]> jfr.im git - yt-dlp.git/blame - yt_dlp/__init__.py
Allow `--exec` to be run at any post-processing stage
[yt-dlp.git] / yt_dlp / __init__.py
CommitLineData
cc52de43 1#!/usr/bin/env python3
dcdb292f 2# coding: utf-8
235b3ba4 3
347182a0 4f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp' # noqa: F541
a4bc4336 5
235b3ba4 6__license__ = 'Public Domain'
235b3ba4 7
0d94f247 8import codecs
8f563f32 9import io
e9f4ccd1 10import itertools
235b3ba4 11import os
0f818663 12import random
43820c03 13import re
235b3ba4 14import sys
235b3ba4 15
2daabe49
PH
16from .options import (
17 parseOpts,
18)
8c25f81b 19from .compat import (
e68301af 20 compat_getpass,
b69fd25c 21 compat_os_name,
e9f4ccd1 22 compat_shlex_quote,
e07e9313 23 workaround_optparse_bug9161,
8c25f81b 24)
f59f5ef8 25from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
8c25f81b 26from .utils import (
a4fd0415
PH
27 DateRange,
28 decodeOption,
f304da8a 29 DownloadCancelled,
a4fd0415 30 DownloadError,
76a264ac 31 error_to_compat_str,
590bc6f6 32 expand_path,
717216b0 33 GeoUtils,
31c49255 34 float_or_none,
35 int_or_none,
347de493 36 match_filter_func,
2d9ec704 37 parse_duration,
a4fd0415 38 preferredencoding,
62e609ab 39 read_batch_urls,
df692c5a 40 render_table,
a4fd0415 41 SameFileError,
e3946f98 42 setproctitle,
a4fd0415
PH
43 std_headers,
44 write_string,
a4fd0415 45)
c19bc311 46from .update import run_update
92a86f4c 47from .downloader import (
a4fd0415
PH
48 FileDownloader,
49)
2bad0e5d 50from .extractor import gen_extractors, list_extractors
eb8a4433 51from .extractor.common import InfoExtractor
1b6712ab 52from .extractor.adobepass import MSO_INFO
e9f4ccd1 53from .postprocessor import (
81a23040 54 FFmpegExtractAudioPP,
55 FFmpegSubtitlesConvertorPP,
56 FFmpegThumbnailsConvertorPP,
57 FFmpegVideoConvertorPP,
58 FFmpegVideoRemuxerPP,
e9f4ccd1 59 MetadataFromFieldPP,
60 MetadataParserPP,
81a23040 61)
8222d8de 62from .YoutubeDL import YoutubeDL
a4fd0415 63
235b3ba4 64
b8ad4f02 65def _real_main(argv=None):
0d94f247
PH
66 # Compatibility fixes for Windows
67 if sys.platform == 'win32':
067aa17e 68 # https://github.com/ytdl-org/youtube-dl/issues/820
0d94f247
PH
69 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
70
e07e9313
PH
71 workaround_optparse_bug9161()
72
7a5c1cfe 73 setproctitle('yt-dlp')
e3946f98 74
b8ad4f02 75 parser, opts, args = parseOpts(argv)
ee8dd27a 76 warnings, deprecation_warnings = [], []
59ae15a5 77
59ae15a5
PH
78 # Set user agent
79 if opts.user_agent is not None:
80 std_headers['User-Agent'] = opts.user_agent
1865ed31 81
28535652
BH
82 # Set referer
83 if opts.referer is not None:
84 std_headers['Referer'] = opts.referer
59ae15a5 85
410afb20 86 # Custom HTTP headers
45016689 87 std_headers.update(opts.headers)
410afb20 88
59ae15a5
PH
89 # Dump user agent
90 if opts.dump_user_agent:
7b0d1c28 91 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
59ae15a5
PH
92 sys.exit(0)
93
94 # Batch file verification
62e609ab 95 batch_urls = []
59ae15a5
PH
96 if opts.batchfile is not None:
97 try:
98 if opts.batchfile == '-':
b69fd25c 99 write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
100 'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
59ae15a5
PH
101 batchfd = sys.stdin
102 else:
e2eca6f6 103 batchfd = io.open(
590bc6f6 104 expand_path(opts.batchfile),
e2eca6f6 105 'r', encoding='utf-8', errors='ignore')
62e609ab 106 batch_urls = read_batch_urls(batchfd)
05afc96b 107 if opts.verbose:
a4bc4336 108 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
59ae15a5 109 except IOError:
826dcff9 110 sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
b2fc1c4f 111 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
c774b3c6 112 _enc = preferredencoding()
41292a38 113 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
59ae15a5 114
59ae15a5 115 if opts.list_extractors:
05900629 116 for ie in list_extractors(opts.age_limit):
251ae04e 117 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
1a2c3c0f 118 matchedUrls = [url for url in all_urls if ie.suitable(url)]
59ae15a5 119 for mu in matchedUrls:
7b0d1c28 120 write_string(' ' + mu + '\n', out=sys.stdout)
59ae15a5 121 sys.exit(0)
0f818663 122 if opts.list_extractor_descriptions:
05900629 123 for ie in list_extractors(opts.age_limit):
251ae04e 124 if not ie.working():
0f818663
PH
125 continue
126 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
15870e90
PH
127 if desc is False:
128 continue
96565c7e 129 if getattr(ie, 'SEARCH_KEY', None) is not None:
50a0f6df 130 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
a4bc4336 131 _COUNTS = ('', '5', '10', 'all')
96565c7e 132 desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
7b0d1c28 133 write_string(desc + '\n', out=sys.stdout)
0f818663 134 sys.exit(0)
87148bb7 135 if opts.ap_list_mso:
1b6712ab 136 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
797c636b 137 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
1b6712ab 138 sys.exit(0)
0f818663 139
59ae15a5 140 # Conflicting, missing and erroneous options
1cefca9e 141 if opts.format == 'best':
b28bac93 142 warnings.append('.\n '.join((
1cefca9e 143 '"-f best" selects the best pre-merged format which is often not the best option',
144 'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
b28bac93 145 'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
1e43a6f7 146 if opts.exec_cmd.get('before_dl') and opts.exec_before_dl_cmd:
147 parser.error('using "--exec-before-download" conflicts with "--exec before_dl:"')
59ae15a5 148 if opts.usenetrc and (opts.username is not None or opts.password is not None):
a4bc4336 149 parser.error('using .netrc conflicts with giving username/password')
59ae15a5 150 if opts.password is not None and opts.username is None:
a4bc4336 151 parser.error('account username missing\n')
1b6712ab
RA
152 if opts.ap_password is not None and opts.ap_username is None:
153 parser.error('TV Provider account username missing\n')
1a241a2d
S
154 if opts.autonumber_size is not None:
155 if opts.autonumber_size <= 0:
156 parser.error('auto number size must be positive')
157 if opts.autonumber_start is not None:
158 if opts.autonumber_start < 0:
159 parser.error('auto number start must be positive or 0')
59ae15a5 160 if opts.username is not None and opts.password is None:
a4bc4336 161 opts.password = compat_getpass('Type account password and press [Return]: ')
1b6712ab
RA
162 if opts.ap_username is not None and opts.ap_password is None:
163 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
59ae15a5
PH
164 if opts.ratelimit is not None:
165 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
166 if numeric_limit is None:
a4bc4336 167 parser.error('invalid rate limit specified')
59ae15a5 168 opts.ratelimit = numeric_limit
51d9739f 169 if opts.throttledratelimit is not None:
170 numeric_limit = FileDownloader.parse_bytes(opts.throttledratelimit)
171 if numeric_limit is None:
172 parser.error('invalid rate limit specified')
173 opts.throttledratelimit = numeric_limit
9e982f9e
JC
174 if opts.min_filesize is not None:
175 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
176 if numeric_limit is None:
a4bc4336 177 parser.error('invalid min_filesize specified')
9e982f9e
JC
178 opts.min_filesize = numeric_limit
179 if opts.max_filesize is not None:
180 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
181 if numeric_limit is None:
a4bc4336 182 parser.error('invalid max_filesize specified')
9e982f9e 183 opts.max_filesize = numeric_limit
065bc354 184 if opts.sleep_interval is not None:
185 if opts.sleep_interval < 0:
1ad6b891
S
186 parser.error('sleep interval must be positive or 0')
187 if opts.max_sleep_interval is not None:
188 if opts.max_sleep_interval < 0:
189 parser.error('max sleep interval must be positive or 0')
050afa60
JZ
190 if opts.sleep_interval is None:
191 parser.error('min sleep interval must be specified, use --min-sleep-interval')
1ad6b891
S
192 if opts.max_sleep_interval < opts.sleep_interval:
193 parser.error('max sleep interval must be greater than or equal to min sleep interval')
194 else:
195 opts.max_sleep_interval = opts.sleep_interval
1cf376f5 196 if opts.sleep_interval_subtitles is not None:
197 if opts.sleep_interval_subtitles < 0:
198 parser.error('subtitles sleep interval must be positive or 0')
199 if opts.sleep_interval_requests is not None:
200 if opts.sleep_interval_requests < 0:
201 parser.error('requests sleep interval must be positive or 0')
797c636b 202 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
87148bb7 203 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
486fb179 204 if opts.overwrites: # --yes-overwrites implies --no-continue
0c3d0f51 205 opts.continue_dl = False
4cf1e5d2 206 if opts.concurrent_fragment_downloads <= 0:
f304da8a 207 parser.error('Concurrent fragments must be positive')
f2ebc5c7 208 if opts.wait_for_video is not None:
38d79fd1 209 min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
210 if min_wait is None or (max_wait is None and '-' in opts.wait_for_video):
f2ebc5c7 211 parser.error('Invalid time range to wait')
38d79fd1 212 elif max_wait is not None and max_wait < min_wait:
213 parser.error('Minimum time range to wait must not be longer than the maximum')
f2ebc5c7 214 opts.wait_for_video = (min_wait, max_wait)
52bb437e 215
62bff2c1 216 def parse_retries(retries, name=''):
52bb437e
S
217 if retries in ('inf', 'infinite'):
218 parsed_retries = float('inf')
baeaeffc
PH
219 else:
220 try:
52bb437e 221 parsed_retries = int(retries)
baeaeffc 222 except (TypeError, ValueError):
62bff2c1 223 parser.error('invalid %sretry count specified' % name)
52bb437e
S
224 return parsed_retries
225 if opts.retries is not None:
226 opts.retries = parse_retries(opts.retries)
205a0654
EH
227 if opts.file_access_retries is not None:
228 opts.file_access_retries = parse_retries(opts.file_access_retries, 'file access ')
52bb437e 229 if opts.fragment_retries is not None:
62bff2c1 230 opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
231 if opts.extractor_retries is not None:
232 opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
59ae15a5
PH
233 if opts.buffersize is not None:
234 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
235 if numeric_buffersize is None:
a4bc4336 236 parser.error('invalid buffer size specified')
59ae15a5 237 opts.buffersize = numeric_buffersize
ba515388
S
238 if opts.http_chunk_size is not None:
239 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
240 if not numeric_chunksize:
241 parser.error('invalid http chunk size specified')
242 opts.http_chunk_size = numeric_chunksize
a19fd00c 243 if opts.playliststart <= 0:
f304da8a 244 raise parser.error('Playlist start must be positive')
a19fd00c 245 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
f304da8a 246 raise parser.error('Playlist end must be greater than playlist start')
59ae15a5 247 if opts.extractaudio:
0930b11f 248 opts.audioformat = opts.audioformat.lower()
81a23040 249 if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
a4bc4336 250 parser.error('invalid audio format specified')
59ae15a5
PH
251 if opts.audioquality:
252 opts.audioquality = opts.audioquality.strip('k').strip('K')
9af98e17 253 audioquality = int_or_none(float_or_none(opts.audioquality)) # int_or_none prevents inf, nan
254 if audioquality is None or audioquality < 0:
a4bc4336 255 parser.error('invalid audio quality specified')
7851b379 256 if opts.recodevideo is not None:
81a23040 257 opts.recodevideo = opts.recodevideo.replace(' ', '')
258 if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
259 parser.error('invalid video remux format specified')
17912249 260 if opts.remuxvideo is not None:
df692c5a 261 opts.remuxvideo = opts.remuxvideo.replace(' ', '')
81a23040 262 if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
17912249 263 parser.error('invalid video remux format specified')
e9fade72 264 if opts.convertsubtitles is not None:
81a23040 265 if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
e9fade72 266 parser.error('invalid subtitle format specified')
8fa43c73 267 if opts.convertthumbnails is not None:
81a23040 268 if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
8fa43c73 269 parser.error('invalid thumbnail format specified')
982ee69a 270 if opts.cookiesfrombrowser is not None:
f59f5ef8
MB
271 mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
272 if mobj is None:
273 parser.error(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
274 browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
275 browser_name = browser_name.lower()
276 if browser_name not in SUPPORTED_BROWSERS:
277 parser.error(f'unsupported browser specified for cookies: "{browser_name}". '
278 f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
279 if keyring is not None:
280 keyring = keyring.upper()
281 if keyring not in SUPPORTED_KEYRINGS:
282 parser.error(f'unsupported keyring specified for cookies: "{keyring}". '
283 f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
284 opts.cookiesfrombrowser = (browser_name, profile, keyring)
717216b0 285 geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
286 if geo_bypass_code is not None:
287 try:
288 GeoUtils.random_ipv4(geo_bypass_code)
289 except Exception:
290 parser.error('unsupported geo-bypass country or ip-block')
982ee69a 291
bd558525
JMF
292 if opts.date is not None:
293 date = DateRange.day(opts.date)
294 else:
295 date = DateRange(opts.dateafter, opts.datebefore)
59ae15a5 296
31654882 297 compat_opts = opts.compat_opts
53ed7066 298
19b824f6 299 def report_conflict(arg1, arg2):
300 warnings.append(f'{arg2} is ignored since {arg1} was given')
301
53ed7066 302 def _unused_compat_opt(name):
303 if name not in compat_opts:
304 return False
305 compat_opts.discard(name)
306 compat_opts.update(['*%s' % name])
307 return True
308
e4f02757 309 def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
53ed7066 310 attr = getattr(opts, opt_name)
311 if compat_name in compat_opts:
312 if attr is None:
313 setattr(opts, opt_name, not default)
314 return True
315 else:
316 if remove_compat:
317 _unused_compat_opt(compat_name)
318 return False
319 elif attr is None:
320 setattr(opts, opt_name, default)
321 return None
322
b1940459 323 set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
53ed7066 324 set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
e4f02757 325 set_default_compat('no-clean-infojson', 'clean_infojson')
dac5df5a 326 if 'no-attach-info-json' in compat_opts:
327 if opts.embed_infojson:
328 _unused_compat_opt('no-attach-info-json')
329 else:
330 opts.embed_infojson = False
53ed7066 331 if 'format-sort' in compat_opts:
332 opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
333 _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
334 _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
335 if _video_multistreams_set is False and _audio_multistreams_set is False:
336 _unused_compat_opt('multistreams')
337 outtmpl_default = opts.outtmpl.get('default')
19b824f6 338 if opts.useid:
339 if outtmpl_default is None:
340 outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
341 else:
342 report_conflict('--output', '--id')
53ed7066 343 if 'filename' in compat_opts:
344 if outtmpl_default is None:
19b824f6 345 outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
53ed7066 346 else:
347 _unused_compat_opt('filename')
348
76a264ac 349 def validate_outtmpl(tmpl, msg):
350 err = YoutubeDL.validate_outtmpl(tmpl)
351 if err:
352 parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
353
354 for k, tmpl in opts.outtmpl.items():
819e0531 355 validate_outtmpl(tmpl, f'{k} output template')
ca30f449 356 for type_, tmpl_list in opts.forceprint.items():
357 for tmpl in tmpl_list:
358 validate_outtmpl(tmpl, f'{type_} print template')
7a340e0d 359 validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
819e0531 360 for k, tmpl in opts.progress_template.items():
361 k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
362 validate_outtmpl(tmpl, f'{k} template')
76a264ac 363
de3ef3ed
PH
364 if opts.extractaudio and not opts.keepvideo and opts.format is None:
365 opts.format = 'bestaudio/best'
366
de6000d9 367 if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
a4bc4336
PH
368 parser.error('Cannot download a video and extract audio into the same'
369 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
de6000d9 370 ' template'.format(outtmpl_default))
0202b52a 371
eb8a4433 372 for f in opts.format_sort:
373 if re.match(InfoExtractor.FormatSort.regex, f) is None:
374 parser.error('invalid format sort string "%s" specified' % f)
29c7a63d 375
e9f4ccd1 376 def metadataparser_actions(f):
377 if isinstance(f, str):
378 cmd = '--parse-metadata %s' % compat_shlex_quote(f)
379 try:
380 actions = [MetadataFromFieldPP.to_action(f)]
381 except Exception as err:
382 parser.error(f'{cmd} is invalid; {err}')
383 else:
384 cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
385 actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
386
387 for action in actions:
388 try:
389 MetadataParserPP.validate_action(*action)
390 except Exception as err:
391 parser.error(f'{cmd} is invalid; {err}')
392 yield action
393
394 if opts.parse_metadata is None:
395 opts.parse_metadata = []
5bfa4862 396 if opts.metafromtitle is not None:
e9f4ccd1 397 opts.parse_metadata.append('title:%s' % opts.metafromtitle)
398 opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
5bfa4862 399
ca30f449 400 any_getting = (any(opts.forceprint.values()) or opts.dumpjson or opts.dump_single_json
401 or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail
402 or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration)
403
c0bdf32a 404 any_printing = opts.print_json
590bc6f6 405 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
525ef922 406
f0884c8b 407 # If JSON is not printed anywhere, but comments are requested, save it to file
408 printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
409 if opts.getcomments and not printing_json:
410 opts.writeinfojson = True
411
7a340e0d
NA
412 if opts.no_sponsorblock:
413 opts.sponsorblock_mark = set()
414 opts.sponsorblock_remove = set()
415 sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
416
7a340e0d
NA
417 opts.remove_chapters = opts.remove_chapters or []
418
7a340e0d
NA
419 if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
420 if opts.sponskrub:
421 if opts.remove_chapters:
422 report_conflict('--remove-chapters', '--sponskrub')
423 if opts.sponsorblock_mark:
424 report_conflict('--sponsorblock-mark', '--sponskrub')
425 if opts.sponsorblock_remove:
426 report_conflict('--sponsorblock-remove', '--sponskrub')
427 opts.sponskrub = False
72755351 428 if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
429 report_conflict('--split-chapter', '--sponskrub-cut')
430 opts.sponskrub_cut = False
431
7a340e0d
NA
432 if opts.remuxvideo and opts.recodevideo:
433 report_conflict('--recode-video', '--remux-video')
434 opts.remuxvideo = False
435
63ad4d43 436 if opts.allow_unplayable_formats:
9222c381 437 def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
438 val = getattr(opts, opt_name)
93e597ba 439 if (not allowed and val) or (allowed and not allowed(val)):
9222c381 440 report_conflict('--allow-unplayable-formats', arg)
441 setattr(opts, opt_name, default)
442
443 report_unplayable_conflict('extractaudio', '--extract-audio')
444 report_unplayable_conflict('remuxvideo', '--remux-video')
445 report_unplayable_conflict('recodevideo', '--recode-video')
446 report_unplayable_conflict('addmetadata', '--embed-metadata')
447 report_unplayable_conflict('addchapters', '--embed-chapters')
448 report_unplayable_conflict('embed_infojson', '--embed-info-json')
449 opts.embed_infojson = False
450 report_unplayable_conflict('embedsubtitles', '--embed-subs')
451 report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
452 report_unplayable_conflict('xattrs', '--xattrs')
453 report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
63ad4d43 454 opts.fixup = 'never'
9222c381 455 report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
456 report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
457 report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
63ad4d43 458 opts.sponskrub = False
459
9222c381 460 if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
461 opts.addchapters = True
462
4f026faf 463 # PostProcessors
3ae5e797 464 postprocessors = list(opts.add_postprocessors)
7a340e0d
NA
465 if sponsorblock_query:
466 postprocessors.append({
467 'key': 'SponsorBlock',
468 'categories': sponsorblock_query,
469 'api': opts.sponsorblock_api,
470 # Run this immediately after extraction is complete
471 'when': 'pre_process'
472 })
e9f4ccd1 473 if opts.parse_metadata:
e7db87f7 474 postprocessors.append({
e9f4ccd1 475 'key': 'MetadataParser',
476 'actions': opts.parse_metadata,
56d868db 477 # Run this immediately after extraction is complete
478 'when': 'pre_process'
479 })
480 if opts.convertsubtitles:
481 postprocessors.append({
482 'key': 'FFmpegSubtitlesConvertor',
483 'format': opts.convertsubtitles,
484 # Run this before the actual video download
485 'when': 'before_dl'
e7db87f7 486 })
8fa43c73 487 if opts.convertthumbnails:
488 postprocessors.append({
489 'key': 'FFmpegThumbnailsConvertor',
490 'format': opts.convertthumbnails,
491 # Run this before the actual video download
492 'when': 'before_dl'
493 })
4f026faf
PH
494 if opts.extractaudio:
495 postprocessors.append({
496 'key': 'FFmpegExtractAudio',
497 'preferredcodec': opts.audioformat,
498 'preferredquality': opts.audioquality,
499 'nopostoverwrites': opts.nopostoverwrites,
500 })
efe87a10
FS
501 if opts.remuxvideo:
502 postprocessors.append({
503 'key': 'FFmpegVideoRemuxer',
504 'preferedformat': opts.remuxvideo,
505 })
4f026faf
PH
506 if opts.recodevideo:
507 postprocessors.append({
508 'key': 'FFmpegVideoConvertor',
509 'preferedformat': opts.recodevideo,
510 })
7a340e0d 511 # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
4f026faf 512 if opts.embedsubtitles:
b51d2ae3 513 already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
4f026faf
PH
514 postprocessors.append({
515 'key': 'FFmpegEmbedSubtitle',
56d868db 516 # already_have_subtitle = True prevents the file from being deleted after embedding
cffab0ee 517 'already_have_subtitle': already_have_subtitle
4f026faf 518 })
b51d2ae3 519 if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
cffab0ee 520 opts.writesubtitles = True
521 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
522 # this was the old behaviour if only --all-sub was given.
523 if opts.allsubtitles and not opts.writeautomaticsub:
524 opts.writesubtitles = True
7a340e0d 525 # ModifyChapters must run before FFmpegMetadataPP
2d9ec704 526 remove_chapters_patterns, remove_ranges = [], []
7a340e0d 527 for regex in opts.remove_chapters:
2d9ec704 528 if regex.startswith('*'):
529 dur = list(map(parse_duration, regex[1:].split('-')))
530 if len(dur) == 2 and all(t is not None for t in dur):
531 remove_ranges.append(tuple(dur))
532 continue
b69fd25c 533 parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
7a340e0d
NA
534 try:
535 remove_chapters_patterns.append(re.compile(regex))
536 except re.error as err:
537 parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
538 if opts.remove_chapters or sponsorblock_query:
539 postprocessors.append({
540 'key': 'ModifyChapters',
541 'remove_chapters_patterns': remove_chapters_patterns,
542 'remove_sponsor_segments': opts.sponsorblock_remove,
2d9ec704 543 'remove_ranges': remove_ranges,
7a340e0d
NA
544 'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
545 'force_keyframes': opts.force_keyframes_at_cuts
546 })
547 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
548 # FFmpegExtractAudioPP as containers before conversion may not support
549 # metadata (3gp, webm, etc.)
550 # By default ffmpeg preserves metadata applicable for both
551 # source and target containers. From this point the container won't change,
552 # so metadata can be added here.
dac5df5a 553 if opts.addmetadata or opts.addchapters or opts.embed_infojson:
554 if opts.embed_infojson is None:
555 opts.embed_infojson = 'if_exists'
7a340e0d
NA
556 postprocessors.append({
557 'key': 'FFmpegMetadata',
558 'add_chapters': opts.addchapters,
559 'add_metadata': opts.addmetadata,
dac5df5a 560 'add_infojson': opts.embed_infojson,
7a340e0d 561 })
ee8dd27a 562 # Deprecated
f4e4be19 563 # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
564 # but must be below EmbedSubtitle and FFmpegMetadata
565 # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
a9e7f546 566 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
567 if opts.sponskrub is not False:
568 postprocessors.append({
569 'key': 'SponSkrub',
570 'path': opts.sponskrub_path,
571 'args': opts.sponskrub_args,
572 'cut': opts.sponskrub_cut,
573 'force': opts.sponskrub_force,
574 'ignoreerror': opts.sponskrub is None,
ee8dd27a 575 '_from_cli': True,
a9e7f546 576 })
f4e4be19 577 if opts.embedthumbnail:
f4e4be19 578 postprocessors.append({
579 'key': 'EmbedThumbnail',
56d868db 580 # already_have_thumbnail = True prevents the file from being deleted after embedding
acc0d6a4 581 'already_have_thumbnail': opts.writethumbnail
f4e4be19 582 })
acc0d6a4 583 if not opts.writethumbnail:
f4e4be19 584 opts.writethumbnail = True
80c03fa9 585 opts.outtmpl['pl_thumbnail'] = ''
72755351 586 if opts.split_chapters:
7a340e0d
NA
587 postprocessors.append({
588 'key': 'FFmpegSplitChapters',
589 'force_keyframes': opts.force_keyframes_at_cuts,
590 })
72755351 591 # XAttrMetadataPP should be run after post-processors that may change file contents
592 if opts.xattrs:
593 postprocessors.append({'key': 'XAttrMetadata'})
1e43a6f7 594 # Exec must be the last PP of each category
595 if opts.exec_before_dl_cmd:
596 opts.exec_cmd.setdefault('before_dl', opts.exec_before_dl_cmd)
597 for when, exec_cmd in opts.exec_cmd.items():
4f026faf 598 postprocessors.append({
ad3dc496 599 'key': 'Exec',
1e43a6f7 600 'exec_cmd': exec_cmd,
56d868db 601 # Run this only after the files have been moved to their final locations
1e43a6f7 602 'when': when,
4f026faf 603 })
1b77b347 604
06869367 605 def report_args_compat(arg, name):
0d1bb027 606 warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
607
b8f6bbe6 608 if 'default' in opts.external_downloader_args:
0d1bb027 609 report_args_compat('--downloader-args', 'external downloaders')
b8f6bbe6 610
45016689 611 if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
06869367 612 report_args_compat('--post-processor-args', 'post-processors')
45016689 613 opts.postprocessor_args.setdefault('sponskrub', [])
614 opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
1b77b347 615
ee8dd27a 616 def report_deprecation(val, old, new=None):
617 if not val:
618 return
619 deprecation_warnings.append(
620 f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
621 else f'{old} is deprecated and may not work as expected')
622
623 report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
624 report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
625 report_deprecation(opts.include_ads, '--include-ads')
626 # report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
627 # report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
628
df692c5a 629 final_ext = (
81a23040 630 opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
631 else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
632 else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
633 else None)
f6d7624f 634
347de493
PH
635 match_filter = (
636 None if opts.match_filter is None
637 else match_filter_func(opts.match_filter))
4f026faf 638
bdde425c 639 ydl_opts = {
59ae15a5 640 'usenetrc': opts.usenetrc,
0001fcb5 641 'netrc_location': opts.netrc_location,
59ae15a5
PH
642 'username': opts.username,
643 'password': opts.password,
83317f69 644 'twofactor': opts.twofactor,
c6c19746 645 'videopassword': opts.videopassword,
797c636b 646 'ap_mso': opts.ap_mso,
1b6712ab
RA
647 'ap_username': opts.ap_username,
648 'ap_password': opts.ap_password,
c0bdf32a 649 'quiet': (opts.quiet or any_getting or any_printing),
ad8915b7 650 'no_warnings': opts.no_warnings,
59ae15a5
PH
651 'forceurl': opts.geturl,
652 'forcetitle': opts.gettitle,
1a2adf3f 653 'forceid': opts.getid,
59ae15a5
PH
654 'forcethumbnail': opts.getthumbnail,
655 'forcedescription': opts.getdescription,
525ef922 656 'forceduration': opts.getduration,
59ae15a5
PH
657 'forcefilename': opts.getfilename,
658 'forceformat': opts.getformat,
d2a1fad9 659 'forceprint': opts.forceprint,
c0bdf32a 660 'forcejson': opts.dumpjson or opts.print_json,
63e0be34 661 'dump_single_json': opts.dump_single_json,
2d30509f 662 'force_write_download_archive': opts.force_write_download_archive,
b7b04c78 663 'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
1bdeb7be 664 'skip_download': opts.skip_download,
59ae15a5 665 'format': opts.format,
63ad4d43 666 'allow_unplayable_formats': opts.allow_unplayable_formats,
b7da73eb 667 'ignore_no_formats_error': opts.ignore_no_formats_error,
eb8a4433 668 'format_sort': opts.format_sort,
669 'format_sort_force': opts.format_sort_force,
909d24dd 670 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
671 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
e8e73840 672 'check_formats': opts.check_formats,
59ae15a5 673 'listformats': opts.listformats,
76d321f6 674 'listformats_table': opts.listformats_table,
486fb179 675 'outtmpl': opts.outtmpl,
a820dc72 676 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
0202b52a 677 'paths': opts.paths,
213c31ae 678 'autonumber_size': opts.autonumber_size,
acbb2374 679 'autonumber_start': opts.autonumber_start,
59ae15a5 680 'restrictfilenames': opts.restrictfilenames,
c2934512 681 'windowsfilenames': opts.windowsfilenames,
59ae15a5 682 'ignoreerrors': opts.ignoreerrors,
d22dec74 683 'force_generic_extractor': opts.force_generic_extractor,
59ae15a5 684 'ratelimit': opts.ratelimit,
51d9739f 685 'throttledratelimit': opts.throttledratelimit,
0c3d0f51 686 'overwrites': opts.overwrites,
52bb437e 687 'retries': opts.retries,
205a0654 688 'file_access_retries': opts.file_access_retries,
52bb437e 689 'fragment_retries': opts.fragment_retries,
62bff2c1 690 'extractor_retries': opts.extractor_retries,
9603b660 691 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
0eee52f3 692 'keep_fragments': opts.keep_fragments,
4cf1e5d2 693 'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
59ae15a5
PH
694 'buffersize': opts.buffersize,
695 'noresizebuffer': opts.noresizebuffer,
ba515388 696 'http_chunk_size': opts.http_chunk_size,
59ae15a5 697 'continuedl': opts.continue_dl,
819e0531 698 'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
5717d91a 699 'progress_with_newline': opts.progress_with_newline,
819e0531 700 'progress_template': opts.progress_template,
59ae15a5
PH
701 'playliststart': opts.playliststart,
702 'playlistend': opts.playlistend,
ff815fe6 703 'playlistreverse': opts.playlist_reverse,
75822ca7 704 'playlistrandom': opts.playlist_random,
47192f92 705 'noplaylist': opts.noplaylist,
de6000d9 706 'logtostderr': outtmpl_default == '-',
59ae15a5
PH
707 'consoletitle': opts.consoletitle,
708 'nopart': opts.nopart,
709 'updatetime': opts.updatetime,
710 'writedescription': opts.writedescription,
1fb07d10 711 'writeannotations': opts.writeannotations,
f0884c8b 712 'writeinfojson': opts.writeinfojson,
1ea24129 713 'allow_playlist_files': opts.allow_playlist_files,
75d43ca0 714 'clean_infojson': opts.clean_infojson,
06167fbb 715 'getcomments': opts.getcomments,
acc0d6a4 716 'writethumbnail': opts.writethumbnail is True,
717 'write_all_thumbnails': opts.writethumbnail == 'all',
732044af 718 'writelink': opts.writelink,
719 'writeurllink': opts.writeurllink,
720 'writewebloclink': opts.writewebloclink,
721 'writedesktoplink': opts.writedesktoplink,
59ae15a5 722 'writesubtitles': opts.writesubtitles,
b004821f 723 'writeautomaticsub': opts.writeautomaticsub,
ae608b80 724 'allsubtitles': opts.allsubtitles,
2a4093ea 725 'listsubtitles': opts.listsubtitles,
9e62bc44 726 'subtitlesformat': opts.subtitlesformat,
d6e203b3 727 'subtitleslangs': opts.subtitleslangs,
8271226a
PH
728 'matchtitle': decodeOption(opts.matchtitle),
729 'rejecttitle': decodeOption(opts.rejecttitle),
59ae15a5
PH
730 'max_downloads': opts.max_downloads,
731 'prefer_free_formats': opts.prefer_free_formats,
bdc3fd2f 732 'trim_file_name': opts.trim_file_name,
59ae15a5 733 'verbose': opts.verbose,
855703e5 734 'dump_intermediate_pages': opts.dump_intermediate_pages,
d41e6efc 735 'write_pages': opts.write_pages,
8d5d3a5d 736 'test': opts.test,
7851b379 737 'keepvideo': opts.keepvideo,
9e982f9e 738 'min_filesize': opts.min_filesize,
bd558525 739 'max_filesize': opts.max_filesize,
5fe18bdb
PH
740 'min_views': opts.min_views,
741 'max_views': opts.max_views,
11d9224e 742 'daterange': date,
7f747732 743 'cachedir': opts.cachedir,
f8061589 744 'youtube_print_sig_code': opts.youtube_print_sig_code,
8dbe9899 745 'age_limit': opts.age_limit,
17093b83 746 'download_archive': download_archive_fn,
ea6e0c2b 747 'break_on_existing': opts.break_on_existing,
8b0d7497 748 'break_on_reject': opts.break_on_reject,
b222c271 749 'break_per_url': opts.break_per_url,
26e2805c 750 'skip_playlist_after_errors': opts.skip_playlist_after_errors,
dca08720 751 'cookiefile': opts.cookiefile,
982ee69a 752 'cookiesfrombrowser': opts.cookiesfrombrowser,
dca08720 753 'nocheckcertificate': opts.no_check_certificate,
7e8c0af0 754 'prefer_insecure': opts.prefer_insecure,
c2e52508 755 'proxy': opts.proxy,
6ad14cab 756 'socket_timeout': opts.socket_timeout,
0783b09b 757 'bidi_workaround': opts.bidi_workaround,
a0ddb8a2 758 'debug_printtraffic': opts.debug_printtraffic,
76b1bd67 759 'prefer_ffmpeg': opts.prefer_ffmpeg,
7b0817e8 760 'include_ads': opts.include_ads,
04b4d394 761 'default_search': opts.default_search,
78895bd3 762 'dynamic_mpd': opts.dynamic_mpd,
5d3a0e79 763 'extractor_args': opts.extractor_args,
4919603f 764 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
78895bd3 765 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
62fec3b2 766 'encoding': opts.encoding,
057a5206 767 'extract_flat': opts.extract_flat,
adbc4ec4 768 'live_from_start': opts.live_from_start,
f2ebc5c7 769 'wait_for_video': opts.wait_for_video,
d77ab8e2 770 'mark_watched': opts.mark_watched,
34c781a2 771 'merge_output_format': opts.merge_output_format,
df692c5a 772 'final_ext': final_ext,
4f026faf 773 'postprocessors': postprocessors,
6271f1ca 774 'fixup': opts.fixup,
be4a824d 775 'source_address': opts.source_address,
58b1f00d 776 'call_home': opts.call_home,
1cf376f5 777 'sleep_interval_requests': opts.sleep_interval_requests,
5f0d813d 778 'sleep_interval': opts.sleep_interval,
065bc354 779 'max_sleep_interval': opts.max_sleep_interval,
0c9df79e 780 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
222516d9 781 'external_downloader': opts.external_downloader,
cfb56d1a 782 'list_thumbnails': opts.list_thumbnails,
c14e88f0 783 'playlist_items': opts.playlist_items,
881e6a1f 784 'xattr_set_filesize': opts.xattr_set_filesize,
347de493 785 'match_filter': match_filter,
7e5db8c9 786 'no_color': opts.no_color,
73fac4e9 787 'ffmpeg_location': opts.ffmpeg_location,
85729c51 788 'hls_prefer_native': opts.hls_prefer_native,
7d106a65 789 'hls_use_mpegts': opts.hls_use_mpegts,
310c2ed2 790 'hls_split_discontinuity': opts.hls_split_discontinuity,
46ee996e 791 'external_downloader_args': opts.external_downloader_args,
45016689 792 'postprocessor_args': opts.postprocessor_args,
91410c9b 793 'cn_verification_proxy': opts.cn_verification_proxy,
38cce791 794 'geo_verification_proxy': opts.geo_verification_proxy,
0a840f58
S
795 'geo_bypass': opts.geo_bypass,
796 'geo_bypass_country': opts.geo_bypass_country,
5f95927a 797 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
49a57e70 798 '_warnings': warnings,
ee8dd27a 799 '_deprecation_warnings': deprecation_warnings,
53ed7066 800 'compat_opts': compat_opts,
bdde425c 801 }
59ae15a5 802
bdde425c 803 with YoutubeDL(ydl_opts) as ydl:
f304da8a 804 actual_use = all_urls or opts.load_info_filename
bdde425c 805
052421ff
PH
806 # Remove cache dir
807 if opts.rm_cachedir:
a0e07d31 808 ydl.cache.remove()
052421ff 809
e5813e53 810 # Update version
811 if opts.update_self:
812 # If updater returns True, exit. Required for windows
c19bc311 813 if run_update(ydl):
e5813e53 814 if actual_use:
6b027907 815 sys.exit('ERROR: The program must exit for the update to complete')
e5813e53 816 sys.exit()
817
bdde425c 818 # Maybe do nothing
e5813e53 819 if not actual_use:
7d4111ed 820 if opts.update_self or opts.rm_cachedir:
bdde425c 821 sys.exit()
59ae15a5 822
7d4111ed 823 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
adc0ae3c
PH
824 parser.error(
825 'You must provide at least one URL.\n'
7a5c1cfe 826 'Type yt-dlp --help to see a list of all options.')
7d4111ed 827
bdde425c 828 try:
1dcc4c0c 829 if opts.load_info_filename is not None:
590bc6f6 830 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
1dcc4c0c
JMF
831 else:
832 retcode = ydl.download(all_urls)
f304da8a 833 except DownloadCancelled:
8b0d7497 834 ydl.to_screen('Aborting remaining downloads')
bdde425c 835 retcode = 101
59ae15a5 836
59ae15a5 837 sys.exit(retcode)
235b3ba4 838
a27b9e8b 839
b8ad4f02 840def main(argv=None):
59ae15a5 841 try:
b8ad4f02 842 _real_main(argv)
59ae15a5
PH
843 except DownloadError:
844 sys.exit(1)
aa9369a2 845 except SameFileError as e:
846 sys.exit(f'ERROR: {e}')
59ae15a5 847 except KeyboardInterrupt:
a4bc4336 848 sys.exit('\nERROR: Interrupted by user')
aa9369a2 849 except BrokenPipeError as e:
cc3fa8d3 850 # https://docs.python.org/3/library/signal.html#note-on-sigpipe
851 devnull = os.open(os.devnull, os.O_WRONLY)
852 os.dup2(devnull, sys.stdout.fileno())
aa9369a2 853 sys.exit(f'\nERROR: {e}')
2bad0e5d 854
582be358 855
2bad0e5d 856__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']