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_os_name,
  22     compat_shlex_quote,
  23     workaround_optparse_bug9161,
  24 )
  25 from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
  26 from .utils import (
  27     DateRange,
  28     decodeOption,
  29     DownloadCancelled,
  30     DownloadError,
  31     error_to_compat_str,
  32     expand_path,
  33     GeoUtils,
  34     float_or_none,
  35     int_or_none,
  36     match_filter_func,
  37     parse_duration,
  38     preferredencoding,
  39     read_batch_urls,
  40     render_table,
  41     SameFileError,
  42     setproctitle,
  43     std_headers,
  44     traverse_obj,
  45     write_string,
  46 )
  47 from .update import run_update
  48 from .downloader import (
  49     FileDownloader,
  50 )
  51 from .extractor import gen_extractors, list_extractors
  52 from .extractor.common import InfoExtractor
  53 from .extractor.adobepass import MSO_INFO
  54 from .postprocessor import (
  55     FFmpegExtractAudioPP,
  56     FFmpegSubtitlesConvertorPP,
  57     FFmpegThumbnailsConvertorPP,
  58     FFmpegVideoConvertorPP,
  59     FFmpegVideoRemuxerPP,
  60     MetadataFromFieldPP,
  61     MetadataParserPP,
  62 )
  63 from .YoutubeDL import YoutubeDL
  64
  65
  66 def _real_main(argv=None):
  67     # Compatibility fixes for Windows
  68     if sys.platform == 'win32':
  69         # https://github.com/ytdl-org/youtube-dl/issues/820
  70         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  71
  72     workaround_optparse_bug9161()
  73
  74     setproctitle('yt-dlp')
  75
  76     parser, opts, args = parseOpts(argv)
  77     warnings, deprecation_warnings = [], []
  78
  79     if opts.user_agent is not None:
  80         opts.headers.setdefault('User-Agent', opts.user_agent)
  81     if opts.referer is not None:
  82         opts.headers.setdefault('Referer', opts.referer)
  83
  84     # Dump user agent
  85     if opts.dump_user_agent:
  86         ua = traverse_obj(opts.headers, 'User-Agent', casesense=False, default=std_headers['User-Agent'])
  87         write_string(f'{ua}\n', out=sys.stdout)
  88         sys.exit(0)
  89
  90     # Batch file verification
  91     batch_urls = []
  92     if opts.batchfile is not None:
  93         try:
  94             if opts.batchfile == '-':
  95                 write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
  96                     'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
  97                 batchfd = sys.stdin
  98             else:
  99                 batchfd = io.open(
 100                     expand_path(opts.batchfile),
 101                     'r', encoding='utf-8', errors='ignore')
 102             batch_urls = read_batch_urls(batchfd)
 103             if opts.verbose:
 104                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
 105         except IOError:
 106             sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
 107     all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
 108     _enc = preferredencoding()
 109     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 110
 111     if opts.list_extractors:
 112         for ie in list_extractors(opts.age_limit):
 113             write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
 114             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 115             for mu in matchedUrls:
 116                 write_string('  ' + mu + '\n', out=sys.stdout)
 117         sys.exit(0)
 118     if opts.list_extractor_descriptions:
 119         for ie in list_extractors(opts.age_limit):
 120             if not ie.working():
 121                 continue
 122             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
 123             if desc is False:
 124                 continue
 125             if getattr(ie, 'SEARCH_KEY', None) is not None:
 126                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 127                 _COUNTS = ('', '5', '10', 'all')
 128                 desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
 129             write_string(desc + '\n', out=sys.stdout)
 130         sys.exit(0)
 131     if opts.ap_list_mso:
 132         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
 133         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
 134         sys.exit(0)
 135
 136     # Conflicting, missing and erroneous options
 137     if opts.format == 'best':
 138         warnings.append('.\n         '.join((
 139             '"-f best" selects the best pre-merged format which is often not the best option',
 140             'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
 141             'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
 142     if opts.exec_cmd.get('before_dl') and opts.exec_before_dl_cmd:
 143         parser.error('using "--exec-before-download" conflicts with "--exec before_dl:"')
 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.file_access_retries is not None:
 224         opts.file_access_retries = parse_retries(opts.file_access_retries, 'file access ')
 225     if opts.fragment_retries is not None:
 226         opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
 227     if opts.extractor_retries is not None:
 228         opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
 229     if opts.buffersize is not None:
 230         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 231         if numeric_buffersize is None:
 232             parser.error('invalid buffer size specified')
 233         opts.buffersize = numeric_buffersize
 234     if opts.http_chunk_size is not None:
 235         numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
 236         if not numeric_chunksize:
 237             parser.error('invalid http chunk size specified')
 238         opts.http_chunk_size = numeric_chunksize
 239     if opts.playliststart <= 0:
 240         raise parser.error('Playlist start must be positive')
 241     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 242         raise parser.error('Playlist end must be greater than playlist start')
 243     if opts.extractaudio:
 244         opts.audioformat = opts.audioformat.lower()
 245         if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
 246             parser.error('invalid audio format specified')
 247     if opts.audioquality:
 248         opts.audioquality = opts.audioquality.strip('k').strip('K')
 249         audioquality = int_or_none(float_or_none(opts.audioquality))  # int_or_none prevents inf, nan
 250         if audioquality is None or audioquality < 0:
 251             parser.error('invalid audio quality specified')
 252     if opts.recodevideo is not None:
 253         opts.recodevideo = opts.recodevideo.replace(' ', '')
 254         if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
 255             parser.error('invalid video remux format specified')
 256     if opts.remuxvideo is not None:
 257         opts.remuxvideo = opts.remuxvideo.replace(' ', '')
 258         if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
 259             parser.error('invalid video remux format specified')
 260     if opts.convertsubtitles is not None:
 261         if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
 262             parser.error('invalid subtitle format specified')
 263     if opts.convertthumbnails is not None:
 264         if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
 265             parser.error('invalid thumbnail format specified')
 266     if opts.cookiesfrombrowser is not None:
 267         mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
 268         if mobj is None:
 269             parser.error(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
 270         browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
 271         browser_name = browser_name.lower()
 272         if browser_name not in SUPPORTED_BROWSERS:
 273             parser.error(f'unsupported browser specified for cookies: "{browser_name}". '
 274                          f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
 275         if keyring is not None:
 276             keyring = keyring.upper()
 277             if keyring not in SUPPORTED_KEYRINGS:
 278                 parser.error(f'unsupported keyring specified for cookies: "{keyring}". '
 279                              f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
 280         opts.cookiesfrombrowser = (browser_name, profile, keyring)
 281     geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
 282     if geo_bypass_code is not None:
 283         try:
 284             GeoUtils.random_ipv4(geo_bypass_code)
 285         except Exception:
 286             parser.error('unsupported geo-bypass country or ip-block')
 287
 288     if opts.date is not None:
 289         date = DateRange.day(opts.date)
 290     else:
 291         date = DateRange(opts.dateafter, opts.datebefore)
 292
 293     compat_opts = opts.compat_opts
 294
 295     def report_conflict(arg1, arg2):
 296         warnings.append(f'{arg2} is ignored since {arg1} was given')
 297
 298     def _unused_compat_opt(name):
 299         if name not in compat_opts:
 300             return False
 301         compat_opts.discard(name)
 302         compat_opts.update(['*%s' % name])
 303         return True
 304
 305     def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
 306         attr = getattr(opts, opt_name)
 307         if compat_name in compat_opts:
 308             if attr is None:
 309                 setattr(opts, opt_name, not default)
 310                 return True
 311             else:
 312                 if remove_compat:
 313                     _unused_compat_opt(compat_name)
 314                 return False
 315         elif attr is None:
 316             setattr(opts, opt_name, default)
 317         return None
 318
 319     set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
 320     set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
 321     set_default_compat('no-clean-infojson', 'clean_infojson')
 322     if 'no-attach-info-json' in compat_opts:
 323         if opts.embed_infojson:
 324             _unused_compat_opt('no-attach-info-json')
 325         else:
 326             opts.embed_infojson = False
 327     if 'format-sort' in compat_opts:
 328         opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
 329     _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
 330     _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
 331     if _video_multistreams_set is False and _audio_multistreams_set is False:
 332         _unused_compat_opt('multistreams')
 333     outtmpl_default = opts.outtmpl.get('default')
 334     if outtmpl_default == '':
 335         outtmpl_default, opts.skip_download = None, True
 336         del opts.outtmpl['default']
 337     if opts.useid:
 338         if outtmpl_default is None:
 339             outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
 340         else:
 341             report_conflict('--output', '--id')
 342     if 'filename' in compat_opts:
 343         if outtmpl_default is None:
 344             outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
 345         else:
 346             _unused_compat_opt('filename')
 347
 348     def validate_outtmpl(tmpl, msg):
 349         err = YoutubeDL.validate_outtmpl(tmpl)
 350         if err:
 351             parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
 352
 353     for k, tmpl in opts.outtmpl.items():
 354         validate_outtmpl(tmpl, f'{k} output template')
 355     for type_, tmpl_list in opts.forceprint.items():
 356         for tmpl in tmpl_list:
 357             validate_outtmpl(tmpl, f'{type_} print template')
 358     for type_, tmpl_list in opts.print_to_file.items():
 359         for tmpl, file in tmpl_list:
 360             validate_outtmpl(tmpl, f'{type_} print-to-file template')
 361             validate_outtmpl(file, f'{type_} print-to-file filename')
 362     validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
 363     for k, tmpl in opts.progress_template.items():
 364         k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
 365         validate_outtmpl(tmpl, f'{k} template')
 366
 367     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 368         opts.format = 'bestaudio/best'
 369
 370     if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
 371         parser.error('Cannot download a video and extract audio into the same'
 372                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 373                      ' template'.format(outtmpl_default))
 374
 375     for f in opts.format_sort:
 376         if re.match(InfoExtractor.FormatSort.regex, f) is None:
 377             parser.error('invalid format sort string "%s" specified' % f)
 378
 379     def metadataparser_actions(f):
 380         if isinstance(f, str):
 381             cmd = '--parse-metadata %s' % compat_shlex_quote(f)
 382             try:
 383                 actions = [MetadataFromFieldPP.to_action(f)]
 384             except Exception as err:
 385                 parser.error(f'{cmd} is invalid; {err}')
 386         else:
 387             cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
 388             actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
 389
 390         for action in actions:
 391             try:
 392                 MetadataParserPP.validate_action(*action)
 393             except Exception as err:
 394                 parser.error(f'{cmd} is invalid; {err}')
 395             yield action
 396
 397     if opts.parse_metadata is None:
 398         opts.parse_metadata = []
 399     if opts.metafromtitle is not None:
 400         opts.parse_metadata.append('title:%s' % opts.metafromtitle)
 401     opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
 402
 403     any_getting = (any(opts.forceprint.values()) or opts.dumpjson or opts.dump_single_json
 404                    or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail
 405                    or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration)
 406
 407     any_printing = opts.print_json
 408     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 409
 410     # If JSON is not printed anywhere, but comments are requested, save it to file
 411     printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
 412     if opts.getcomments and not printing_json:
 413         opts.writeinfojson = True
 414
 415     if opts.no_sponsorblock:
 416         opts.sponsorblock_mark = set()
 417         opts.sponsorblock_remove = set()
 418     sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
 419
 420     opts.remove_chapters = opts.remove_chapters or []
 421
 422     if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
 423         if opts.sponskrub:
 424             if opts.remove_chapters:
 425                 report_conflict('--remove-chapters', '--sponskrub')
 426             if opts.sponsorblock_mark:
 427                 report_conflict('--sponsorblock-mark', '--sponskrub')
 428             if opts.sponsorblock_remove:
 429                 report_conflict('--sponsorblock-remove', '--sponskrub')
 430         opts.sponskrub = False
 431     if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
 432         report_conflict('--split-chapter', '--sponskrub-cut')
 433         opts.sponskrub_cut = False
 434
 435     if opts.remuxvideo and opts.recodevideo:
 436         report_conflict('--recode-video', '--remux-video')
 437         opts.remuxvideo = False
 438
 439     if opts.allow_unplayable_formats:
 440         def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
 441             val = getattr(opts, opt_name)
 442             if (not allowed and val) or (allowed and not allowed(val)):
 443                 report_conflict('--allow-unplayable-formats', arg)
 444                 setattr(opts, opt_name, default)
 445
 446         report_unplayable_conflict('extractaudio', '--extract-audio')
 447         report_unplayable_conflict('remuxvideo', '--remux-video')
 448         report_unplayable_conflict('recodevideo', '--recode-video')
 449         report_unplayable_conflict('addmetadata', '--embed-metadata')
 450         report_unplayable_conflict('addchapters', '--embed-chapters')
 451         report_unplayable_conflict('embed_infojson', '--embed-info-json')
 452         opts.embed_infojson = False
 453         report_unplayable_conflict('embedsubtitles', '--embed-subs')
 454         report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
 455         report_unplayable_conflict('xattrs', '--xattrs')
 456         report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
 457         opts.fixup = 'never'
 458         report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
 459         report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
 460         report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
 461         opts.sponskrub = False
 462
 463     if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
 464         opts.addchapters = True
 465
 466     # PostProcessors
 467     postprocessors = list(opts.add_postprocessors)
 468     if sponsorblock_query:
 469         postprocessors.append({
 470             'key': 'SponsorBlock',
 471             'categories': sponsorblock_query,
 472             'api': opts.sponsorblock_api,
 473             # Run this after filtering videos
 474             'when': 'after_filter'
 475         })
 476     if opts.parse_metadata:
 477         postprocessors.append({
 478             'key': 'MetadataParser',
 479             'actions': opts.parse_metadata,
 480             # Run this immediately after extraction is complete
 481             'when': 'pre_process'
 482         })
 483     if opts.convertsubtitles:
 484         postprocessors.append({
 485             'key': 'FFmpegSubtitlesConvertor',
 486             'format': opts.convertsubtitles,
 487             # Run this before the actual video download
 488             'when': 'before_dl'
 489         })
 490     if opts.convertthumbnails:
 491         postprocessors.append({
 492             'key': 'FFmpegThumbnailsConvertor',
 493             'format': opts.convertthumbnails,
 494             # Run this before the actual video download
 495             'when': 'before_dl'
 496         })
 497     if opts.extractaudio:
 498         postprocessors.append({
 499             'key': 'FFmpegExtractAudio',
 500             'preferredcodec': opts.audioformat,
 501             'preferredquality': opts.audioquality,
 502             'nopostoverwrites': opts.nopostoverwrites,
 503         })
 504     if opts.remuxvideo:
 505         postprocessors.append({
 506             'key': 'FFmpegVideoRemuxer',
 507             'preferedformat': opts.remuxvideo,
 508         })
 509     if opts.recodevideo:
 510         postprocessors.append({
 511             'key': 'FFmpegVideoConvertor',
 512             'preferedformat': opts.recodevideo,
 513         })
 514     # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
 515     if opts.embedsubtitles:
 516         already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
 517         postprocessors.append({
 518             'key': 'FFmpegEmbedSubtitle',
 519             # already_have_subtitle = True prevents the file from being deleted after embedding
 520             'already_have_subtitle': already_have_subtitle
 521         })
 522         if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
 523             opts.writesubtitles = True
 524     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 525     # this was the old behaviour if only --all-sub was given.
 526     if opts.allsubtitles and not opts.writeautomaticsub:
 527         opts.writesubtitles = True
 528     # ModifyChapters must run before FFmpegMetadataPP
 529     remove_chapters_patterns, remove_ranges = [], []
 530     for regex in opts.remove_chapters:
 531         if regex.startswith('*'):
 532             dur = list(map(parse_duration, regex[1:].split('-')))
 533             if len(dur) == 2 and all(t is not None for t in dur):
 534                 remove_ranges.append(tuple(dur))
 535                 continue
 536             parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
 537         try:
 538             remove_chapters_patterns.append(re.compile(regex))
 539         except re.error as err:
 540             parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
 541     if opts.remove_chapters or sponsorblock_query:
 542         postprocessors.append({
 543             'key': 'ModifyChapters',
 544             'remove_chapters_patterns': remove_chapters_patterns,
 545             'remove_sponsor_segments': opts.sponsorblock_remove,
 546             'remove_ranges': remove_ranges,
 547             'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
 548             'force_keyframes': opts.force_keyframes_at_cuts
 549         })
 550     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 551     # FFmpegExtractAudioPP as containers before conversion may not support
 552     # metadata (3gp, webm, etc.)
 553     # By default ffmpeg preserves metadata applicable for both
 554     # source and target containers. From this point the container won't change,
 555     # so metadata can be added here.
 556     if opts.addmetadata or opts.addchapters or opts.embed_infojson:
 557         if opts.embed_infojson is None:
 558             opts.embed_infojson = 'if_exists'
 559         postprocessors.append({
 560             'key': 'FFmpegMetadata',
 561             'add_chapters': opts.addchapters,
 562             'add_metadata': opts.addmetadata,
 563             'add_infojson': opts.embed_infojson,
 564         })
 565     # Deprecated
 566     # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
 567     # but must be below EmbedSubtitle and FFmpegMetadata
 568     # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
 569     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
 570     if opts.sponskrub is not False:
 571         postprocessors.append({
 572             'key': 'SponSkrub',
 573             'path': opts.sponskrub_path,
 574             'args': opts.sponskrub_args,
 575             'cut': opts.sponskrub_cut,
 576             'force': opts.sponskrub_force,
 577             'ignoreerror': opts.sponskrub is None,
 578             '_from_cli': True,
 579         })
 580     if opts.embedthumbnail:
 581         postprocessors.append({
 582             'key': 'EmbedThumbnail',
 583             # already_have_thumbnail = True prevents the file from being deleted after embedding
 584             'already_have_thumbnail': opts.writethumbnail
 585         })
 586         if not opts.writethumbnail:
 587             opts.writethumbnail = True
 588             opts.outtmpl['pl_thumbnail'] = ''
 589     if opts.split_chapters:
 590         postprocessors.append({
 591             'key': 'FFmpegSplitChapters',
 592             'force_keyframes': opts.force_keyframes_at_cuts,
 593         })
 594     # XAttrMetadataPP should be run after post-processors that may change file contents
 595     if opts.xattrs:
 596         postprocessors.append({'key': 'XAttrMetadata'})
 597     if opts.concat_playlist != 'never':
 598         postprocessors.append({
 599             'key': 'FFmpegConcat',
 600             'only_multi_video': opts.concat_playlist != 'always',
 601             'when': 'playlist',
 602         })
 603     # Exec must be the last PP of each category
 604     if opts.exec_before_dl_cmd:
 605         opts.exec_cmd.setdefault('before_dl', opts.exec_before_dl_cmd)
 606     for when, exec_cmd in opts.exec_cmd.items():
 607         postprocessors.append({
 608             'key': 'Exec',
 609             'exec_cmd': exec_cmd,
 610             # Run this only after the files have been moved to their final locations
 611             'when': when,
 612         })
 613
 614     def report_args_compat(arg, name):
 615         warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
 616
 617     if 'default' in opts.external_downloader_args:
 618         report_args_compat('--downloader-args', 'external downloaders')
 619
 620     if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
 621         report_args_compat('--post-processor-args', 'post-processors')
 622         opts.postprocessor_args.setdefault('sponskrub', [])
 623         opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
 624
 625     def report_deprecation(val, old, new=None):
 626         if not val:
 627             return
 628         deprecation_warnings.append(
 629             f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
 630             else f'{old} is deprecated and may not work as expected')
 631
 632     report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
 633     report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
 634     report_deprecation(opts.include_ads, '--include-ads')
 635     # report_deprecation(opts.call_home, '--call-home')  # We may re-implement this in future
 636     # report_deprecation(opts.writeannotations, '--write-annotations')  # It's just that no website has it
 637
 638     final_ext = (
 639         opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
 640         else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
 641         else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
 642         else None)
 643
 644     match_filter = (
 645         None if opts.match_filter is None
 646         else match_filter_func(opts.match_filter))
 647
 648     ydl_opts = {
 649         'usenetrc': opts.usenetrc,
 650         'netrc_location': opts.netrc_location,
 651         'username': opts.username,
 652         'password': opts.password,
 653         'twofactor': opts.twofactor,
 654         'videopassword': opts.videopassword,
 655         'ap_mso': opts.ap_mso,
 656         'ap_username': opts.ap_username,
 657         'ap_password': opts.ap_password,
 658         'quiet': (opts.quiet or any_getting or any_printing),
 659         'no_warnings': opts.no_warnings,
 660         'forceurl': opts.geturl,
 661         'forcetitle': opts.gettitle,
 662         'forceid': opts.getid,
 663         'forcethumbnail': opts.getthumbnail,
 664         'forcedescription': opts.getdescription,
 665         'forceduration': opts.getduration,
 666         'forcefilename': opts.getfilename,
 667         'forceformat': opts.getformat,
 668         'forceprint': opts.forceprint,
 669         'print_to_file': opts.print_to_file,
 670         'forcejson': opts.dumpjson or opts.print_json,
 671         'dump_single_json': opts.dump_single_json,
 672         'force_write_download_archive': opts.force_write_download_archive,
 673         'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
 674         'skip_download': opts.skip_download,
 675         'format': opts.format,
 676         'allow_unplayable_formats': opts.allow_unplayable_formats,
 677         'ignore_no_formats_error': opts.ignore_no_formats_error,
 678         'format_sort': opts.format_sort,
 679         'format_sort_force': opts.format_sort_force,
 680         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 681         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 682         'check_formats': opts.check_formats,
 683         'listformats': opts.listformats,
 684         'listformats_table': opts.listformats_table,
 685         'outtmpl': opts.outtmpl,
 686         'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
 687         'paths': opts.paths,
 688         'autonumber_size': opts.autonumber_size,
 689         'autonumber_start': opts.autonumber_start,
 690         'restrictfilenames': opts.restrictfilenames,
 691         'windowsfilenames': opts.windowsfilenames,
 692         'ignoreerrors': opts.ignoreerrors,
 693         'force_generic_extractor': opts.force_generic_extractor,
 694         'ratelimit': opts.ratelimit,
 695         'throttledratelimit': opts.throttledratelimit,
 696         'overwrites': opts.overwrites,
 697         'retries': opts.retries,
 698         'file_access_retries': opts.file_access_retries,
 699         'fragment_retries': opts.fragment_retries,
 700         'extractor_retries': opts.extractor_retries,
 701         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 702         'keep_fragments': opts.keep_fragments,
 703         'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
 704         'buffersize': opts.buffersize,
 705         'noresizebuffer': opts.noresizebuffer,
 706         'http_chunk_size': opts.http_chunk_size,
 707         'continuedl': opts.continue_dl,
 708         'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
 709         'progress_with_newline': opts.progress_with_newline,
 710         'progress_template': opts.progress_template,
 711         'playliststart': opts.playliststart,
 712         'playlistend': opts.playlistend,
 713         'playlistreverse': opts.playlist_reverse,
 714         'playlistrandom': opts.playlist_random,
 715         'noplaylist': opts.noplaylist,
 716         'logtostderr': outtmpl_default == '-',
 717         'consoletitle': opts.consoletitle,
 718         'nopart': opts.nopart,
 719         'updatetime': opts.updatetime,
 720         'writedescription': opts.writedescription,
 721         'writeannotations': opts.writeannotations,
 722         'writeinfojson': opts.writeinfojson,
 723         'allow_playlist_files': opts.allow_playlist_files,
 724         'clean_infojson': opts.clean_infojson,
 725         'getcomments': opts.getcomments,
 726         'writethumbnail': opts.writethumbnail is True,
 727         'write_all_thumbnails': opts.writethumbnail == 'all',
 728         'writelink': opts.writelink,
 729         'writeurllink': opts.writeurllink,
 730         'writewebloclink': opts.writewebloclink,
 731         'writedesktoplink': opts.writedesktoplink,
 732         'writesubtitles': opts.writesubtitles,
 733         'writeautomaticsub': opts.writeautomaticsub,
 734         'allsubtitles': opts.allsubtitles,
 735         'listsubtitles': opts.listsubtitles,
 736         'subtitlesformat': opts.subtitlesformat,
 737         'subtitleslangs': opts.subtitleslangs,
 738         'matchtitle': decodeOption(opts.matchtitle),
 739         'rejecttitle': decodeOption(opts.rejecttitle),
 740         'max_downloads': opts.max_downloads,
 741         'prefer_free_formats': opts.prefer_free_formats,
 742         'trim_file_name': opts.trim_file_name,
 743         'verbose': opts.verbose,
 744         'dump_intermediate_pages': opts.dump_intermediate_pages,
 745         'write_pages': opts.write_pages,
 746         'test': opts.test,
 747         'keepvideo': opts.keepvideo,
 748         'min_filesize': opts.min_filesize,
 749         'max_filesize': opts.max_filesize,
 750         'min_views': opts.min_views,
 751         'max_views': opts.max_views,
 752         'daterange': date,
 753         'cachedir': opts.cachedir,
 754         'youtube_print_sig_code': opts.youtube_print_sig_code,
 755         'age_limit': opts.age_limit,
 756         'download_archive': download_archive_fn,
 757         'break_on_existing': opts.break_on_existing,
 758         'break_on_reject': opts.break_on_reject,
 759         'break_per_url': opts.break_per_url,
 760         'skip_playlist_after_errors': opts.skip_playlist_after_errors,
 761         'cookiefile': opts.cookiefile,
 762         'cookiesfrombrowser': opts.cookiesfrombrowser,
 763         'legacyserverconnect': opts.legacy_server_connect,
 764         'nocheckcertificate': opts.no_check_certificate,
 765         'prefer_insecure': opts.prefer_insecure,
 766         'http_headers': opts.headers,
 767         'proxy': opts.proxy,
 768         'socket_timeout': opts.socket_timeout,
 769         'bidi_workaround': opts.bidi_workaround,
 770         'debug_printtraffic': opts.debug_printtraffic,
 771         'prefer_ffmpeg': opts.prefer_ffmpeg,
 772         'include_ads': opts.include_ads,
 773         'default_search': opts.default_search,
 774         'dynamic_mpd': opts.dynamic_mpd,
 775         'extractor_args': opts.extractor_args,
 776         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 777         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 778         'encoding': opts.encoding,
 779         'extract_flat': opts.extract_flat,
 780         'live_from_start': opts.live_from_start,
 781         'wait_for_video': opts.wait_for_video,
 782         'mark_watched': opts.mark_watched,
 783         'merge_output_format': opts.merge_output_format,
 784         'final_ext': final_ext,
 785         'postprocessors': postprocessors,
 786         'fixup': opts.fixup,
 787         'source_address': opts.source_address,
 788         'call_home': opts.call_home,
 789         'sleep_interval_requests': opts.sleep_interval_requests,
 790         'sleep_interval': opts.sleep_interval,
 791         'max_sleep_interval': opts.max_sleep_interval,
 792         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 793         'external_downloader': opts.external_downloader,
 794         'list_thumbnails': opts.list_thumbnails,
 795         'playlist_items': opts.playlist_items,
 796         'xattr_set_filesize': opts.xattr_set_filesize,
 797         'match_filter': match_filter,
 798         'no_color': opts.no_color,
 799         'ffmpeg_location': opts.ffmpeg_location,
 800         'hls_prefer_native': opts.hls_prefer_native,
 801         'hls_use_mpegts': opts.hls_use_mpegts,
 802         'hls_split_discontinuity': opts.hls_split_discontinuity,
 803         'external_downloader_args': opts.external_downloader_args,
 804         'postprocessor_args': opts.postprocessor_args,
 805         'cn_verification_proxy': opts.cn_verification_proxy,
 806         'geo_verification_proxy': opts.geo_verification_proxy,
 807         'geo_bypass': opts.geo_bypass,
 808         'geo_bypass_country': opts.geo_bypass_country,
 809         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 810         '_warnings': warnings,
 811         '_deprecation_warnings': deprecation_warnings,
 812         'compat_opts': compat_opts,
 813     }
 814
 815     with YoutubeDL(ydl_opts) as ydl:
 816         actual_use = all_urls or opts.load_info_filename
 817
 818         # Remove cache dir
 819         if opts.rm_cachedir:
 820             ydl.cache.remove()
 821
 822         # Update version
 823         if opts.update_self:
 824             # If updater returns True, exit. Required for windows
 825             if run_update(ydl):
 826                 if actual_use:
 827                     sys.exit('ERROR: The program must exit for the update to complete')
 828                 sys.exit()
 829
 830         # Maybe do nothing
 831         if not actual_use:
 832             if opts.update_self or opts.rm_cachedir:
 833                 sys.exit()
 834
 835             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 836             parser.error(
 837                 'You must provide at least one URL.\n'
 838                 'Type yt-dlp --help to see a list of all options.')
 839
 840         try:
 841             if opts.load_info_filename is not None:
 842                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
 843             else:
 844                 retcode = ydl.download(all_urls)
 845         except DownloadCancelled:
 846             ydl.to_screen('Aborting remaining downloads')
 847             retcode = 101
 848
 849     sys.exit(retcode)
 850
 851
 852 def main(argv=None):
 853     try:
 854         _real_main(argv)
 855     except DownloadError:
 856         sys.exit(1)
 857     except SameFileError as e:
 858         sys.exit(f'ERROR: {e}')
 859     except KeyboardInterrupt:
 860         sys.exit('\nERROR: Interrupted by user')
 861     except BrokenPipeError as e:
 862         # https://docs.python.org/3/library/signal.html#note-on-sigpipe
 863         devnull = os.open(os.devnull, os.O_WRONLY)
 864         os.dup2(devnull, sys.stdout.fileno())
 865         sys.exit(f'\nERROR: {e}')
 866
 867
 868 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']