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