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