_download': 'm3u8',
+        'params': {'skip_download': True},
     }, {
         'url': 'https://roosterteeth.com/watch/rwby-bonus-25',
         'info_dict': {
@@ -112,7 +112,7 @@ class RoosterTeethIE(RoosterTeethBaseIE):
             'thumbnail': r're:^https?://.*\.(png|jpe?g)$',
             'ext': 'mp4',
         },
-        'skip_download': 'm3u8',
+        'params': {'skip_download': True},
     }, {
         'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
         'only_matching': True,

yt_dlp/extractor/soundcloud.py

@@ -130,7 +130,7 @@ class SoundcloudBaseIE(InfoExtractor):
         elif username is not None:
             self.report_warning(
                 'Login using username and password is not currently supported. '
-                'Use "--user oauth --password <oauth_token>" to login using an oauth token')
+                'Use "--username oauth --password <oauth_token>" to login using an oauth token')
 
         r'''
         def genDevId():

yt_dlp/extractor/voicy.py

@@ -6,9 +6,10 @@ from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     smuggle_url,
+    str_or_none,
     traverse_obj,
-    unsmuggle_url,
     unified_strdate,
+    unsmuggle_url,
 )
 
 import itertools
@@ -25,9 +26,9 @@ class VoicyBaseIE(InfoExtractor):
             'id': voice_id,
             'title': compat_str(value.get('PlaylistName')),
             'uploader': value.get('SpeakerName'),
-            'uploader_id': compat_str(value.get('SpeakerId')),
+            'uploader_id': str_or_none(value.get('SpeakerId')),
             'channel': value.get('ChannelName'),
-            'channel_id': compat_str(value.get('ChannelId')),
+            'channel_id': str_or_none(value.get('ChannelId')),
             'upload_date': upload_date,
         }
 

yt_dlp/options.py

@@ -668,7 +668,7 @@ def parseOpts(overrideArguments=None):
     downloader.add_option(
         '-N', '--concurrent-fragments',
         dest='concurrent_fragment_downloads', metavar='N', default=1, type=int,
-        help='Number of fragments of a dash/hlsnative video that should be download concurrently (default is %default)')
+        help='Number of fragments of a dash/hlsnative video that should be downloaded concurrently (default is %default)')
     downloader.add_option(
         '-r', '--limit-rate', '--rate-limit',
         dest='ratelimit', metavar='RATE',

yt_dlp/postprocessor/metadataparser.py

@@ -99,7 +99,7 @@ class MetadataParserPP(PostProcessor):
 class MetadataFromFieldPP(MetadataParserPP):
     @classmethod
     def to_action(cls, f):
-        match = re.match(r'(?P<in>.*?)(?<!\\):(?P<out>.+)$', f)
+        match = re.match(r'(?s)(?P<in>.*?)(?<!\\):(?P<out>.+)$', f)
         if match is None:
             raise ValueError(f'it should be FROM:TO, not {f!r}')
         return (

yt_dlp/update.py

@@ -257,7 +257,7 @@ def update_self(to_screen, verbose, opener):
 
     write_string(
         'DeprecationWarning: "yt_dlp.update.update_self" is deprecated and may be removed in a future version. '
-        'Use "yt_dlp.update.run_update(ydl)" instead')
+        'Use "yt_dlp.update.run_update(ydl)" instead\n')
 
     class FakeYDL():
         _opener = opener

yt_dlp/utils.py

@@ -1862,7 +1862,6 @@ def _windows_write_string(s, out):
     False if it has yet to be written out."""
     # Adapted from http://stackoverflow.com/a/3259271/35070
 
-    import ctypes
     import ctypes.wintypes
 
     WIN_OUTPUT_IDS = {
@@ -3193,30 +3192,29 @@ def parse_codecs(codecs_str):
         if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2',
                      'h263', 'h264', 'mp4v', 'hvc1', 'av1', 'theora', 'dvh1', 'dvhe'):
             if not vcodec:
-                vcodec = '.'.join(parts[:4]) if codec in ('vp9', 'av1') else full_codec
+                vcodec = '.'.join(parts[:4]) if codec in ('vp9', 'av1', 'hvc1') else full_codec
                 if codec in ('dvh1', 'dvhe'):
                     hdr = 'DV'
                 elif codec == 'av1' and len(parts) > 3 and parts[3] == '10':
                     hdr = 'HDR10'
                 elif full_codec.replace('0', '').startswith('vp9.2'):
                     hdr = 'HDR10'
-        elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
+        elif codec in ('flac', 'mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
             if not acodec:
                 acodec = full_codec
         else:
             write_string('WARNING: Unknown codec %s\n' % full_codec, sys.stderr)
-    if not vcodec and not acodec:
-        if len(split_codecs) == 2:
-            return {
-                'vcodec': split_codecs[0],
-                'acodec': split_codecs[1],
-            }
-    else:
+    if vcodec or acodec:
         return {
             'vcodec': vcodec or 'none',
             'acodec': acodec or 'none',
             'dynamic_range': hdr,
         }
+    elif len(split_codecs) == 2:
+        return {
+            'vcodec': split_codecs[0],
+            'acodec': split_codecs[1],
+        }
     return {}