yt_dlp/__init__.py

   1 f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp'  # noqa: F541
   2
   3 __license__ = 'Public Domain'
   4
   5 import getpass
   6 import itertools
   7 import optparse
   8 import os
   9 import re
  10 import sys
  11
  12 from .compat import compat_shlex_quote
  13 from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
  14 from .downloader import FileDownloader
  15 from .downloader.external import get_external_downloader
  16 from .extractor import list_extractor_classes
  17 from .extractor.adobepass import MSO_INFO
  18 from .extractor.common import InfoExtractor
  19 from .options import parseOpts
  20 from .postprocessor import (
  21     FFmpegExtractAudioPP,
  22     FFmpegSubtitlesConvertorPP,
  23     FFmpegThumbnailsConvertorPP,
  24     FFmpegVideoConvertorPP,
  25     FFmpegVideoRemuxerPP,
  26     MetadataFromFieldPP,
  27     MetadataParserPP,
  28 )
  29 from .update import Updater
  30 from .utils import (
  31     NO_DEFAULT,
  32     POSTPROCESS_WHEN,
  33     DateRange,
  34     DownloadCancelled,
  35     DownloadError,
  36     GeoUtils,
  37     PlaylistEntries,
  38     SameFileError,
  39     decodeOption,
  40     download_range_func,
  41     expand_path,
  42     float_or_none,
  43     format_field,
  44     int_or_none,
  45     match_filter_func,
  46     parse_duration,
  47     preferredencoding,
  48     read_batch_urls,
  49     read_stdin,
  50     render_table,
  51     setproctitle,
  52     std_headers,
  53     traverse_obj,
  54     variadic,
  55     write_string,
  56 )
  57 from .YoutubeDL import YoutubeDL
  58
  59
  60 def _exit(status=0, *args):
  61     for msg in args:
  62         sys.stderr.write(msg)
  63     raise SystemExit(status)
  64
  65
  66 def get_urls(urls, batchfile, verbose):
  67     # Batch file verification
  68     batch_urls = []
  69     if batchfile is not None:
  70         try:
  71             batch_urls = read_batch_urls(
  72                 read_stdin('URLs') if batchfile == '-'
  73                 else open(expand_path(batchfile), encoding='utf-8', errors='ignore'))
  74             if verbose:
  75                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  76         except OSError:
  77             _exit(f'ERROR: batch file {batchfile} could not be read')
  78     _enc = preferredencoding()
  79     return [
  80         url.strip().decode(_enc, 'ignore') if isinstance(url, bytes) else url.strip()
  81         for url in batch_urls + urls]
  82
  83
  84 def print_extractor_information(opts, urls):
  85     # Importing GenericIE is currently slow since it imports other extractors
  86     # TODO: Move this back to module level after generalization of embed detection
  87     from .extractor.generic import GenericIE
  88
  89     out = ''
  90     if opts.list_extractors:
  91         urls = dict.fromkeys(urls, False)
  92         for ie in list_extractor_classes(opts.age_limit):
  93             out += ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n'
  94             if ie == GenericIE:
  95                 matched_urls = [url for url, matched in urls.items() if not matched]
  96             else:
  97                 matched_urls = tuple(filter(ie.suitable, urls.keys()))
  98                 urls.update(dict.fromkeys(matched_urls, True))
  99             out += ''.join(f'  {url}\n' for url in matched_urls)
 100     elif opts.list_extractor_descriptions:
 101         _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 102         out = '\n'.join(
 103             ie.description(markdown=False, search_examples=_SEARCHES)
 104             for ie in list_extractor_classes(opts.age_limit) if ie.working() and ie.IE_DESC is not False)
 105     elif opts.ap_list_mso:
 106         out = 'Supported TV Providers:\n%s\n' % render_table(
 107             ['mso', 'mso name'],
 108             [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()])
 109     else:
 110         return False
 111     write_string(out, out=sys.stdout)
 112     return True
 113
 114
 115 def set_compat_opts(opts):
 116     def _unused_compat_opt(name):
 117         if name not in opts.compat_opts:
 118             return False
 119         opts.compat_opts.discard(name)
 120         opts.compat_opts.update(['*%s' % name])
 121         return True
 122
 123     def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
 124         attr = getattr(opts, opt_name)
 125         if compat_name in opts.compat_opts:
 126             if attr is None:
 127                 setattr(opts, opt_name, not default)
 128                 return True
 129             else:
 130                 if remove_compat:
 131                     _unused_compat_opt(compat_name)
 132                 return False
 133         elif attr is None:
 134             setattr(opts, opt_name, default)
 135         return None
 136
 137     set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
 138     set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
 139     set_default_compat('no-clean-infojson', 'clean_infojson')
 140     if 'no-attach-info-json' in opts.compat_opts:
 141         if opts.embed_infojson:
 142             _unused_compat_opt('no-attach-info-json')
 143         else:
 144             opts.embed_infojson = False
 145     if 'format-sort' in opts.compat_opts:
 146         opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
 147     _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
 148     _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
 149     if _video_multistreams_set is False and _audio_multistreams_set is False:
 150         _unused_compat_opt('multistreams')
 151     if 'filename' in opts.compat_opts:
 152         if opts.outtmpl.get('default') is None:
 153             opts.outtmpl.update({'default': '%(title)s-%(id)s.%(ext)s'})
 154         else:
 155             _unused_compat_opt('filename')
 156
 157
 158 def validate_options(opts):
 159     def validate(cndn, name, value=None, msg=None):
 160         if cndn:
 161             return True
 162         raise ValueError((msg or 'invalid {name} "{value}" given').format(name=name, value=value))
 163
 164     def validate_in(name, value, items, msg=None):
 165         return validate(value is None or value in items, name, value, msg)
 166
 167     def validate_regex(name, value, regex):
 168         return validate(value is None or re.match(regex, value), name, value)
 169
 170     def validate_positive(name, value, strict=False):
 171         return validate(value is None or value > 0 or (not strict and value == 0),
 172                         name, value, '{name} "{value}" must be positive' + ('' if strict else ' or 0'))
 173
 174     def validate_minmax(min_val, max_val, min_name, max_name=None):
 175         if max_val is None or min_val is None or max_val >= min_val:
 176             return
 177         if not max_name:
 178             min_name, max_name = f'min {min_name}', f'max {min_name}'
 179         raise ValueError(f'{max_name} "{max_val}" must be must be greater than or equal to {min_name} "{min_val}"')
 180
 181     # Usernames and passwords
 182     validate(not opts.usenetrc or (opts.username is None and opts.password is None),
 183              '.netrc', msg='using {name} conflicts with giving username/password')
 184     validate(opts.password is None or opts.username is not None, 'account username', msg='{name} missing')
 185     validate(opts.ap_password is None or opts.ap_username is not None,
 186              'TV Provider account username', msg='{name} missing')
 187     validate_in('TV Provider', opts.ap_mso, MSO_INFO,
 188                 'Unsupported {name} "{value}", use --ap-list-mso to get a list of supported TV Providers')
 189
 190     # Numbers
 191     validate_positive('autonumber start', opts.autonumber_start)
 192     validate_positive('autonumber size', opts.autonumber_size, True)
 193     validate_positive('concurrent fragments', opts.concurrent_fragment_downloads, True)
 194     validate_positive('playlist start', opts.playliststart, True)
 195     if opts.playlistend != -1:
 196         validate_minmax(opts.playliststart, opts.playlistend, 'playlist start', 'playlist end')
 197
 198     # Time ranges
 199     validate_positive('subtitles sleep interval', opts.sleep_interval_subtitles)
 200     validate_positive('requests sleep interval', opts.sleep_interval_requests)
 201     validate_positive('sleep interval', opts.sleep_interval)
 202     validate_positive('max sleep interval', opts.max_sleep_interval)
 203     if opts.sleep_interval is None:
 204         validate(
 205             opts.max_sleep_interval is None, 'min sleep interval',
 206             msg='{name} must be specified; use --min-sleep-interval')
 207     elif opts.max_sleep_interval is None:
 208         opts.max_sleep_interval = opts.sleep_interval
 209     else:
 210         validate_minmax(opts.sleep_interval, opts.max_sleep_interval, 'sleep interval')
 211
 212     if opts.wait_for_video is not None:
 213         min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
 214         validate(min_wait is not None and not (max_wait is None and '-' in opts.wait_for_video),
 215                  'time range to wait for video', opts.wait_for_video)
 216         validate_minmax(min_wait, max_wait, 'time range to wait for video')
 217         opts.wait_for_video = (min_wait, max_wait)
 218
 219     # Format sort
 220     for f in opts.format_sort:
 221         validate_regex('format sorting', f, InfoExtractor.FormatSort.regex)
 222
 223     # Postprocessor formats
 224     validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE)
 225     validate_in('subtitle format', opts.convertsubtitles, FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS)
 226     validate_regex('thumbnail format', opts.convertthumbnails, FFmpegThumbnailsConvertorPP.FORMAT_RE)
 227     validate_regex('recode video format', opts.recodevideo, FFmpegVideoConvertorPP.FORMAT_RE)
 228     validate_regex('remux video format', opts.remuxvideo, FFmpegVideoRemuxerPP.FORMAT_RE)
 229     if opts.audioquality:
 230         opts.audioquality = opts.audioquality.strip('k').strip('K')
 231         # int_or_none prevents inf, nan
 232         validate_positive('audio quality', int_or_none(float_or_none(opts.audioquality), default=0))
 233
 234     # Retries
 235     def parse_retries(name, value):
 236         if value is None:
 237             return None
 238         elif value in ('inf', 'infinite'):
 239             return float('inf')
 240         try:
 241             return int(value)
 242         except (TypeError, ValueError):
 243             validate(False, f'{name} retry count', value)
 244
 245     opts.retries = parse_retries('download', opts.retries)
 246     opts.fragment_retries = parse_retries('fragment', opts.fragment_retries)
 247     opts.extractor_retries = parse_retries('extractor', opts.extractor_retries)
 248     opts.file_access_retries = parse_retries('file access', opts.file_access_retries)
 249
 250     # Retry sleep function
 251     def parse_sleep_func(expr):
 252         NUMBER_RE = r'\d+(?:\.\d+)?'
 253         op, start, limit, step, *_ = tuple(re.fullmatch(
 254             rf'(?:(linear|exp)=)?({NUMBER_RE})(?::({NUMBER_RE})?)?(?::({NUMBER_RE}))?',
 255             expr.strip()).groups()) + (None, None)
 256
 257         if op == 'exp':
 258             return lambda n: min(float(start) * (float(step or 2) ** n), float(limit or 'inf'))
 259         else:
 260             default_step = start if op or limit else 0
 261             return lambda n: min(float(start) + float(step or default_step) * n, float(limit or 'inf'))
 262
 263     for key, expr in opts.retry_sleep.items():
 264         if not expr:
 265             del opts.retry_sleep[key]
 266             continue
 267         try:
 268             opts.retry_sleep[key] = parse_sleep_func(expr)
 269         except AttributeError:
 270             raise ValueError(f'invalid {key} retry sleep expression {expr!r}')
 271
 272     # Bytes
 273     def parse_bytes(name, value):
 274         if value is None:
 275             return None
 276         numeric_limit = FileDownloader.parse_bytes(value)
 277         validate(numeric_limit is not None, 'rate limit', value)
 278         return numeric_limit
 279
 280     opts.ratelimit = parse_bytes('rate limit', opts.ratelimit)
 281     opts.throttledratelimit = parse_bytes('throttled rate limit', opts.throttledratelimit)
 282     opts.min_filesize = parse_bytes('min filesize', opts.min_filesize)
 283     opts.max_filesize = parse_bytes('max filesize', opts.max_filesize)
 284     opts.buffersize = parse_bytes('buffer size', opts.buffersize)
 285     opts.http_chunk_size = parse_bytes('http chunk size', opts.http_chunk_size)
 286
 287     # Output templates
 288     def validate_outtmpl(tmpl, msg):
 289         err = YoutubeDL.validate_outtmpl(tmpl)
 290         if err:
 291             raise ValueError(f'invalid {msg} "{tmpl}": {err}')
 292
 293     for k, tmpl in opts.outtmpl.items():
 294         validate_outtmpl(tmpl, f'{k} output template')
 295     for type_, tmpl_list in opts.forceprint.items():
 296         for tmpl in tmpl_list:
 297             validate_outtmpl(tmpl, f'{type_} print template')
 298     for type_, tmpl_list in opts.print_to_file.items():
 299         for tmpl, file in tmpl_list:
 300             validate_outtmpl(tmpl, f'{type_} print to file template')
 301             validate_outtmpl(file, f'{type_} print to file filename')
 302     validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
 303     for k, tmpl in opts.progress_template.items():
 304         k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
 305         validate_outtmpl(tmpl, f'{k} template')
 306
 307     outtmpl_default = opts.outtmpl.get('default')
 308     if outtmpl_default == '':
 309         opts.skip_download = None
 310         del opts.outtmpl['default']
 311     if outtmpl_default and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
 312         raise ValueError(
 313             'Cannot download a video and extract audio into the same file! '
 314             f'Use "{outtmpl_default}.%(ext)s" instead of "{outtmpl_default}" as the output template')
 315
 316     def parse_chapters(name, value):
 317         chapters, ranges = [], []
 318         for regex in value or []:
 319             if regex.startswith('*'):
 320                 for range in regex[1:].split(','):
 321                     dur = tuple(map(parse_duration, range.strip().split('-')))
 322                     if len(dur) == 2 and all(t is not None for t in dur):
 323                         ranges.append(dur)
 324                     else:
 325                         raise ValueError(f'invalid {name} time range "{regex}". Must be of the form *start-end')
 326                 continue
 327             try:
 328                 chapters.append(re.compile(regex))
 329             except re.error as err:
 330                 raise ValueError(f'invalid {name} regex "{regex}" - {err}')
 331         return chapters, ranges
 332
 333     opts.remove_chapters, opts.remove_ranges = parse_chapters('--remove-chapters', opts.remove_chapters)
 334     opts.download_ranges = download_range_func(*parse_chapters('--download-sections', opts.download_ranges))
 335
 336     # Cookies from browser
 337     if opts.cookiesfrombrowser:
 338         mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
 339         if mobj is None:
 340             raise ValueError(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
 341         browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
 342         browser_name = browser_name.lower()
 343         if browser_name not in SUPPORTED_BROWSERS:
 344             raise ValueError(f'unsupported browser specified for cookies: "{browser_name}". '
 345                              f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
 346         if keyring is not None:
 347             keyring = keyring.upper()
 348             if keyring not in SUPPORTED_KEYRINGS:
 349                 raise ValueError(f'unsupported keyring specified for cookies: "{keyring}". '
 350                                  f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
 351         opts.cookiesfrombrowser = (browser_name, profile, keyring)
 352
 353     # MetadataParser
 354     def metadataparser_actions(f):
 355         if isinstance(f, str):
 356             cmd = '--parse-metadata %s' % compat_shlex_quote(f)
 357             try:
 358                 actions = [MetadataFromFieldPP.to_action(f)]
 359             except Exception as err:
 360                 raise ValueError(f'{cmd} is invalid; {err}')
 361         else:
 362             cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
 363             actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
 364
 365         for action in actions:
 366             try:
 367                 MetadataParserPP.validate_action(*action)
 368             except Exception as err:
 369                 raise ValueError(f'{cmd} is invalid; {err}')
 370             yield action
 371
 372     parse_metadata = opts.parse_metadata or []
 373     if opts.metafromtitle is not None:
 374         parse_metadata.append('title:%s' % opts.metafromtitle)
 375     opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, parse_metadata)))
 376
 377     # Other options
 378     if opts.playlist_items is not None:
 379         try:
 380             tuple(PlaylistEntries.parse_playlist_items(opts.playlist_items))
 381         except Exception as err:
 382             raise ValueError(f'Invalid playlist-items {opts.playlist_items!r}: {err}')
 383
 384     geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
 385     if geo_bypass_code is not None:
 386         try:
 387             GeoUtils.random_ipv4(geo_bypass_code)
 388         except Exception:
 389             raise ValueError('unsupported geo-bypass country or ip-block')
 390
 391     opts.match_filter = match_filter_func(opts.match_filter)
 392
 393     if opts.download_archive is not None:
 394         opts.download_archive = expand_path(opts.download_archive)
 395
 396     if opts.user_agent is not None:
 397         opts.headers.setdefault('User-Agent', opts.user_agent)
 398     if opts.referer is not None:
 399         opts.headers.setdefault('Referer', opts.referer)
 400
 401     if opts.no_sponsorblock:
 402         opts.sponsorblock_mark = opts.sponsorblock_remove = set()
 403
 404     default_downloader = None
 405     for proto, path in opts.external_downloader.items():
 406         if path == 'native':
 407             continue
 408         ed = get_external_downloader(path)
 409         if ed is None:
 410             raise ValueError(
 411                 f'No such {format_field(proto, None, "%s ", ignore="default")}external downloader "{path}"')
 412         elif ed and proto == 'default':
 413             default_downloader = ed.get_basename()
 414
 415     warnings, deprecation_warnings = [], []
 416
 417     # Common mistake: -f best
 418     if opts.format == 'best':
 419         warnings.append('.\n         '.join((
 420             '"-f best" selects the best pre-merged format which is often not the best option',
 421             'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
 422             'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
 423
 424     # --(postprocessor/downloader)-args without name
 425     def report_args_compat(name, value, key1, key2=None, where=None):
 426         if key1 in value and key2 not in value:
 427             warnings.append(f'{name.title()} arguments given without specifying name. '
 428                             f'The arguments will be given to {where or f"all {name}s"}')
 429             return True
 430         return False
 431
 432     if report_args_compat('external downloader', opts.external_downloader_args,
 433                           'default', where=default_downloader) and default_downloader:
 434         # Compat with youtube-dl's behavior. See https://github.com/ytdl-org/youtube-dl/commit/49c5293014bc11ec8c009856cd63cffa6296c1e1
 435         opts.external_downloader_args.setdefault(default_downloader, opts.external_downloader_args.pop('default'))
 436
 437     if report_args_compat('post-processor', opts.postprocessor_args, 'default-compat', 'default'):
 438         opts.postprocessor_args['default'] = opts.postprocessor_args.pop('default-compat')
 439         opts.postprocessor_args.setdefault('sponskrub', [])
 440
 441     def report_conflict(arg1, opt1, arg2='--allow-unplayable-formats', opt2='allow_unplayable_formats',
 442                         val1=NO_DEFAULT, val2=NO_DEFAULT, default=False):
 443         if val2 is NO_DEFAULT:
 444             val2 = getattr(opts, opt2)
 445         if not val2:
 446             return
 447
 448         if val1 is NO_DEFAULT:
 449             val1 = getattr(opts, opt1)
 450         if val1:
 451             warnings.append(f'{arg1} is ignored since {arg2} was given')
 452         setattr(opts, opt1, default)
 453
 454     # Conflicting options
 455     report_conflict('--playlist-reverse', 'playlist_reverse', '--playlist-random', 'playlist_random')
 456     report_conflict('--playlist-reverse', 'playlist_reverse', '--lazy-playlist', 'lazy_playlist')
 457     report_conflict('--playlist-random', 'playlist_random', '--lazy-playlist', 'lazy_playlist')
 458     report_conflict('--dateafter', 'dateafter', '--date', 'date', default=None)
 459     report_conflict('--datebefore', 'datebefore', '--date', 'date', default=None)
 460     report_conflict('--exec-before-download', 'exec_before_dl_cmd',
 461                     '"--exec before_dl:"', 'exec_cmd', val2=opts.exec_cmd.get('before_dl'))
 462     report_conflict('--id', 'useid', '--output', 'outtmpl', val2=opts.outtmpl.get('default'))
 463     report_conflict('--remux-video', 'remuxvideo', '--recode-video', 'recodevideo')
 464     report_conflict('--sponskrub', 'sponskrub', '--remove-chapters', 'remove_chapters')
 465     report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-mark', 'sponsorblock_mark')
 466     report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-remove', 'sponsorblock_remove')
 467     report_conflict('--sponskrub-cut', 'sponskrub_cut', '--split-chapter', 'split_chapters',
 468                     val1=opts.sponskrub and opts.sponskrub_cut)
 469
 470     # Conflicts with --allow-unplayable-formats
 471     report_conflict('--add-metadata', 'addmetadata')
 472     report_conflict('--embed-chapters', 'addchapters')
 473     report_conflict('--embed-info-json', 'embed_infojson')
 474     report_conflict('--embed-subs', 'embedsubtitles')
 475     report_conflict('--embed-thumbnail', 'embedthumbnail')
 476     report_conflict('--extract-audio', 'extractaudio')
 477     report_conflict('--fixup', 'fixup', val1=opts.fixup not in (None, 'never', 'ignore'), default='never')
 478     report_conflict('--recode-video', 'recodevideo')
 479     report_conflict('--remove-chapters', 'remove_chapters', default=[])
 480     report_conflict('--remux-video', 'remuxvideo')
 481     report_conflict('--sponskrub', 'sponskrub')
 482     report_conflict('--sponsorblock-remove', 'sponsorblock_remove', default=set())
 483     report_conflict('--xattrs', 'xattrs')
 484
 485     # Fully deprecated options
 486     def report_deprecation(val, old, new=None):
 487         if not val:
 488             return
 489         deprecation_warnings.append(
 490             f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
 491             else f'{old} is deprecated and may not work as expected')
 492
 493     report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
 494     report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
 495     # report_deprecation(opts.include_ads, '--include-ads')  # We may re-implement this in future
 496     # report_deprecation(opts.call_home, '--call-home')  # We may re-implement this in future
 497     # report_deprecation(opts.writeannotations, '--write-annotations')  # It's just that no website has it
 498
 499     # Dependent options
 500     opts.date = DateRange.day(opts.date) if opts.date else DateRange(opts.dateafter, opts.datebefore)
 501
 502     if opts.exec_before_dl_cmd:
 503         opts.exec_cmd['before_dl'] = opts.exec_before_dl_cmd
 504
 505     if opts.useid:  # --id is not deprecated in youtube-dl
 506         opts.outtmpl['default'] = '%(id)s.%(ext)s'
 507
 508     if opts.overwrites:  # --force-overwrites implies --no-continue
 509         opts.continue_dl = False
 510
 511     if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
 512         # Add chapters when adding metadata or marking sponsors
 513         opts.addchapters = True
 514
 515     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 516         # Do not unnecessarily download audio
 517         opts.format = 'bestaudio/best'
 518
 519     if opts.getcomments and opts.writeinfojson is None:
 520         # If JSON is not printed anywhere, but comments are requested, save it to file
 521         if not opts.dumpjson or opts.print_json or opts.dump_single_json:
 522             opts.writeinfojson = True
 523
 524     if opts.allsubtitles and not (opts.embedsubtitles or opts.writeautomaticsub):
 525         # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 526         opts.writesubtitles = True
 527
 528     if opts.addmetadata and opts.embed_infojson is None:
 529         # If embedding metadata and infojson is present, embed it
 530         opts.embed_infojson = 'if_exists'
 531
 532     # Ask for passwords
 533     if opts.username is not None and opts.password is None:
 534         opts.password = getpass.getpass('Type account password and press [Return]: ')
 535     if opts.ap_username is not None and opts.ap_password is None:
 536         opts.ap_password = getpass.getpass('Type TV provider account password and press [Return]: ')
 537
 538     return warnings, deprecation_warnings
 539
 540
 541 def get_postprocessors(opts):
 542     yield from opts.add_postprocessors
 543
 544     if opts.parse_metadata:
 545         yield {
 546             'key': 'MetadataParser',
 547             'actions': opts.parse_metadata,
 548             'when': 'pre_process'
 549         }
 550     sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
 551     if sponsorblock_query:
 552         yield {
 553             'key': 'SponsorBlock',
 554             'categories': sponsorblock_query,
 555             'api': opts.sponsorblock_api,
 556             'when': 'after_filter'
 557         }
 558     if opts.convertsubtitles:
 559         yield {
 560             'key': 'FFmpegSubtitlesConvertor',
 561             'format': opts.convertsubtitles,
 562             'when': 'before_dl'
 563         }
 564     if opts.convertthumbnails:
 565         yield {
 566             'key': 'FFmpegThumbnailsConvertor',
 567             'format': opts.convertthumbnails,
 568             'when': 'before_dl'
 569         }
 570     if opts.extractaudio:
 571         yield {
 572             'key': 'FFmpegExtractAudio',
 573             'preferredcodec': opts.audioformat,
 574             'preferredquality': opts.audioquality,
 575             'nopostoverwrites': opts.nopostoverwrites,
 576         }
 577     if opts.remuxvideo:
 578         yield {
 579             'key': 'FFmpegVideoRemuxer',
 580             'preferedformat': opts.remuxvideo,
 581         }
 582     if opts.recodevideo:
 583         yield {
 584             'key': 'FFmpegVideoConvertor',
 585             'preferedformat': opts.recodevideo,
 586         }
 587     # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
 588     if opts.embedsubtitles:
 589         keep_subs = 'no-keep-subs' not in opts.compat_opts
 590         yield {
 591             'key': 'FFmpegEmbedSubtitle',
 592             # already_have_subtitle = True prevents the file from being deleted after embedding
 593             'already_have_subtitle': opts.writesubtitles and keep_subs
 594         }
 595         if not opts.writeautomaticsub and keep_subs:
 596             opts.writesubtitles = True
 597
 598     # ModifyChapters must run before FFmpegMetadataPP
 599     if opts.remove_chapters or sponsorblock_query:
 600         yield {
 601             'key': 'ModifyChapters',
 602             'remove_chapters_patterns': opts.remove_chapters,
 603             'remove_sponsor_segments': opts.sponsorblock_remove,
 604             'remove_ranges': opts.remove_ranges,
 605             'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
 606             'force_keyframes': opts.force_keyframes_at_cuts
 607         }
 608     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 609     # FFmpegExtractAudioPP as containers before conversion may not support
 610     # metadata (3gp, webm, etc.)
 611     # By default ffmpeg preserves metadata applicable for both
 612     # source and target containers. From this point the container won't change,
 613     # so metadata can be added here.
 614     if opts.addmetadata or opts.addchapters or opts.embed_infojson:
 615         yield {
 616             'key': 'FFmpegMetadata',
 617             'add_chapters': opts.addchapters,
 618             'add_metadata': opts.addmetadata,
 619             'add_infojson': opts.embed_infojson,
 620         }
 621     # Deprecated
 622     # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
 623     # but must be below EmbedSubtitle and FFmpegMetadata
 624     # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
 625     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
 626     if opts.sponskrub is not False:
 627         yield {
 628             'key': 'SponSkrub',
 629             'path': opts.sponskrub_path,
 630             'args': opts.sponskrub_args,
 631             'cut': opts.sponskrub_cut,
 632             'force': opts.sponskrub_force,
 633             'ignoreerror': opts.sponskrub is None,
 634             '_from_cli': True,
 635         }
 636     if opts.embedthumbnail:
 637         yield {
 638             'key': 'EmbedThumbnail',
 639             # already_have_thumbnail = True prevents the file from being deleted after embedding
 640             'already_have_thumbnail': opts.writethumbnail
 641         }
 642         if not opts.writethumbnail:
 643             opts.writethumbnail = True
 644             opts.outtmpl['pl_thumbnail'] = ''
 645     if opts.split_chapters:
 646         yield {
 647             'key': 'FFmpegSplitChapters',
 648             'force_keyframes': opts.force_keyframes_at_cuts,
 649         }
 650     # XAttrMetadataPP should be run after post-processors that may change file contents
 651     if opts.xattrs:
 652         yield {'key': 'XAttrMetadata'}
 653     if opts.concat_playlist != 'never':
 654         yield {
 655             'key': 'FFmpegConcat',
 656             'only_multi_video': opts.concat_playlist != 'always',
 657             'when': 'playlist',
 658         }
 659     # Exec must be the last PP of each category
 660     for when, exec_cmd in opts.exec_cmd.items():
 661         yield {
 662             'key': 'Exec',
 663             'exec_cmd': exec_cmd,
 664             'when': when,
 665         }
 666
 667
 668 def parse_options(argv=None):
 669     """ @returns (parser, opts, urls, ydl_opts) """
 670     parser, opts, urls = parseOpts(argv)
 671     urls = get_urls(urls, opts.batchfile, opts.verbose)
 672
 673     set_compat_opts(opts)
 674     try:
 675         warnings, deprecation_warnings = validate_options(opts)
 676     except ValueError as err:
 677         parser.error(f'{err}\n')
 678
 679     postprocessors = list(get_postprocessors(opts))
 680
 681     print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[2:])
 682     any_getting = any(getattr(opts, k) for k in (
 683         'dumpjson', 'dump_single_json', 'getdescription', 'getduration', 'getfilename',
 684         'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
 685     ))
 686
 687     final_ext = (
 688         opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
 689         else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
 690         else opts.audioformat if (opts.extractaudio and opts.audioformat in FFmpegExtractAudioPP.SUPPORTED_EXTS)
 691         else None)
 692
 693     return parser, opts, urls, {
 694         'usenetrc': opts.usenetrc,
 695         'netrc_location': opts.netrc_location,
 696         'username': opts.username,
 697         'password': opts.password,
 698         'twofactor': opts.twofactor,
 699         'videopassword': opts.videopassword,
 700         'ap_mso': opts.ap_mso,
 701         'ap_username': opts.ap_username,
 702         'ap_password': opts.ap_password,
 703         'client_certificate': opts.client_certificate,
 704         'client_certificate_key': opts.client_certificate_key,
 705         'client_certificate_password': opts.client_certificate_password,
 706         'quiet': opts.quiet or any_getting or opts.print_json or bool(opts.forceprint),
 707         'no_warnings': opts.no_warnings,
 708         'forceurl': opts.geturl,
 709         'forcetitle': opts.gettitle,
 710         'forceid': opts.getid,
 711         'forcethumbnail': opts.getthumbnail,
 712         'forcedescription': opts.getdescription,
 713         'forceduration': opts.getduration,
 714         'forcefilename': opts.getfilename,
 715         'forceformat': opts.getformat,
 716         'forceprint': opts.forceprint,
 717         'print_to_file': opts.print_to_file,
 718         'forcejson': opts.dumpjson or opts.print_json,
 719         'dump_single_json': opts.dump_single_json,
 720         'force_write_download_archive': opts.force_write_download_archive,
 721         'simulate': (print_only or any_getting or None) if opts.simulate is None else opts.simulate,
 722         'skip_download': opts.skip_download,
 723         'format': opts.format,
 724         'allow_unplayable_formats': opts.allow_unplayable_formats,
 725         'ignore_no_formats_error': opts.ignore_no_formats_error,
 726         'format_sort': opts.format_sort,
 727         'format_sort_force': opts.format_sort_force,
 728         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 729         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 730         'check_formats': opts.check_formats,
 731         'listformats': opts.listformats,
 732         'listformats_table': opts.listformats_table,
 733         'outtmpl': opts.outtmpl,
 734         'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
 735         'paths': opts.paths,
 736         'autonumber_size': opts.autonumber_size,
 737         'autonumber_start': opts.autonumber_start,
 738         'restrictfilenames': opts.restrictfilenames,
 739         'windowsfilenames': opts.windowsfilenames,
 740         'ignoreerrors': opts.ignoreerrors,
 741         'force_generic_extractor': opts.force_generic_extractor,
 742         'ratelimit': opts.ratelimit,
 743         'throttledratelimit': opts.throttledratelimit,
 744         'overwrites': opts.overwrites,
 745         'retries': opts.retries,
 746         'file_access_retries': opts.file_access_retries,
 747         'fragment_retries': opts.fragment_retries,
 748         'extractor_retries': opts.extractor_retries,
 749         'retry_sleep_functions': opts.retry_sleep,
 750         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 751         'keep_fragments': opts.keep_fragments,
 752         'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
 753         'buffersize': opts.buffersize,
 754         'noresizebuffer': opts.noresizebuffer,
 755         'http_chunk_size': opts.http_chunk_size,
 756         'continuedl': opts.continue_dl,
 757         'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
 758         'progress_with_newline': opts.progress_with_newline,
 759         'progress_template': opts.progress_template,
 760         'playliststart': opts.playliststart,
 761         'playlistend': opts.playlistend,
 762         'playlistreverse': opts.playlist_reverse,
 763         'playlistrandom': opts.playlist_random,
 764         'lazy_playlist': opts.lazy_playlist,
 765         'noplaylist': opts.noplaylist,
 766         'logtostderr': opts.outtmpl.get('default') == '-',
 767         'consoletitle': opts.consoletitle,
 768         'nopart': opts.nopart,
 769         'updatetime': opts.updatetime,
 770         'writedescription': opts.writedescription,
 771         'writeannotations': opts.writeannotations,
 772         'writeinfojson': opts.writeinfojson,
 773         'allow_playlist_files': opts.allow_playlist_files,
 774         'clean_infojson': opts.clean_infojson,
 775         'getcomments': opts.getcomments,
 776         'writethumbnail': opts.writethumbnail is True,
 777         'write_all_thumbnails': opts.writethumbnail == 'all',
 778         'writelink': opts.writelink,
 779         'writeurllink': opts.writeurllink,
 780         'writewebloclink': opts.writewebloclink,
 781         'writedesktoplink': opts.writedesktoplink,
 782         'writesubtitles': opts.writesubtitles,
 783         'writeautomaticsub': opts.writeautomaticsub,
 784         'allsubtitles': opts.allsubtitles,
 785         'listsubtitles': opts.listsubtitles,
 786         'subtitlesformat': opts.subtitlesformat,
 787         'subtitleslangs': opts.subtitleslangs,
 788         'matchtitle': decodeOption(opts.matchtitle),
 789         'rejecttitle': decodeOption(opts.rejecttitle),
 790         'max_downloads': opts.max_downloads,
 791         'prefer_free_formats': opts.prefer_free_formats,
 792         'trim_file_name': opts.trim_file_name,
 793         'verbose': opts.verbose,
 794         'dump_intermediate_pages': opts.dump_intermediate_pages,
 795         'write_pages': opts.write_pages,
 796         'load_pages': opts.load_pages,
 797         'test': opts.test,
 798         'keepvideo': opts.keepvideo,
 799         'min_filesize': opts.min_filesize,
 800         'max_filesize': opts.max_filesize,
 801         'min_views': opts.min_views,
 802         'max_views': opts.max_views,
 803         'daterange': opts.date,
 804         'cachedir': opts.cachedir,
 805         'youtube_print_sig_code': opts.youtube_print_sig_code,
 806         'age_limit': opts.age_limit,
 807         'download_archive': opts.download_archive,
 808         'break_on_existing': opts.break_on_existing,
 809         'break_on_reject': opts.break_on_reject,
 810         'break_per_url': opts.break_per_url,
 811         'skip_playlist_after_errors': opts.skip_playlist_after_errors,
 812         'cookiefile': opts.cookiefile,
 813         'cookiesfrombrowser': opts.cookiesfrombrowser,
 814         'legacyserverconnect': opts.legacy_server_connect,
 815         'nocheckcertificate': opts.no_check_certificate,
 816         'prefer_insecure': opts.prefer_insecure,
 817         'http_headers': opts.headers,
 818         'proxy': opts.proxy,
 819         'socket_timeout': opts.socket_timeout,
 820         'bidi_workaround': opts.bidi_workaround,
 821         'debug_printtraffic': opts.debug_printtraffic,
 822         'prefer_ffmpeg': opts.prefer_ffmpeg,
 823         'include_ads': opts.include_ads,
 824         'default_search': opts.default_search,
 825         'dynamic_mpd': opts.dynamic_mpd,
 826         'extractor_args': opts.extractor_args,
 827         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 828         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 829         'encoding': opts.encoding,
 830         'extract_flat': opts.extract_flat,
 831         'live_from_start': opts.live_from_start,
 832         'wait_for_video': opts.wait_for_video,
 833         'mark_watched': opts.mark_watched,
 834         'merge_output_format': opts.merge_output_format,
 835         'final_ext': final_ext,
 836         'postprocessors': postprocessors,
 837         'fixup': opts.fixup,
 838         'source_address': opts.source_address,
 839         'call_home': opts.call_home,
 840         'sleep_interval_requests': opts.sleep_interval_requests,
 841         'sleep_interval': opts.sleep_interval,
 842         'max_sleep_interval': opts.max_sleep_interval,
 843         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 844         'external_downloader': opts.external_downloader,
 845         'download_ranges': opts.download_ranges,
 846         'force_keyframes_at_cuts': opts.force_keyframes_at_cuts,
 847         'list_thumbnails': opts.list_thumbnails,
 848         'playlist_items': opts.playlist_items,
 849         'xattr_set_filesize': opts.xattr_set_filesize,
 850         'match_filter': opts.match_filter,
 851         'no_color': opts.no_color,
 852         'ffmpeg_location': opts.ffmpeg_location,
 853         'hls_prefer_native': opts.hls_prefer_native,
 854         'hls_use_mpegts': opts.hls_use_mpegts,
 855         'hls_split_discontinuity': opts.hls_split_discontinuity,
 856         'external_downloader_args': opts.external_downloader_args,
 857         'postprocessor_args': opts.postprocessor_args,
 858         'cn_verification_proxy': opts.cn_verification_proxy,
 859         'geo_verification_proxy': opts.geo_verification_proxy,
 860         'geo_bypass': opts.geo_bypass,
 861         'geo_bypass_country': opts.geo_bypass_country,
 862         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 863         '_warnings': warnings,
 864         '_deprecation_warnings': deprecation_warnings,
 865         'compat_opts': opts.compat_opts,
 866     }
 867
 868
 869 def _real_main(argv=None):
 870     setproctitle('yt-dlp')
 871
 872     parser, opts, all_urls, ydl_opts = parse_options(argv)
 873
 874     # Dump user agent
 875     if opts.dump_user_agent:
 876         ua = traverse_obj(opts.headers, 'User-Agent', casesense=False, default=std_headers['User-Agent'])
 877         write_string(f'{ua}\n', out=sys.stdout)
 878         return
 879
 880     if print_extractor_information(opts, all_urls):
 881         return
 882
 883     with YoutubeDL(ydl_opts) as ydl:
 884         pre_process = opts.update_self or opts.rm_cachedir
 885         actual_use = all_urls or opts.load_info_filename
 886
 887         if opts.rm_cachedir:
 888             ydl.cache.remove()
 889
 890         updater = Updater(ydl)
 891         if opts.update_self and updater.update() and actual_use:
 892             if updater.cmd:
 893                 return updater.restart()
 894             # This code is reachable only for zip variant in py < 3.10
 895             # It makes sense to exit here, but the old behavior is to continue
 896             ydl.report_warning('Restart yt-dlp to use the updated version')
 897             # return 100, 'ERROR: The program must exit for the update to complete'
 898
 899         if not actual_use:
 900             if pre_process:
 901                 return ydl._download_retcode
 902
 903             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 904             parser.error(
 905                 'You must provide at least one URL.\n'
 906                 'Type yt-dlp --help to see a list of all options.')
 907
 908         parser.destroy()
 909         try:
 910             if opts.load_info_filename is not None:
 911                 return ydl.download_with_info_file(expand_path(opts.load_info_filename))
 912             else:
 913                 return ydl.download(all_urls)
 914         except DownloadCancelled:
 915             ydl.to_screen('Aborting remaining downloads')
 916             return 101
 917
 918
 919 def main(argv=None):
 920     try:
 921         _exit(*variadic(_real_main(argv)))
 922     except DownloadError:
 923         _exit(1)
 924     except SameFileError as e:
 925         _exit(f'ERROR: {e}')
 926     except KeyboardInterrupt:
 927         _exit('\nERROR: Interrupted by user')
 928     except BrokenPipeError as e:
 929         # https://docs.python.org/3/library/signal.html#note-on-sigpipe
 930         devnull = os.open(os.devnull, os.O_WRONLY)
 931         os.dup2(devnull, sys.stdout.fileno())
 932         _exit(f'\nERROR: {e}')
 933     except optparse.OptParseError as e:
 934         _exit(2, f'\n{e}')
 935
 936
 937 from .extractor import gen_extractors, list_extractors
 938
 939 __all__ = [
 940     'main',
 941     'YoutubeDL',
 942     'parse_options',
 943     'gen_extractors',
 944     'list_extractors',
 945 ]