yt_dlp/__init__.py

   1 #!/usr/bin/env python3
   2 f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp'  # noqa: F541
   3
   4 __license__ = 'Public Domain'
   5
   6 import itertools
   7 import optparse
   8 import os
   9 import re
  10 import sys
  11
  12 from .compat import compat_getpass, compat_shlex_quote
  13 from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
  14 from .downloader import FileDownloader
  15 from .extractor import list_extractor_classes
  16 from .extractor.adobepass import MSO_INFO
  17 from .extractor.common import InfoExtractor
  18 from .options import parseOpts
  19 from .postprocessor import (
  20     FFmpegExtractAudioPP,
  21     FFmpegSubtitlesConvertorPP,
  22     FFmpegThumbnailsConvertorPP,
  23     FFmpegVideoConvertorPP,
  24     FFmpegVideoRemuxerPP,
  25     MetadataFromFieldPP,
  26     MetadataParserPP,
  27 )
  28 from .update import run_update
  29 from .utils import (
  30     NO_DEFAULT,
  31     POSTPROCESS_WHEN,
  32     DateRange,
  33     DownloadCancelled,
  34     DownloadError,
  35     GeoUtils,
  36     PlaylistEntries,
  37     SameFileError,
  38     decodeOption,
  39     download_range_func,
  40     expand_path,
  41     float_or_none,
  42     int_or_none,
  43     match_filter_func,
  44     parse_duration,
  45     preferredencoding,
  46     read_batch_urls,
  47     read_stdin,
  48     render_table,
  49     setproctitle,
  50     std_headers,
  51     traverse_obj,
  52     variadic,
  53     write_string,
  54 )
  55 from .YoutubeDL import YoutubeDL
  56
  57
  58 def _exit(status=0, *args):
  59     for msg in args:
  60         sys.stderr.write(msg)
  61     raise SystemExit(status)
  62
  63
  64 def get_urls(urls, batchfile, verbose):
  65     # Batch file verification
  66     batch_urls = []
  67     if batchfile is not None:
  68         try:
  69             batch_urls = read_batch_urls(
  70                 read_stdin('URLs') if batchfile == '-'
  71                 else open(expand_path(batchfile), encoding='utf-8', errors='ignore'))
  72             if verbose:
  73                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  74         except OSError:
  75             _exit(f'ERROR: batch file {batchfile} could not be read')
  76     _enc = preferredencoding()
  77     return [
  78         url.strip().decode(_enc, 'ignore') if isinstance(url, bytes) else url.strip()
  79         for url in batch_urls + urls]
  80
  81
  82 def print_extractor_information(opts, urls):
  83     # Importing GenericIE is currently slow since it imports other extractors
  84     # TODO: Move this back to module level after generalization of embed detection
  85     from .extractor.generic import GenericIE
  86
  87     out = ''
  88     if opts.list_extractors:
  89         urls = dict.fromkeys(urls, False)
  90         for ie in list_extractor_classes(opts.age_limit):
  91             out += ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n'
  92             if ie == GenericIE:
  93                 matched_urls = [url for url, matched in urls.items() if not matched]
  94             else:
  95                 matched_urls = tuple(filter(ie.suitable, urls.keys()))
  96                 urls.update(dict.fromkeys(matched_urls, True))
  97             out += ''.join(f'  {url}\n' for url in matched_urls)
  98     elif opts.list_extractor_descriptions:
  99         _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 100         out = '\n'.join(
 101             ie.description(markdown=False, search_examples=_SEARCHES)
 102             for ie in list_extractor_classes(opts.age_limit) if ie.working() and ie.IE_DESC is not False)
 103     elif opts.ap_list_mso:
 104         out = 'Supported TV Providers:\n%s\n' % render_table(
 105             ['mso', 'mso name'],
 106             [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()])
 107     else:
 108         return False
 109     write_string(out, out=sys.stdout)
 110     return True
 111
 112
 113 def set_compat_opts(opts):
 114     def _unused_compat_opt(name):
 115         if name not in opts.compat_opts:
 116             return False
 117         opts.compat_opts.discard(name)
 118         opts.compat_opts.update(['*%s' % name])
 119         return True
 120
 121     def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
 122         attr = getattr(opts, opt_name)
 123         if compat_name in opts.compat_opts:
 124             if attr is None:
 125                 setattr(opts, opt_name, not default)
 126                 return True
 127             else:
 128                 if remove_compat:
 129                     _unused_compat_opt(compat_name)
 130                 return False
 131         elif attr is None:
 132             setattr(opts, opt_name, default)
 133         return None
 134
 135     set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
 136     set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
 137     set_default_compat('no-clean-infojson', 'clean_infojson')
 138     if 'no-attach-info-json' in opts.compat_opts:
 139         if opts.embed_infojson:
 140             _unused_compat_opt('no-attach-info-json')
 141         else:
 142             opts.embed_infojson = False
 143     if 'format-sort' in opts.compat_opts:
 144         opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
 145     _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
 146     _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
 147     if _video_multistreams_set is False and _audio_multistreams_set is False:
 148         _unused_compat_opt('multistreams')
 149     if 'filename' in opts.compat_opts:
 150         if opts.outtmpl.get('default') is None:
 151             opts.outtmpl.update({'default': '%(title)s-%(id)s.%(ext)s'})
 152         else:
 153             _unused_compat_opt('filename')
 154
 155
 156 def validate_options(opts):
 157     def validate(cndn, name, value=None, msg=None):
 158         if cndn:
 159             return True
 160         raise ValueError((msg or 'invalid {name} "{value}" given').format(name=name, value=value))
 161
 162     def validate_in(name, value, items, msg=None):
 163         return validate(value is None or value in items, name, value, msg)
 164
 165     def validate_regex(name, value, regex):
 166         return validate(value is None or re.match(regex, value), name, value)
 167
 168     def validate_positive(name, value, strict=False):
 169         return validate(value is None or value > 0 or (not strict and value == 0),
 170                         name, value, '{name} "{value}" must be positive' + ('' if strict else ' or 0'))
 171
 172     def validate_minmax(min_val, max_val, min_name, max_name=None):
 173         if max_val is None or min_val is None or max_val >= min_val:
 174             return
 175         if not max_name:
 176             min_name, max_name = f'min {min_name}', f'max {min_name}'
 177         raise ValueError(f'{max_name} "{max_val}" must be must be greater than or equal to {min_name} "{min_val}"')
 178
 179     # Usernames and passwords
 180     validate(not opts.usenetrc or (opts.username is None and opts.password is None),
 181              '.netrc', msg='using {name} conflicts with giving username/password')
 182     validate(opts.password is None or opts.username is not None, 'account username', msg='{name} missing')
 183     validate(opts.ap_password is None or opts.ap_username is not None,
 184              'TV Provider account username', msg='{name} missing')
 185     validate_in('TV Provider', opts.ap_mso, MSO_INFO,
 186                 'Unsupported {name} "{value}", use --ap-list-mso to get a list of supported TV Providers')
 187
 188     # Numbers
 189     validate_positive('autonumber start', opts.autonumber_start)
 190     validate_positive('autonumber size', opts.autonumber_size, True)
 191     validate_positive('concurrent fragments', opts.concurrent_fragment_downloads, True)
 192     validate_positive('playlist start', opts.playliststart, True)
 193     if opts.playlistend != -1:
 194         validate_minmax(opts.playliststart, opts.playlistend, 'playlist start', 'playlist end')
 195
 196     # Time ranges
 197     validate_positive('subtitles sleep interval', opts.sleep_interval_subtitles)
 198     validate_positive('requests sleep interval', opts.sleep_interval_requests)
 199     validate_positive('sleep interval', opts.sleep_interval)
 200     validate_positive('max sleep interval', opts.max_sleep_interval)
 201     if opts.sleep_interval is None:
 202         validate(
 203             opts.max_sleep_interval is None, 'min sleep interval',
 204             msg='{name} must be specified; use --min-sleep-interval')
 205     elif opts.max_sleep_interval is None:
 206         opts.max_sleep_interval = opts.sleep_interval
 207     else:
 208         validate_minmax(opts.sleep_interval, opts.max_sleep_interval, 'sleep interval')
 209
 210     if opts.wait_for_video is not None:
 211         min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
 212         validate(min_wait is not None and not (max_wait is None and '-' in opts.wait_for_video),
 213                  'time range to wait for video', opts.wait_for_video)
 214         validate_minmax(min_wait, max_wait, 'time range to wait for video')
 215         opts.wait_for_video = (min_wait, max_wait)
 216
 217     # Format sort
 218     for f in opts.format_sort:
 219         validate_regex('format sorting', f, InfoExtractor.FormatSort.regex)
 220
 221     # Postprocessor formats
 222     validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE)
 223     validate_in('subtitle format', opts.convertsubtitles, FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS)
 224     validate_regex('thumbnail format', opts.convertthumbnails, FFmpegThumbnailsConvertorPP.FORMAT_RE)
 225     validate_regex('recode video format', opts.recodevideo, FFmpegVideoConvertorPP.FORMAT_RE)
 226     validate_regex('remux video format', opts.remuxvideo, FFmpegVideoRemuxerPP.FORMAT_RE)
 227     if opts.audioquality:
 228         opts.audioquality = opts.audioquality.strip('k').strip('K')
 229         # int_or_none prevents inf, nan
 230         validate_positive('audio quality', int_or_none(float_or_none(opts.audioquality), default=0))
 231
 232     # Retries
 233     def parse_retries(name, value):
 234         if value is None:
 235             return None
 236         elif value in ('inf', 'infinite'):
 237             return float('inf')
 238         try:
 239             return int(value)
 240         except (TypeError, ValueError):
 241             validate(False, f'{name} retry count', value)
 242
 243     opts.retries = parse_retries('download', opts.retries)
 244     opts.fragment_retries = parse_retries('fragment', opts.fragment_retries)
 245     opts.extractor_retries = parse_retries('extractor', opts.extractor_retries)
 246     opts.file_access_retries = parse_retries('file access', opts.file_access_retries)
 247
 248     # Retry sleep function
 249     def parse_sleep_func(expr):
 250         NUMBER_RE = r'\d+(?:\.\d+)?'
 251         op, start, limit, step, *_ = tuple(re.fullmatch(
 252             rf'(?:(linear|exp)=)?({NUMBER_RE})(?::({NUMBER_RE})?)?(?::({NUMBER_RE}))?',
 253             expr.strip()).groups()) + (None, None)
 254
 255         if op == 'exp':
 256             return lambda n: min(float(start) * (float(step or 2) ** n), float(limit or 'inf'))
 257         else:
 258             default_step = start if op or limit else 0
 259             return lambda n: min(float(start) + float(step or default_step) * n, float(limit or 'inf'))
 260
 261     for key, expr in opts.retry_sleep.items():
 262         if not expr:
 263             del opts.retry_sleep[key]
 264             continue
 265         try:
 266             opts.retry_sleep[key] = parse_sleep_func(expr)
 267         except AttributeError:
 268             raise ValueError(f'invalid {key} retry sleep expression {expr!r}')
 269
 270     # Bytes
 271     def parse_bytes(name, value):
 272         if value is None:
 273             return None
 274         numeric_limit = FileDownloader.parse_bytes(value)
 275         validate(numeric_limit is not None, 'rate limit', value)
 276         return numeric_limit
 277
 278     opts.ratelimit = parse_bytes('rate limit', opts.ratelimit)
 279     opts.throttledratelimit = parse_bytes('throttled rate limit', opts.throttledratelimit)
 280     opts.min_filesize = parse_bytes('min filesize', opts.min_filesize)
 281     opts.max_filesize = parse_bytes('max filesize', opts.max_filesize)
 282     opts.buffersize = parse_bytes('buffer size', opts.buffersize)
 283     opts.http_chunk_size = parse_bytes('http chunk size', opts.http_chunk_size)
 284
 285     # Output templates
 286     def validate_outtmpl(tmpl, msg):
 287         err = YoutubeDL.validate_outtmpl(tmpl)
 288         if err:
 289             raise ValueError(f'invalid {msg} "{tmpl}": {err}')
 290
 291     for k, tmpl in opts.outtmpl.items():
 292         validate_outtmpl(tmpl, f'{k} output template')
 293     for type_, tmpl_list in opts.forceprint.items():
 294         for tmpl in tmpl_list:
 295             validate_outtmpl(tmpl, f'{type_} print template')
 296     for type_, tmpl_list in opts.print_to_file.items():
 297         for tmpl, file in tmpl_list:
 298             validate_outtmpl(tmpl, f'{type_} print to file template')
 299             validate_outtmpl(file, f'{type_} print to file filename')
 300     validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
 301     for k, tmpl in opts.progress_template.items():
 302         k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
 303         validate_outtmpl(tmpl, f'{k} template')
 304
 305     outtmpl_default = opts.outtmpl.get('default')
 306     if outtmpl_default == '':
 307         opts.skip_download = None
 308         del opts.outtmpl['default']
 309     if outtmpl_default and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
 310         raise ValueError(
 311             'Cannot download a video and extract audio into the same file! '
 312             f'Use "{outtmpl_default}.%(ext)s" instead of "{outtmpl_default}" as the output template')
 313
 314     def parse_chapters(name, value):
 315         chapters, ranges = [], []
 316         for regex in value or []:
 317             if regex.startswith('*'):
 318                 for range in regex[1:].split(','):
 319                     dur = tuple(map(parse_duration, range.strip().split('-')))
 320                     if len(dur) == 2 and all(t is not None for t in dur):
 321                         ranges.append(dur)
 322                     else:
 323                         raise ValueError(f'invalid {name} time range "{regex}". Must be of the form *start-end')
 324                 continue
 325             try:
 326                 chapters.append(re.compile(regex))
 327             except re.error as err:
 328                 raise ValueError(f'invalid {name} regex "{regex}" - {err}')
 329         return chapters, ranges
 330
 331     opts.remove_chapters, opts.remove_ranges = parse_chapters('--remove-chapters', opts.remove_chapters)
 332     opts.download_ranges = download_range_func(*parse_chapters('--download-sections', opts.download_ranges))
 333
 334     # Cookies from browser
 335     if opts.cookiesfrombrowser:
 336         mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
 337         if mobj is None:
 338             raise ValueError(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
 339         browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
 340         browser_name = browser_name.lower()
 341         if browser_name not in SUPPORTED_BROWSERS:
 342             raise ValueError(f'unsupported browser specified for cookies: "{browser_name}". '
 343                              f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
 344         if keyring is not None:
 345             keyring = keyring.upper()
 346             if keyring not in SUPPORTED_KEYRINGS:
 347                 raise ValueError(f'unsupported keyring specified for cookies: "{keyring}". '
 348                                  f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
 349         opts.cookiesfrombrowser = (browser_name, profile, keyring)
 350
 351     # MetadataParser
 352     def metadataparser_actions(f):
 353         if isinstance(f, str):
 354             cmd = '--parse-metadata %s' % compat_shlex_quote(f)
 355             try:
 356                 actions = [MetadataFromFieldPP.to_action(f)]
 357             except Exception as err:
 358                 raise ValueError(f'{cmd} is invalid; {err}')
 359         else:
 360             cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
 361             actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
 362
 363         for action in actions:
 364             try:
 365                 MetadataParserPP.validate_action(*action)
 366             except Exception as err:
 367                 raise ValueError(f'{cmd} is invalid; {err}')
 368             yield action
 369
 370     parse_metadata = opts.parse_metadata or []
 371     if opts.metafromtitle is not None:
 372         parse_metadata.append('title:%s' % opts.metafromtitle)
 373     opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, parse_metadata)))
 374
 375     # Other options
 376     if opts.playlist_items is not None:
 377         try:
 378             tuple(PlaylistEntries.parse_playlist_items(opts.playlist_items))
 379         except Exception as err:
 380             raise ValueError(f'Invalid playlist-items {opts.playlist_items!r}: {err}')
 381
 382     geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
 383     if geo_bypass_code is not None:
 384         try:
 385             GeoUtils.random_ipv4(geo_bypass_code)
 386         except Exception:
 387             raise ValueError('unsupported geo-bypass country or ip-block')
 388
 389     opts.match_filter = match_filter_func(opts.match_filter)
 390
 391     if opts.download_archive is not None:
 392         opts.download_archive = expand_path(opts.download_archive)
 393
 394     if opts.user_agent is not None:
 395         opts.headers.setdefault('User-Agent', opts.user_agent)
 396     if opts.referer is not None:
 397         opts.headers.setdefault('Referer', opts.referer)
 398
 399     if opts.no_sponsorblock:
 400         opts.sponsorblock_mark = opts.sponsorblock_remove = set()
 401
 402     warnings, deprecation_warnings = [], []
 403
 404     # Common mistake: -f best
 405     if opts.format == 'best':
 406         warnings.append('.\n         '.join((
 407             '"-f best" selects the best pre-merged format which is often not the best option',
 408             'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
 409             'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
 410
 411     # --(postprocessor/downloader)-args without name
 412     def report_args_compat(name, value, key1, key2=None):
 413         if key1 in value and key2 not in value:
 414             warnings.append(f'{name} arguments given without specifying name. The arguments will be given to all {name}s')
 415             return True
 416         return False
 417
 418     report_args_compat('external downloader', opts.external_downloader_args, 'default')
 419     if report_args_compat('post-processor', opts.postprocessor_args, 'default-compat', 'default'):
 420         opts.postprocessor_args['default'] = opts.postprocessor_args.pop('default-compat')
 421         opts.postprocessor_args.setdefault('sponskrub', [])
 422
 423     def report_conflict(arg1, opt1, arg2='--allow-unplayable-formats', opt2='allow_unplayable_formats',
 424                         val1=NO_DEFAULT, val2=NO_DEFAULT, default=False):
 425         if val2 is NO_DEFAULT:
 426             val2 = getattr(opts, opt2)
 427         if not val2:
 428             return
 429
 430         if val1 is NO_DEFAULT:
 431             val1 = getattr(opts, opt1)
 432         if val1:
 433             warnings.append(f'{arg1} is ignored since {arg2} was given')
 434         setattr(opts, opt1, default)
 435
 436     # Conflicting options
 437     report_conflict('--playlist-reverse', 'playlist_reverse', '--playlist-random', 'playlist_random')
 438     report_conflict('--playlist-reverse', 'playlist_reverse', '--lazy-playlist', 'lazy_playlist')
 439     report_conflict('--playlist-random', 'playlist_random', '--lazy-playlist', 'lazy_playlist')
 440     report_conflict('--dateafter', 'dateafter', '--date', 'date', default=None)
 441     report_conflict('--datebefore', 'datebefore', '--date', 'date', default=None)
 442     report_conflict('--exec-before-download', 'exec_before_dl_cmd',
 443                     '"--exec before_dl:"', 'exec_cmd', val2=opts.exec_cmd.get('before_dl'))
 444     report_conflict('--id', 'useid', '--output', 'outtmpl', val2=opts.outtmpl.get('default'))
 445     report_conflict('--remux-video', 'remuxvideo', '--recode-video', 'recodevideo')
 446     report_conflict('--sponskrub', 'sponskrub', '--remove-chapters', 'remove_chapters')
 447     report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-mark', 'sponsorblock_mark')
 448     report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-remove', 'sponsorblock_remove')
 449     report_conflict('--sponskrub-cut', 'sponskrub_cut', '--split-chapter', 'split_chapters',
 450                     val1=opts.sponskrub and opts.sponskrub_cut)
 451
 452     # Conflicts with --allow-unplayable-formats
 453     report_conflict('--add-metadata', 'addmetadata')
 454     report_conflict('--embed-chapters', 'addchapters')
 455     report_conflict('--embed-info-json', 'embed_infojson')
 456     report_conflict('--embed-subs', 'embedsubtitles')
 457     report_conflict('--embed-thumbnail', 'embedthumbnail')
 458     report_conflict('--extract-audio', 'extractaudio')
 459     report_conflict('--fixup', 'fixup', val1=opts.fixup not in (None, 'never', 'ignore'), default='never')
 460     report_conflict('--recode-video', 'recodevideo')
 461     report_conflict('--remove-chapters', 'remove_chapters', default=[])
 462     report_conflict('--remux-video', 'remuxvideo')
 463     report_conflict('--sponskrub', 'sponskrub')
 464     report_conflict('--sponsorblock-remove', 'sponsorblock_remove', default=set())
 465     report_conflict('--xattrs', 'xattrs')
 466
 467     # Fully deprecated options
 468     def report_deprecation(val, old, new=None):
 469         if not val:
 470             return
 471         deprecation_warnings.append(
 472             f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
 473             else f'{old} is deprecated and may not work as expected')
 474
 475     report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
 476     report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
 477     # report_deprecation(opts.include_ads, '--include-ads')  # We may re-implement this in future
 478     # report_deprecation(opts.call_home, '--call-home')  # We may re-implement this in future
 479     # report_deprecation(opts.writeannotations, '--write-annotations')  # It's just that no website has it
 480
 481     # Dependent options
 482     opts.date = DateRange.day(opts.date) if opts.date else DateRange(opts.dateafter, opts.datebefore)
 483
 484     if opts.exec_before_dl_cmd:
 485         opts.exec_cmd['before_dl'] = opts.exec_before_dl_cmd
 486
 487     if opts.useid:  # --id is not deprecated in youtube-dl
 488         opts.outtmpl['default'] = '%(id)s.%(ext)s'
 489
 490     if opts.overwrites:  # --force-overwrites implies --no-continue
 491         opts.continue_dl = False
 492
 493     if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
 494         # Add chapters when adding metadata or marking sponsors
 495         opts.addchapters = True
 496
 497     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 498         # Do not unnecessarily download audio
 499         opts.format = 'bestaudio/best'
 500
 501     if opts.getcomments and opts.writeinfojson is None:
 502         # If JSON is not printed anywhere, but comments are requested, save it to file
 503         if not opts.dumpjson or opts.print_json or opts.dump_single_json:
 504             opts.writeinfojson = True
 505
 506     if opts.allsubtitles and not (opts.embedsubtitles or opts.writeautomaticsub):
 507         # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 508         opts.writesubtitles = True
 509
 510     if opts.addmetadata and opts.embed_infojson is None:
 511         # If embedding metadata and infojson is present, embed it
 512         opts.embed_infojson = 'if_exists'
 513
 514     # Ask for passwords
 515     if opts.username is not None and opts.password is None:
 516         opts.password = compat_getpass('Type account password and press [Return]: ')
 517     if opts.ap_username is not None and opts.ap_password is None:
 518         opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
 519
 520     return warnings, deprecation_warnings
 521
 522
 523 def get_postprocessors(opts):
 524     yield from opts.add_postprocessors
 525
 526     if opts.parse_metadata:
 527         yield {
 528             'key': 'MetadataParser',
 529             'actions': opts.parse_metadata,
 530             'when': 'pre_process'
 531         }
 532     sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
 533     if sponsorblock_query:
 534         yield {
 535             'key': 'SponsorBlock',
 536             'categories': sponsorblock_query,
 537             'api': opts.sponsorblock_api,
 538             'when': 'after_filter'
 539         }
 540     if opts.convertsubtitles:
 541         yield {
 542             'key': 'FFmpegSubtitlesConvertor',
 543             'format': opts.convertsubtitles,
 544             'when': 'before_dl'
 545         }
 546     if opts.convertthumbnails:
 547         yield {
 548             'key': 'FFmpegThumbnailsConvertor',
 549             'format': opts.convertthumbnails,
 550             'when': 'before_dl'
 551         }
 552     if opts.extractaudio:
 553         yield {
 554             'key': 'FFmpegExtractAudio',
 555             'preferredcodec': opts.audioformat,
 556             'preferredquality': opts.audioquality,
 557             'nopostoverwrites': opts.nopostoverwrites,
 558         }
 559     if opts.remuxvideo:
 560         yield {
 561             'key': 'FFmpegVideoRemuxer',
 562             'preferedformat': opts.remuxvideo,
 563         }
 564     if opts.recodevideo:
 565         yield {
 566             'key': 'FFmpegVideoConvertor',
 567             'preferedformat': opts.recodevideo,
 568         }
 569     # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
 570     if opts.embedsubtitles:
 571         keep_subs = 'no-keep-subs' not in opts.compat_opts
 572         yield {
 573             'key': 'FFmpegEmbedSubtitle',
 574             # already_have_subtitle = True prevents the file from being deleted after embedding
 575             'already_have_subtitle': opts.writesubtitles and keep_subs
 576         }
 577         if not opts.writeautomaticsub and keep_subs:
 578             opts.writesubtitles = True
 579
 580     # ModifyChapters must run before FFmpegMetadataPP
 581     if opts.remove_chapters or sponsorblock_query:
 582         yield {
 583             'key': 'ModifyChapters',
 584             'remove_chapters_patterns': opts.remove_chapters,
 585             'remove_sponsor_segments': opts.sponsorblock_remove,
 586             'remove_ranges': opts.remove_ranges,
 587             'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
 588             'force_keyframes': opts.force_keyframes_at_cuts
 589         }
 590     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 591     # FFmpegExtractAudioPP as containers before conversion may not support
 592     # metadata (3gp, webm, etc.)
 593     # By default ffmpeg preserves metadata applicable for both
 594     # source and target containers. From this point the container won't change,
 595     # so metadata can be added here.
 596     if opts.addmetadata or opts.addchapters or opts.embed_infojson:
 597         yield {
 598             'key': 'FFmpegMetadata',
 599             'add_chapters': opts.addchapters,
 600             'add_metadata': opts.addmetadata,
 601             'add_infojson': opts.embed_infojson,
 602         }
 603     # Deprecated
 604     # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
 605     # but must be below EmbedSubtitle and FFmpegMetadata
 606     # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
 607     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
 608     if opts.sponskrub is not False:
 609         yield {
 610             'key': 'SponSkrub',
 611             'path': opts.sponskrub_path,
 612             'args': opts.sponskrub_args,
 613             'cut': opts.sponskrub_cut,
 614             'force': opts.sponskrub_force,
 615             'ignoreerror': opts.sponskrub is None,
 616             '_from_cli': True,
 617         }
 618     if opts.embedthumbnail:
 619         yield {
 620             'key': 'EmbedThumbnail',
 621             # already_have_thumbnail = True prevents the file from being deleted after embedding
 622             'already_have_thumbnail': opts.writethumbnail
 623         }
 624         if not opts.writethumbnail:
 625             opts.writethumbnail = True
 626             opts.outtmpl['pl_thumbnail'] = ''
 627     if opts.split_chapters:
 628         yield {
 629             'key': 'FFmpegSplitChapters',
 630             'force_keyframes': opts.force_keyframes_at_cuts,
 631         }
 632     # XAttrMetadataPP should be run after post-processors that may change file contents
 633     if opts.xattrs:
 634         yield {'key': 'XAttrMetadata'}
 635     if opts.concat_playlist != 'never':
 636         yield {
 637             'key': 'FFmpegConcat',
 638             'only_multi_video': opts.concat_playlist != 'always',
 639             'when': 'playlist',
 640         }
 641     # Exec must be the last PP of each category
 642     for when, exec_cmd in opts.exec_cmd.items():
 643         yield {
 644             'key': 'Exec',
 645             'exec_cmd': exec_cmd,
 646             'when': when,
 647         }
 648
 649
 650 def parse_options(argv=None):
 651     """ @returns (parser, opts, urls, ydl_opts) """
 652     parser, opts, urls = parseOpts(argv)
 653     urls = get_urls(urls, opts.batchfile, opts.verbose)
 654
 655     set_compat_opts(opts)
 656     try:
 657         warnings, deprecation_warnings = validate_options(opts)
 658     except ValueError as err:
 659         parser.error(f'{err}\n')
 660
 661     postprocessors = list(get_postprocessors(opts))
 662
 663     print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[2:])
 664     any_getting = any(getattr(opts, k) for k in (
 665         'dumpjson', 'dump_single_json', 'getdescription', 'getduration', 'getfilename',
 666         'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
 667     ))
 668
 669     final_ext = (
 670         opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
 671         else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
 672         else opts.audioformat if (opts.extractaudio and opts.audioformat in FFmpegExtractAudioPP.SUPPORTED_EXTS)
 673         else None)
 674
 675     return parser, opts, urls, {
 676         'usenetrc': opts.usenetrc,
 677         'netrc_location': opts.netrc_location,
 678         'username': opts.username,
 679         'password': opts.password,
 680         'twofactor': opts.twofactor,
 681         'videopassword': opts.videopassword,
 682         'ap_mso': opts.ap_mso,
 683         'ap_username': opts.ap_username,
 684         'ap_password': opts.ap_password,
 685         'client_certificate': opts.client_certificate,
 686         'client_certificate_key': opts.client_certificate_key,
 687         'client_certificate_password': opts.client_certificate_password,
 688         'quiet': opts.quiet or any_getting or opts.print_json or bool(opts.forceprint),
 689         'no_warnings': opts.no_warnings,
 690         'forceurl': opts.geturl,
 691         'forcetitle': opts.gettitle,
 692         'forceid': opts.getid,
 693         'forcethumbnail': opts.getthumbnail,
 694         'forcedescription': opts.getdescription,
 695         'forceduration': opts.getduration,
 696         'forcefilename': opts.getfilename,
 697         'forceformat': opts.getformat,
 698         'forceprint': opts.forceprint,
 699         'print_to_file': opts.print_to_file,
 700         'forcejson': opts.dumpjson or opts.print_json,
 701         'dump_single_json': opts.dump_single_json,
 702         'force_write_download_archive': opts.force_write_download_archive,
 703         'simulate': (print_only or any_getting or None) if opts.simulate is None else opts.simulate,
 704         'skip_download': opts.skip_download,
 705         'format': opts.format,
 706         'allow_unplayable_formats': opts.allow_unplayable_formats,
 707         'ignore_no_formats_error': opts.ignore_no_formats_error,
 708         'format_sort': opts.format_sort,
 709         'format_sort_force': opts.format_sort_force,
 710         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 711         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 712         'check_formats': opts.check_formats,
 713         'listformats': opts.listformats,
 714         'listformats_table': opts.listformats_table,
 715         'outtmpl': opts.outtmpl,
 716         'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
 717         'paths': opts.paths,
 718         'autonumber_size': opts.autonumber_size,
 719         'autonumber_start': opts.autonumber_start,
 720         'restrictfilenames': opts.restrictfilenames,
 721         'windowsfilenames': opts.windowsfilenames,
 722         'ignoreerrors': opts.ignoreerrors,
 723         'force_generic_extractor': opts.force_generic_extractor,
 724         'ratelimit': opts.ratelimit,
 725         'throttledratelimit': opts.throttledratelimit,
 726         'overwrites': opts.overwrites,
 727         'retries': opts.retries,
 728         'file_access_retries': opts.file_access_retries,
 729         'fragment_retries': opts.fragment_retries,
 730         'extractor_retries': opts.extractor_retries,
 731         'retry_sleep_functions': opts.retry_sleep,
 732         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 733         'keep_fragments': opts.keep_fragments,
 734         'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
 735         'buffersize': opts.buffersize,
 736         'noresizebuffer': opts.noresizebuffer,
 737         'http_chunk_size': opts.http_chunk_size,
 738         'continuedl': opts.continue_dl,
 739         'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
 740         'progress_with_newline': opts.progress_with_newline,
 741         'progress_template': opts.progress_template,
 742         'playliststart': opts.playliststart,
 743         'playlistend': opts.playlistend,
 744         'playlistreverse': opts.playlist_reverse,
 745         'playlistrandom': opts.playlist_random,
 746         'lazy_playlist': opts.lazy_playlist,
 747         'noplaylist': opts.noplaylist,
 748         'logtostderr': opts.outtmpl.get('default') == '-',
 749         'consoletitle': opts.consoletitle,
 750         'nopart': opts.nopart,
 751         'updatetime': opts.updatetime,
 752         'writedescription': opts.writedescription,
 753         'writeannotations': opts.writeannotations,
 754         'writeinfojson': opts.writeinfojson,
 755         'allow_playlist_files': opts.allow_playlist_files,
 756         'clean_infojson': opts.clean_infojson,
 757         'getcomments': opts.getcomments,
 758         'writethumbnail': opts.writethumbnail is True,
 759         'write_all_thumbnails': opts.writethumbnail == 'all',
 760         'writelink': opts.writelink,
 761         'writeurllink': opts.writeurllink,
 762         'writewebloclink': opts.writewebloclink,
 763         'writedesktoplink': opts.writedesktoplink,
 764         'writesubtitles': opts.writesubtitles,
 765         'writeautomaticsub': opts.writeautomaticsub,
 766         'allsubtitles': opts.allsubtitles,
 767         'listsubtitles': opts.listsubtitles,
 768         'subtitlesformat': opts.subtitlesformat,
 769         'subtitleslangs': opts.subtitleslangs,
 770         'matchtitle': decodeOption(opts.matchtitle),
 771         'rejecttitle': decodeOption(opts.rejecttitle),
 772         'max_downloads': opts.max_downloads,
 773         'prefer_free_formats': opts.prefer_free_formats,
 774         'trim_file_name': opts.trim_file_name,
 775         'verbose': opts.verbose,
 776         'dump_intermediate_pages': opts.dump_intermediate_pages,
 777         'write_pages': opts.write_pages,
 778         'load_pages': opts.load_pages,
 779         'test': opts.test,
 780         'keepvideo': opts.keepvideo,
 781         'min_filesize': opts.min_filesize,
 782         'max_filesize': opts.max_filesize,
 783         'min_views': opts.min_views,
 784         'max_views': opts.max_views,
 785         'daterange': opts.date,
 786         'cachedir': opts.cachedir,
 787         'youtube_print_sig_code': opts.youtube_print_sig_code,
 788         'age_limit': opts.age_limit,
 789         'download_archive': opts.download_archive,
 790         'break_on_existing': opts.break_on_existing,
 791         'break_on_reject': opts.break_on_reject,
 792         'break_per_url': opts.break_per_url,
 793         'skip_playlist_after_errors': opts.skip_playlist_after_errors,
 794         'cookiefile': opts.cookiefile,
 795         'cookiesfrombrowser': opts.cookiesfrombrowser,
 796         'legacyserverconnect': opts.legacy_server_connect,
 797         'nocheckcertificate': opts.no_check_certificate,
 798         'prefer_insecure': opts.prefer_insecure,
 799         'http_headers': opts.headers,
 800         'proxy': opts.proxy,
 801         'socket_timeout': opts.socket_timeout,
 802         'bidi_workaround': opts.bidi_workaround,
 803         'debug_printtraffic': opts.debug_printtraffic,
 804         'prefer_ffmpeg': opts.prefer_ffmpeg,
 805         'include_ads': opts.include_ads,
 806         'default_search': opts.default_search,
 807         'dynamic_mpd': opts.dynamic_mpd,
 808         'extractor_args': opts.extractor_args,
 809         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 810         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 811         'encoding': opts.encoding,
 812         'extract_flat': opts.extract_flat,
 813         'live_from_start': opts.live_from_start,
 814         'wait_for_video': opts.wait_for_video,
 815         'mark_watched': opts.mark_watched,
 816         'merge_output_format': opts.merge_output_format,
 817         'final_ext': final_ext,
 818         'postprocessors': postprocessors,
 819         'fixup': opts.fixup,
 820         'source_address': opts.source_address,
 821         'call_home': opts.call_home,
 822         'sleep_interval_requests': opts.sleep_interval_requests,
 823         'sleep_interval': opts.sleep_interval,
 824         'max_sleep_interval': opts.max_sleep_interval,
 825         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 826         'external_downloader': opts.external_downloader,
 827         'download_ranges': opts.download_ranges,
 828         'force_keyframes_at_cuts': opts.force_keyframes_at_cuts,
 829         'list_thumbnails': opts.list_thumbnails,
 830         'playlist_items': opts.playlist_items,
 831         'xattr_set_filesize': opts.xattr_set_filesize,
 832         'match_filter': opts.match_filter,
 833         'no_color': opts.no_color,
 834         'ffmpeg_location': opts.ffmpeg_location,
 835         'hls_prefer_native': opts.hls_prefer_native,
 836         'hls_use_mpegts': opts.hls_use_mpegts,
 837         'hls_split_discontinuity': opts.hls_split_discontinuity,
 838         'external_downloader_args': opts.external_downloader_args,
 839         'postprocessor_args': opts.postprocessor_args,
 840         'cn_verification_proxy': opts.cn_verification_proxy,
 841         'geo_verification_proxy': opts.geo_verification_proxy,
 842         'geo_bypass': opts.geo_bypass,
 843         'geo_bypass_country': opts.geo_bypass_country,
 844         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 845         '_warnings': warnings,
 846         '_deprecation_warnings': deprecation_warnings,
 847         'compat_opts': opts.compat_opts,
 848     }
 849
 850
 851 def _real_main(argv=None):
 852     setproctitle('yt-dlp')
 853
 854     parser, opts, all_urls, ydl_opts = parse_options(argv)
 855
 856     # Dump user agent
 857     if opts.dump_user_agent:
 858         ua = traverse_obj(opts.headers, 'User-Agent', casesense=False, default=std_headers['User-Agent'])
 859         write_string(f'{ua}\n', out=sys.stdout)
 860         return
 861
 862     if print_extractor_information(opts, all_urls):
 863         return
 864
 865     with YoutubeDL(ydl_opts) as ydl:
 866         actual_use = all_urls or opts.load_info_filename
 867
 868         if opts.rm_cachedir:
 869             ydl.cache.remove()
 870
 871         if opts.update_self and run_update(ydl) and actual_use:
 872             # If updater returns True, exit. Required for windows
 873             return 100, 'ERROR: The program must exit for the update to complete'
 874
 875         if not actual_use:
 876             if opts.update_self or opts.rm_cachedir:
 877                 return ydl._download_retcode
 878
 879             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 880             parser.error(
 881                 'You must provide at least one URL.\n'
 882                 'Type yt-dlp --help to see a list of all options.')
 883
 884         parser.destroy()
 885         try:
 886             if opts.load_info_filename is not None:
 887                 return ydl.download_with_info_file(expand_path(opts.load_info_filename))
 888             else:
 889                 return ydl.download(all_urls)
 890         except DownloadCancelled:
 891             ydl.to_screen('Aborting remaining downloads')
 892             return 101
 893
 894
 895 def main(argv=None):
 896     try:
 897         _exit(*variadic(_real_main(argv)))
 898     except DownloadError:
 899         _exit(1)
 900     except SameFileError as e:
 901         _exit(f'ERROR: {e}')
 902     except KeyboardInterrupt:
 903         _exit('\nERROR: Interrupted by user')
 904     except BrokenPipeError as e:
 905         # https://docs.python.org/3/library/signal.html#note-on-sigpipe
 906         devnull = os.open(os.devnull, os.O_WRONLY)
 907         os.dup2(devnull, sys.stdout.fileno())
 908         _exit(f'\nERROR: {e}')
 909     except optparse.OptParseError as e:
 910         _exit(2, f'\n{e}')
 911
 912
 913 from .extractor import gen_extractors, list_extractors
 914
 915 __all__ = [
 916     'main',
 917     'YoutubeDL',
 918     'parse_options',
 919     'gen_extractors',
 920     'list_extractors',
 921 ]