yt_dlp/__init__.py

   1 #!/usr/bin/env python3
   2 # coding: utf-8
   3
   4 f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp'  # noqa: F541
   5
   6 __license__ = 'Public Domain'
   7
   8 import codecs
   9 import io
  10 import itertools
  11 import os
  12 import random
  13 import re
  14 import sys
  15
  16 from .options import (
  17     parseOpts,
  18 )
  19 from .compat import (
  20     compat_getpass,
  21     compat_shlex_quote,
  22     workaround_optparse_bug9161,
  23 )
  24 from .cookies import SUPPORTED_BROWSERS
  25 from .utils import (
  26     DateRange,
  27     decodeOption,
  28     DownloadCancelled,
  29     DownloadError,
  30     error_to_compat_str,
  31     expand_path,
  32     GeoUtils,
  33     float_or_none,
  34     int_or_none,
  35     match_filter_func,
  36     parse_duration,
  37     preferredencoding,
  38     read_batch_urls,
  39     render_table,
  40     SameFileError,
  41     setproctitle,
  42     std_headers,
  43     write_string,
  44 )
  45 from .update import run_update
  46 from .downloader import (
  47     FileDownloader,
  48 )
  49 from .extractor import gen_extractors, list_extractors
  50 from .extractor.common import InfoExtractor
  51 from .extractor.adobepass import MSO_INFO
  52 from .postprocessor import (
  53     FFmpegExtractAudioPP,
  54     FFmpegSubtitlesConvertorPP,
  55     FFmpegThumbnailsConvertorPP,
  56     FFmpegVideoConvertorPP,
  57     FFmpegVideoRemuxerPP,
  58     MetadataFromFieldPP,
  59     MetadataParserPP,
  60 )
  61 from .YoutubeDL import YoutubeDL
  62
  63
  64 def _real_main(argv=None):
  65     # Compatibility fixes for Windows
  66     if sys.platform == 'win32':
  67         # https://github.com/ytdl-org/youtube-dl/issues/820
  68         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  69
  70     workaround_optparse_bug9161()
  71
  72     setproctitle('yt-dlp')
  73
  74     parser, opts, args = parseOpts(argv)
  75     warnings, deprecation_warnings = [], []
  76
  77     # Set user agent
  78     if opts.user_agent is not None:
  79         std_headers['User-Agent'] = opts.user_agent
  80
  81     # Set referer
  82     if opts.referer is not None:
  83         std_headers['Referer'] = opts.referer
  84
  85     # Custom HTTP headers
  86     std_headers.update(opts.headers)
  87
  88     # Dump user agent
  89     if opts.dump_user_agent:
  90         write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
  91         sys.exit(0)
  92
  93     # Batch file verification
  94     batch_urls = []
  95     if opts.batchfile is not None:
  96         try:
  97             if opts.batchfile == '-':
  98                 write_string('Reading URLs from stdin:\n')
  99                 batchfd = sys.stdin
 100             else:
 101                 batchfd = io.open(
 102                     expand_path(opts.batchfile),
 103                     'r', encoding='utf-8', errors='ignore')
 104             batch_urls = read_batch_urls(batchfd)
 105             if opts.verbose:
 106                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
 107         except IOError:
 108             sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
 109     all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
 110     _enc = preferredencoding()
 111     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 112
 113     if opts.list_extractors:
 114         for ie in list_extractors(opts.age_limit):
 115             write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
 116             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 117             for mu in matchedUrls:
 118                 write_string('  ' + mu + '\n', out=sys.stdout)
 119         sys.exit(0)
 120     if opts.list_extractor_descriptions:
 121         for ie in list_extractors(opts.age_limit):
 122             if not ie.working():
 123                 continue
 124             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
 125             if desc is False:
 126                 continue
 127             if getattr(ie, 'SEARCH_KEY', None) is not None:
 128                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 129                 _COUNTS = ('', '5', '10', 'all')
 130                 desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
 131             write_string(desc + '\n', out=sys.stdout)
 132         sys.exit(0)
 133     if opts.ap_list_mso:
 134         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
 135         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
 136         sys.exit(0)
 137
 138     # Conflicting, missing and erroneous options
 139     if opts.format == 'best':
 140         warnings.append('.\n         '.join(
 141             '"-f best" selects the best pre-merged format which is often not the best option',
 142             'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
 143             'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning'))
 144     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 145         parser.error('using .netrc conflicts with giving username/password')
 146     if opts.password is not None and opts.username is None:
 147         parser.error('account username missing\n')
 148     if opts.ap_password is not None and opts.ap_username is None:
 149         parser.error('TV Provider account username missing\n')
 150     if opts.autonumber_size is not None:
 151         if opts.autonumber_size <= 0:
 152             parser.error('auto number size must be positive')
 153     if opts.autonumber_start is not None:
 154         if opts.autonumber_start < 0:
 155             parser.error('auto number start must be positive or 0')
 156     if opts.username is not None and opts.password is None:
 157         opts.password = compat_getpass('Type account password and press [Return]: ')
 158     if opts.ap_username is not None and opts.ap_password is None:
 159         opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
 160     if opts.ratelimit is not None:
 161         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 162         if numeric_limit is None:
 163             parser.error('invalid rate limit specified')
 164         opts.ratelimit = numeric_limit
 165     if opts.throttledratelimit is not None:
 166         numeric_limit = FileDownloader.parse_bytes(opts.throttledratelimit)
 167         if numeric_limit is None:
 168             parser.error('invalid rate limit specified')
 169         opts.throttledratelimit = numeric_limit
 170     if opts.min_filesize is not None:
 171         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 172         if numeric_limit is None:
 173             parser.error('invalid min_filesize specified')
 174         opts.min_filesize = numeric_limit
 175     if opts.max_filesize is not None:
 176         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 177         if numeric_limit is None:
 178             parser.error('invalid max_filesize specified')
 179         opts.max_filesize = numeric_limit
 180     if opts.sleep_interval is not None:
 181         if opts.sleep_interval < 0:
 182             parser.error('sleep interval must be positive or 0')
 183     if opts.max_sleep_interval is not None:
 184         if opts.max_sleep_interval < 0:
 185             parser.error('max sleep interval must be positive or 0')
 186         if opts.sleep_interval is None:
 187             parser.error('min sleep interval must be specified, use --min-sleep-interval')
 188         if opts.max_sleep_interval < opts.sleep_interval:
 189             parser.error('max sleep interval must be greater than or equal to min sleep interval')
 190     else:
 191         opts.max_sleep_interval = opts.sleep_interval
 192     if opts.sleep_interval_subtitles is not None:
 193         if opts.sleep_interval_subtitles < 0:
 194             parser.error('subtitles sleep interval must be positive or 0')
 195     if opts.sleep_interval_requests is not None:
 196         if opts.sleep_interval_requests < 0:
 197             parser.error('requests sleep interval must be positive or 0')
 198     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
 199         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 200     if opts.overwrites:  # --yes-overwrites implies --no-continue
 201         opts.continue_dl = False
 202     if opts.concurrent_fragment_downloads <= 0:
 203         parser.error('Concurrent fragments must be positive')
 204     if opts.wait_for_video is not None:
 205         min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
 206         if min_wait is None or (max_wait is None and '-' in opts.wait_for_video):
 207             parser.error('Invalid time range to wait')
 208         elif max_wait is not None and max_wait < min_wait:
 209             parser.error('Minimum time range to wait must not be longer than the maximum')
 210         opts.wait_for_video = (min_wait, max_wait)
 211
 212     def parse_retries(retries, name=''):
 213         if retries in ('inf', 'infinite'):
 214             parsed_retries = float('inf')
 215         else:
 216             try:
 217                 parsed_retries = int(retries)
 218             except (TypeError, ValueError):
 219                 parser.error('invalid %sretry count specified' % name)
 220         return parsed_retries
 221     if opts.retries is not None:
 222         opts.retries = parse_retries(opts.retries)
 223     if opts.fragment_retries is not None:
 224         opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
 225     if opts.extractor_retries is not None:
 226         opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
 227     if opts.buffersize is not None:
 228         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 229         if numeric_buffersize is None:
 230             parser.error('invalid buffer size specified')
 231         opts.buffersize = numeric_buffersize
 232     if opts.http_chunk_size is not None:
 233         numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
 234         if not numeric_chunksize:
 235             parser.error('invalid http chunk size specified')
 236         opts.http_chunk_size = numeric_chunksize
 237     if opts.playliststart <= 0:
 238         raise parser.error('Playlist start must be positive')
 239     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 240         raise parser.error('Playlist end must be greater than playlist start')
 241     if opts.extractaudio:
 242         opts.audioformat = opts.audioformat.lower()
 243         if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
 244             parser.error('invalid audio format specified')
 245     if opts.audioquality:
 246         opts.audioquality = opts.audioquality.strip('k').strip('K')
 247         audioquality = int_or_none(float_or_none(opts.audioquality))  # int_or_none prevents inf, nan
 248         if audioquality is None or audioquality < 0:
 249             parser.error('invalid audio quality specified')
 250     if opts.recodevideo is not None:
 251         opts.recodevideo = opts.recodevideo.replace(' ', '')
 252         if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
 253             parser.error('invalid video remux format specified')
 254     if opts.remuxvideo is not None:
 255         opts.remuxvideo = opts.remuxvideo.replace(' ', '')
 256         if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
 257             parser.error('invalid video remux format specified')
 258     if opts.convertsubtitles is not None:
 259         if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
 260             parser.error('invalid subtitle format specified')
 261     if opts.convertthumbnails is not None:
 262         if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
 263             parser.error('invalid thumbnail format specified')
 264     if opts.cookiesfrombrowser is not None:
 265         opts.cookiesfrombrowser = [
 266             part.strip() or None for part in opts.cookiesfrombrowser.split(':', 1)]
 267         if opts.cookiesfrombrowser[0].lower() not in SUPPORTED_BROWSERS:
 268             parser.error('unsupported browser specified for cookies')
 269     geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
 270     if geo_bypass_code is not None:
 271         try:
 272             GeoUtils.random_ipv4(geo_bypass_code)
 273         except Exception:
 274             parser.error('unsupported geo-bypass country or ip-block')
 275
 276     if opts.date is not None:
 277         date = DateRange.day(opts.date)
 278     else:
 279         date = DateRange(opts.dateafter, opts.datebefore)
 280
 281     compat_opts = opts.compat_opts
 282
 283     def report_conflict(arg1, arg2):
 284         warnings.append(f'{arg2} is ignored since {arg1} was given')
 285
 286     def _unused_compat_opt(name):
 287         if name not in compat_opts:
 288             return False
 289         compat_opts.discard(name)
 290         compat_opts.update(['*%s' % name])
 291         return True
 292
 293     def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
 294         attr = getattr(opts, opt_name)
 295         if compat_name in compat_opts:
 296             if attr is None:
 297                 setattr(opts, opt_name, not default)
 298                 return True
 299             else:
 300                 if remove_compat:
 301                     _unused_compat_opt(compat_name)
 302                 return False
 303         elif attr is None:
 304             setattr(opts, opt_name, default)
 305         return None
 306
 307     set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
 308     set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
 309     set_default_compat('no-clean-infojson', 'clean_infojson')
 310     if 'no-attach-info-json' in compat_opts:
 311         if opts.embed_infojson:
 312             _unused_compat_opt('no-attach-info-json')
 313         else:
 314             opts.embed_infojson = False
 315     if 'format-sort' in compat_opts:
 316         opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
 317     _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
 318     _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
 319     if _video_multistreams_set is False and _audio_multistreams_set is False:
 320         _unused_compat_opt('multistreams')
 321     outtmpl_default = opts.outtmpl.get('default')
 322     if opts.useid:
 323         if outtmpl_default is None:
 324             outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
 325         else:
 326             report_conflict('--output', '--id')
 327     if 'filename' in compat_opts:
 328         if outtmpl_default is None:
 329             outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
 330         else:
 331             _unused_compat_opt('filename')
 332
 333     def validate_outtmpl(tmpl, msg):
 334         err = YoutubeDL.validate_outtmpl(tmpl)
 335         if err:
 336             parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
 337
 338     for k, tmpl in opts.outtmpl.items():
 339         validate_outtmpl(tmpl, f'{k} output template')
 340     opts.forceprint = opts.forceprint or []
 341     for tmpl in opts.forceprint or []:
 342         validate_outtmpl(tmpl, 'print template')
 343     validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
 344     for k, tmpl in opts.progress_template.items():
 345         k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
 346         validate_outtmpl(tmpl, f'{k} template')
 347
 348     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 349         opts.format = 'bestaudio/best'
 350
 351     if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
 352         parser.error('Cannot download a video and extract audio into the same'
 353                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 354                      ' template'.format(outtmpl_default))
 355
 356     for f in opts.format_sort:
 357         if re.match(InfoExtractor.FormatSort.regex, f) is None:
 358             parser.error('invalid format sort string "%s" specified' % f)
 359
 360     def metadataparser_actions(f):
 361         if isinstance(f, str):
 362             cmd = '--parse-metadata %s' % compat_shlex_quote(f)
 363             try:
 364                 actions = [MetadataFromFieldPP.to_action(f)]
 365             except Exception as err:
 366                 parser.error(f'{cmd} is invalid; {err}')
 367         else:
 368             cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
 369             actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
 370
 371         for action in actions:
 372             try:
 373                 MetadataParserPP.validate_action(*action)
 374             except Exception as err:
 375                 parser.error(f'{cmd} is invalid; {err}')
 376             yield action
 377
 378     if opts.parse_metadata is None:
 379         opts.parse_metadata = []
 380     if opts.metafromtitle is not None:
 381         opts.parse_metadata.append('title:%s' % opts.metafromtitle)
 382     opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
 383
 384     any_getting = opts.forceprint or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
 385     any_printing = opts.print_json
 386     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 387
 388     # If JSON is not printed anywhere, but comments are requested, save it to file
 389     printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
 390     if opts.getcomments and not printing_json:
 391         opts.writeinfojson = True
 392
 393     if opts.no_sponsorblock:
 394         opts.sponsorblock_mark = set()
 395         opts.sponsorblock_remove = set()
 396     sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
 397
 398     opts.remove_chapters = opts.remove_chapters or []
 399
 400     if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
 401         if opts.sponskrub:
 402             if opts.remove_chapters:
 403                 report_conflict('--remove-chapters', '--sponskrub')
 404             if opts.sponsorblock_mark:
 405                 report_conflict('--sponsorblock-mark', '--sponskrub')
 406             if opts.sponsorblock_remove:
 407                 report_conflict('--sponsorblock-remove', '--sponskrub')
 408         opts.sponskrub = False
 409     if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
 410         report_conflict('--split-chapter', '--sponskrub-cut')
 411         opts.sponskrub_cut = False
 412
 413     if opts.remuxvideo and opts.recodevideo:
 414         report_conflict('--recode-video', '--remux-video')
 415         opts.remuxvideo = False
 416
 417     if opts.allow_unplayable_formats:
 418         def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
 419             val = getattr(opts, opt_name)
 420             if (not allowed and val) or (allowed and not allowed(val)):
 421                 report_conflict('--allow-unplayable-formats', arg)
 422                 setattr(opts, opt_name, default)
 423
 424         report_unplayable_conflict('extractaudio', '--extract-audio')
 425         report_unplayable_conflict('remuxvideo', '--remux-video')
 426         report_unplayable_conflict('recodevideo', '--recode-video')
 427         report_unplayable_conflict('addmetadata', '--embed-metadata')
 428         report_unplayable_conflict('addchapters', '--embed-chapters')
 429         report_unplayable_conflict('embed_infojson', '--embed-info-json')
 430         opts.embed_infojson = False
 431         report_unplayable_conflict('embedsubtitles', '--embed-subs')
 432         report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
 433         report_unplayable_conflict('xattrs', '--xattrs')
 434         report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
 435         opts.fixup = 'never'
 436         report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
 437         report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
 438         report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
 439         opts.sponskrub = False
 440
 441     if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
 442         opts.addchapters = True
 443
 444     # PostProcessors
 445     postprocessors = list(opts.add_postprocessors)
 446     if sponsorblock_query:
 447         postprocessors.append({
 448             'key': 'SponsorBlock',
 449             'categories': sponsorblock_query,
 450             'api': opts.sponsorblock_api,
 451             # Run this immediately after extraction is complete
 452             'when': 'pre_process'
 453         })
 454     if opts.parse_metadata:
 455         postprocessors.append({
 456             'key': 'MetadataParser',
 457             'actions': opts.parse_metadata,
 458             # Run this immediately after extraction is complete
 459             'when': 'pre_process'
 460         })
 461     if opts.convertsubtitles:
 462         postprocessors.append({
 463             'key': 'FFmpegSubtitlesConvertor',
 464             'format': opts.convertsubtitles,
 465             # Run this before the actual video download
 466             'when': 'before_dl'
 467         })
 468     if opts.convertthumbnails:
 469         postprocessors.append({
 470             'key': 'FFmpegThumbnailsConvertor',
 471             'format': opts.convertthumbnails,
 472             # Run this before the actual video download
 473             'when': 'before_dl'
 474         })
 475     # Must be after all other before_dl
 476     if opts.exec_before_dl_cmd:
 477         postprocessors.append({
 478             'key': 'Exec',
 479             'exec_cmd': opts.exec_before_dl_cmd,
 480             'when': 'before_dl'
 481         })
 482     if opts.extractaudio:
 483         postprocessors.append({
 484             'key': 'FFmpegExtractAudio',
 485             'preferredcodec': opts.audioformat,
 486             'preferredquality': opts.audioquality,
 487             'nopostoverwrites': opts.nopostoverwrites,
 488         })
 489     if opts.remuxvideo:
 490         postprocessors.append({
 491             'key': 'FFmpegVideoRemuxer',
 492             'preferedformat': opts.remuxvideo,
 493         })
 494     if opts.recodevideo:
 495         postprocessors.append({
 496             'key': 'FFmpegVideoConvertor',
 497             'preferedformat': opts.recodevideo,
 498         })
 499     # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
 500     if opts.embedsubtitles:
 501         already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
 502         postprocessors.append({
 503             'key': 'FFmpegEmbedSubtitle',
 504             # already_have_subtitle = True prevents the file from being deleted after embedding
 505             'already_have_subtitle': already_have_subtitle
 506         })
 507         if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
 508             opts.writesubtitles = True
 509     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 510     # this was the old behaviour if only --all-sub was given.
 511     if opts.allsubtitles and not opts.writeautomaticsub:
 512         opts.writesubtitles = True
 513     # ModifyChapters must run before FFmpegMetadataPP
 514     remove_chapters_patterns, remove_ranges = [], []
 515     for regex in opts.remove_chapters:
 516         if regex.startswith('*'):
 517             dur = list(map(parse_duration, regex[1:].split('-')))
 518             if len(dur) == 2 and all(t is not None for t in dur):
 519                 remove_ranges.append(tuple(dur))
 520                 continue
 521             parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form ?start-end')
 522         try:
 523             remove_chapters_patterns.append(re.compile(regex))
 524         except re.error as err:
 525             parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
 526     if opts.remove_chapters or sponsorblock_query:
 527         postprocessors.append({
 528             'key': 'ModifyChapters',
 529             'remove_chapters_patterns': remove_chapters_patterns,
 530             'remove_sponsor_segments': opts.sponsorblock_remove,
 531             'remove_ranges': remove_ranges,
 532             'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
 533             'force_keyframes': opts.force_keyframes_at_cuts
 534         })
 535     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 536     # FFmpegExtractAudioPP as containers before conversion may not support
 537     # metadata (3gp, webm, etc.)
 538     # By default ffmpeg preserves metadata applicable for both
 539     # source and target containers. From this point the container won't change,
 540     # so metadata can be added here.
 541     if opts.addmetadata or opts.addchapters or opts.embed_infojson:
 542         if opts.embed_infojson is None:
 543             opts.embed_infojson = 'if_exists'
 544         postprocessors.append({
 545             'key': 'FFmpegMetadata',
 546             'add_chapters': opts.addchapters,
 547             'add_metadata': opts.addmetadata,
 548             'add_infojson': opts.embed_infojson,
 549         })
 550     # Deprecated
 551     # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
 552     # but must be below EmbedSubtitle and FFmpegMetadata
 553     # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
 554     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
 555     if opts.sponskrub is not False:
 556         postprocessors.append({
 557             'key': 'SponSkrub',
 558             'path': opts.sponskrub_path,
 559             'args': opts.sponskrub_args,
 560             'cut': opts.sponskrub_cut,
 561             'force': opts.sponskrub_force,
 562             'ignoreerror': opts.sponskrub is None,
 563             '_from_cli': True,
 564         })
 565     if opts.embedthumbnail:
 566         postprocessors.append({
 567             'key': 'EmbedThumbnail',
 568             # already_have_thumbnail = True prevents the file from being deleted after embedding
 569             'already_have_thumbnail': opts.writethumbnail
 570         })
 571         if not opts.writethumbnail:
 572             opts.writethumbnail = True
 573             opts.outtmpl['pl_thumbnail'] = ''
 574     if opts.split_chapters:
 575         postprocessors.append({
 576             'key': 'FFmpegSplitChapters',
 577             'force_keyframes': opts.force_keyframes_at_cuts,
 578         })
 579     # XAttrMetadataPP should be run after post-processors that may change file contents
 580     if opts.xattrs:
 581         postprocessors.append({'key': 'XAttrMetadata'})
 582     # Exec must be the last PP
 583     if opts.exec_cmd:
 584         postprocessors.append({
 585             'key': 'Exec',
 586             'exec_cmd': opts.exec_cmd,
 587             # Run this only after the files have been moved to their final locations
 588             'when': 'after_move'
 589         })
 590
 591     def report_args_compat(arg, name):
 592         warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
 593
 594     if 'default' in opts.external_downloader_args:
 595         report_args_compat('--downloader-args', 'external downloaders')
 596
 597     if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
 598         report_args_compat('--post-processor-args', 'post-processors')
 599         opts.postprocessor_args.setdefault('sponskrub', [])
 600         opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
 601
 602     def report_deprecation(val, old, new=None):
 603         if not val:
 604             return
 605         deprecation_warnings.append(
 606             f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
 607             else f'{old} is deprecated and may not work as expected')
 608
 609     report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
 610     report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
 611     report_deprecation(opts.include_ads, '--include-ads')
 612     # report_deprecation(opts.call_home, '--call-home')  # We may re-implement this in future
 613     # report_deprecation(opts.writeannotations, '--write-annotations')  # It's just that no website has it
 614
 615     final_ext = (
 616         opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
 617         else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
 618         else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
 619         else None)
 620
 621     match_filter = (
 622         None if opts.match_filter is None
 623         else match_filter_func(opts.match_filter))
 624
 625     ydl_opts = {
 626         'usenetrc': opts.usenetrc,
 627         'netrc_location': opts.netrc_location,
 628         'username': opts.username,
 629         'password': opts.password,
 630         'twofactor': opts.twofactor,
 631         'videopassword': opts.videopassword,
 632         'ap_mso': opts.ap_mso,
 633         'ap_username': opts.ap_username,
 634         'ap_password': opts.ap_password,
 635         'quiet': (opts.quiet or any_getting or any_printing),
 636         'no_warnings': opts.no_warnings,
 637         'forceurl': opts.geturl,
 638         'forcetitle': opts.gettitle,
 639         'forceid': opts.getid,
 640         'forcethumbnail': opts.getthumbnail,
 641         'forcedescription': opts.getdescription,
 642         'forceduration': opts.getduration,
 643         'forcefilename': opts.getfilename,
 644         'forceformat': opts.getformat,
 645         'forceprint': opts.forceprint,
 646         'forcejson': opts.dumpjson or opts.print_json,
 647         'dump_single_json': opts.dump_single_json,
 648         'force_write_download_archive': opts.force_write_download_archive,
 649         'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
 650         'skip_download': opts.skip_download,
 651         'format': opts.format,
 652         'allow_unplayable_formats': opts.allow_unplayable_formats,
 653         'ignore_no_formats_error': opts.ignore_no_formats_error,
 654         'format_sort': opts.format_sort,
 655         'format_sort_force': opts.format_sort_force,
 656         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 657         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 658         'check_formats': opts.check_formats,
 659         'listformats': opts.listformats,
 660         'listformats_table': opts.listformats_table,
 661         'outtmpl': opts.outtmpl,
 662         'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
 663         'paths': opts.paths,
 664         'autonumber_size': opts.autonumber_size,
 665         'autonumber_start': opts.autonumber_start,
 666         'restrictfilenames': opts.restrictfilenames,
 667         'windowsfilenames': opts.windowsfilenames,
 668         'ignoreerrors': opts.ignoreerrors,
 669         'force_generic_extractor': opts.force_generic_extractor,
 670         'ratelimit': opts.ratelimit,
 671         'throttledratelimit': opts.throttledratelimit,
 672         'overwrites': opts.overwrites,
 673         'retries': opts.retries,
 674         'fragment_retries': opts.fragment_retries,
 675         'extractor_retries': opts.extractor_retries,
 676         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 677         'keep_fragments': opts.keep_fragments,
 678         'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
 679         'buffersize': opts.buffersize,
 680         'noresizebuffer': opts.noresizebuffer,
 681         'http_chunk_size': opts.http_chunk_size,
 682         'continuedl': opts.continue_dl,
 683         'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
 684         'progress_with_newline': opts.progress_with_newline,
 685         'progress_template': opts.progress_template,
 686         'playliststart': opts.playliststart,
 687         'playlistend': opts.playlistend,
 688         'playlistreverse': opts.playlist_reverse,
 689         'playlistrandom': opts.playlist_random,
 690         'noplaylist': opts.noplaylist,
 691         'logtostderr': outtmpl_default == '-',
 692         'consoletitle': opts.consoletitle,
 693         'nopart': opts.nopart,
 694         'updatetime': opts.updatetime,
 695         'writedescription': opts.writedescription,
 696         'writeannotations': opts.writeannotations,
 697         'writeinfojson': opts.writeinfojson,
 698         'allow_playlist_files': opts.allow_playlist_files,
 699         'clean_infojson': opts.clean_infojson,
 700         'getcomments': opts.getcomments,
 701         'writethumbnail': opts.writethumbnail is True,
 702         'write_all_thumbnails': opts.writethumbnail == 'all',
 703         'writelink': opts.writelink,
 704         'writeurllink': opts.writeurllink,
 705         'writewebloclink': opts.writewebloclink,
 706         'writedesktoplink': opts.writedesktoplink,
 707         'writesubtitles': opts.writesubtitles,
 708         'writeautomaticsub': opts.writeautomaticsub,
 709         'allsubtitles': opts.allsubtitles,
 710         'listsubtitles': opts.listsubtitles,
 711         'subtitlesformat': opts.subtitlesformat,
 712         'subtitleslangs': opts.subtitleslangs,
 713         'matchtitle': decodeOption(opts.matchtitle),
 714         'rejecttitle': decodeOption(opts.rejecttitle),
 715         'max_downloads': opts.max_downloads,
 716         'prefer_free_formats': opts.prefer_free_formats,
 717         'trim_file_name': opts.trim_file_name,
 718         'verbose': opts.verbose,
 719         'dump_intermediate_pages': opts.dump_intermediate_pages,
 720         'write_pages': opts.write_pages,
 721         'test': opts.test,
 722         'keepvideo': opts.keepvideo,
 723         'min_filesize': opts.min_filesize,
 724         'max_filesize': opts.max_filesize,
 725         'min_views': opts.min_views,
 726         'max_views': opts.max_views,
 727         'daterange': date,
 728         'cachedir': opts.cachedir,
 729         'youtube_print_sig_code': opts.youtube_print_sig_code,
 730         'age_limit': opts.age_limit,
 731         'download_archive': download_archive_fn,
 732         'break_on_existing': opts.break_on_existing,
 733         'break_on_reject': opts.break_on_reject,
 734         'break_per_url': opts.break_per_url,
 735         'skip_playlist_after_errors': opts.skip_playlist_after_errors,
 736         'cookiefile': opts.cookiefile,
 737         'cookiesfrombrowser': opts.cookiesfrombrowser,
 738         'nocheckcertificate': opts.no_check_certificate,
 739         'prefer_insecure': opts.prefer_insecure,
 740         'proxy': opts.proxy,
 741         'socket_timeout': opts.socket_timeout,
 742         'bidi_workaround': opts.bidi_workaround,
 743         'debug_printtraffic': opts.debug_printtraffic,
 744         'prefer_ffmpeg': opts.prefer_ffmpeg,
 745         'include_ads': opts.include_ads,
 746         'default_search': opts.default_search,
 747         'dynamic_mpd': opts.dynamic_mpd,
 748         'extractor_args': opts.extractor_args,
 749         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 750         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 751         'encoding': opts.encoding,
 752         'extract_flat': opts.extract_flat,
 753         'live_from_start': opts.live_from_start,
 754         'wait_for_video': opts.wait_for_video,
 755         'mark_watched': opts.mark_watched,
 756         'merge_output_format': opts.merge_output_format,
 757         'final_ext': final_ext,
 758         'postprocessors': postprocessors,
 759         'fixup': opts.fixup,
 760         'source_address': opts.source_address,
 761         'call_home': opts.call_home,
 762         'sleep_interval_requests': opts.sleep_interval_requests,
 763         'sleep_interval': opts.sleep_interval,
 764         'max_sleep_interval': opts.max_sleep_interval,
 765         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 766         'external_downloader': opts.external_downloader,
 767         'list_thumbnails': opts.list_thumbnails,
 768         'playlist_items': opts.playlist_items,
 769         'xattr_set_filesize': opts.xattr_set_filesize,
 770         'match_filter': match_filter,
 771         'no_color': opts.no_color,
 772         'ffmpeg_location': opts.ffmpeg_location,
 773         'hls_prefer_native': opts.hls_prefer_native,
 774         'hls_use_mpegts': opts.hls_use_mpegts,
 775         'hls_split_discontinuity': opts.hls_split_discontinuity,
 776         'external_downloader_args': opts.external_downloader_args,
 777         'postprocessor_args': opts.postprocessor_args,
 778         'cn_verification_proxy': opts.cn_verification_proxy,
 779         'geo_verification_proxy': opts.geo_verification_proxy,
 780         'geo_bypass': opts.geo_bypass,
 781         'geo_bypass_country': opts.geo_bypass_country,
 782         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 783         '_warnings': warnings,
 784         '_deprecation_warnings': deprecation_warnings,
 785         'compat_opts': compat_opts,
 786     }
 787
 788     with YoutubeDL(ydl_opts) as ydl:
 789         actual_use = all_urls or opts.load_info_filename
 790
 791         # Remove cache dir
 792         if opts.rm_cachedir:
 793             ydl.cache.remove()
 794
 795         # Update version
 796         if opts.update_self:
 797             # If updater returns True, exit. Required for windows
 798             if run_update(ydl):
 799                 if actual_use:
 800                     sys.exit('ERROR: The program must exit for the update to complete')
 801                 sys.exit()
 802
 803         # Maybe do nothing
 804         if not actual_use:
 805             if opts.update_self or opts.rm_cachedir:
 806                 sys.exit()
 807
 808             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 809             parser.error(
 810                 'You must provide at least one URL.\n'
 811                 'Type yt-dlp --help to see a list of all options.')
 812
 813         try:
 814             if opts.load_info_filename is not None:
 815                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
 816             else:
 817                 retcode = ydl.download(all_urls)
 818         except DownloadCancelled:
 819             ydl.to_screen('Aborting remaining downloads')
 820             retcode = 101
 821
 822     sys.exit(retcode)
 823
 824
 825 def main(argv=None):
 826     try:
 827         _real_main(argv)
 828     except DownloadError:
 829         sys.exit(1)
 830     except SameFileError as e:
 831         sys.exit(f'ERROR: {e}')
 832     except KeyboardInterrupt:
 833         sys.exit('\nERROR: Interrupted by user')
 834     except BrokenPipeError as e:
 835         # https://docs.python.org/3/library/signal.html#note-on-sigpipe
 836         devnull = os.open(os.devnull, os.O_WRONLY)
 837         os.dup2(devnull, sys.stdout.fileno())
 838         sys.exit(f'\nERROR: {e}')
 839
 840
 841 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']