]> jfr.im git - yt-dlp.git/blob - yt_dlp/__init__.py
Add option `--file-access-retries` (#2066)
[yt-dlp.git] / 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
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 write_string,
45 )
46 from .update import run_update
47 from .downloader import (
48 FileDownloader,
49 )
50 from .extractor import gen_extractors, list_extractors
51 from .extractor.common import InfoExtractor
52 from .extractor.adobepass import MSO_INFO
53 from .postprocessor import (
54 FFmpegExtractAudioPP,
55 FFmpegSubtitlesConvertorPP,
56 FFmpegThumbnailsConvertorPP,
57 FFmpegVideoConvertorPP,
58 FFmpegVideoRemuxerPP,
59 MetadataFromFieldPP,
60 MetadataParserPP,
61 )
62 from .YoutubeDL import YoutubeDL
63
64
65 def _real_main(argv=None):
66 # Compatibility fixes for Windows
67 if sys.platform == 'win32':
68 # https://github.com/ytdl-org/youtube-dl/issues/820
69 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
70
71 workaround_optparse_bug9161()
72
73 setproctitle('yt-dlp')
74
75 parser, opts, args = parseOpts(argv)
76 warnings, deprecation_warnings = [], []
77
78 # Set user agent
79 if opts.user_agent is not None:
80 std_headers['User-Agent'] = opts.user_agent
81
82 # Set referer
83 if opts.referer is not None:
84 std_headers['Referer'] = opts.referer
85
86 # Custom HTTP headers
87 std_headers.update(opts.headers)
88
89 # Dump user agent
90 if opts.dump_user_agent:
91 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
92 sys.exit(0)
93
94 # Batch file verification
95 batch_urls = []
96 if opts.batchfile is not None:
97 try:
98 if opts.batchfile == '-':
99 write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
100 'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
101 batchfd = sys.stdin
102 else:
103 batchfd = io.open(
104 expand_path(opts.batchfile),
105 'r', encoding='utf-8', errors='ignore')
106 batch_urls = read_batch_urls(batchfd)
107 if opts.verbose:
108 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
109 except IOError:
110 sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
111 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
112 _enc = preferredencoding()
113 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
114
115 if opts.list_extractors:
116 for ie in list_extractors(opts.age_limit):
117 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
118 matchedUrls = [url for url in all_urls if ie.suitable(url)]
119 for mu in matchedUrls:
120 write_string(' ' + mu + '\n', out=sys.stdout)
121 sys.exit(0)
122 if opts.list_extractor_descriptions:
123 for ie in list_extractors(opts.age_limit):
124 if not ie.working():
125 continue
126 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
127 if desc is False:
128 continue
129 if getattr(ie, 'SEARCH_KEY', None) is not None:
130 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
131 _COUNTS = ('', '5', '10', 'all')
132 desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
133 write_string(desc + '\n', out=sys.stdout)
134 sys.exit(0)
135 if opts.ap_list_mso:
136 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
137 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
138 sys.exit(0)
139
140 # Conflicting, missing and erroneous options
141 if opts.format == 'best':
142 warnings.append('.\n '.join(
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',
145 'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning'))
146 if opts.usenetrc and (opts.username is not None or opts.password is not None):
147 parser.error('using .netrc conflicts with giving username/password')
148 if opts.password is not None and opts.username is None:
149 parser.error('account username missing\n')
150 if opts.ap_password is not None and opts.ap_username is None:
151 parser.error('TV Provider account username missing\n')
152 if opts.autonumber_size is not None:
153 if opts.autonumber_size <= 0:
154 parser.error('auto number size must be positive')
155 if opts.autonumber_start is not None:
156 if opts.autonumber_start < 0:
157 parser.error('auto number start must be positive or 0')
158 if opts.username is not None and opts.password is None:
159 opts.password = compat_getpass('Type account password and press [Return]: ')
160 if opts.ap_username is not None and opts.ap_password is None:
161 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
162 if opts.ratelimit is not None:
163 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
164 if numeric_limit is None:
165 parser.error('invalid rate limit specified')
166 opts.ratelimit = numeric_limit
167 if opts.throttledratelimit is not None:
168 numeric_limit = FileDownloader.parse_bytes(opts.throttledratelimit)
169 if numeric_limit is None:
170 parser.error('invalid rate limit specified')
171 opts.throttledratelimit = numeric_limit
172 if opts.min_filesize is not None:
173 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
174 if numeric_limit is None:
175 parser.error('invalid min_filesize specified')
176 opts.min_filesize = numeric_limit
177 if opts.max_filesize is not None:
178 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
179 if numeric_limit is None:
180 parser.error('invalid max_filesize specified')
181 opts.max_filesize = numeric_limit
182 if opts.sleep_interval is not None:
183 if opts.sleep_interval < 0:
184 parser.error('sleep interval must be positive or 0')
185 if opts.max_sleep_interval is not None:
186 if opts.max_sleep_interval < 0:
187 parser.error('max sleep interval must be positive or 0')
188 if opts.sleep_interval is None:
189 parser.error('min sleep interval must be specified, use --min-sleep-interval')
190 if opts.max_sleep_interval < opts.sleep_interval:
191 parser.error('max sleep interval must be greater than or equal to min sleep interval')
192 else:
193 opts.max_sleep_interval = opts.sleep_interval
194 if opts.sleep_interval_subtitles is not None:
195 if opts.sleep_interval_subtitles < 0:
196 parser.error('subtitles sleep interval must be positive or 0')
197 if opts.sleep_interval_requests is not None:
198 if opts.sleep_interval_requests < 0:
199 parser.error('requests sleep interval must be positive or 0')
200 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
201 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
202 if opts.overwrites: # --yes-overwrites implies --no-continue
203 opts.continue_dl = False
204 if opts.concurrent_fragment_downloads <= 0:
205 parser.error('Concurrent fragments must be positive')
206 if opts.wait_for_video is not None:
207 min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
208 if min_wait is None or (max_wait is None and '-' in opts.wait_for_video):
209 parser.error('Invalid time range to wait')
210 elif max_wait is not None and max_wait < min_wait:
211 parser.error('Minimum time range to wait must not be longer than the maximum')
212 opts.wait_for_video = (min_wait, max_wait)
213
214 def parse_retries(retries, name=''):
215 if retries in ('inf', 'infinite'):
216 parsed_retries = float('inf')
217 else:
218 try:
219 parsed_retries = int(retries)
220 except (TypeError, ValueError):
221 parser.error('invalid %sretry count specified' % name)
222 return parsed_retries
223 if opts.retries is not None:
224 opts.retries = parse_retries(opts.retries)
225 if opts.file_access_retries is not None:
226 opts.file_access_retries = parse_retries(opts.file_access_retries, 'file access ')
227 if opts.fragment_retries is not None:
228 opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
229 if opts.extractor_retries is not None:
230 opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
231 if opts.buffersize is not None:
232 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
233 if numeric_buffersize is None:
234 parser.error('invalid buffer size specified')
235 opts.buffersize = numeric_buffersize
236 if opts.http_chunk_size is not None:
237 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
238 if not numeric_chunksize:
239 parser.error('invalid http chunk size specified')
240 opts.http_chunk_size = numeric_chunksize
241 if opts.playliststart <= 0:
242 raise parser.error('Playlist start must be positive')
243 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
244 raise parser.error('Playlist end must be greater than playlist start')
245 if opts.extractaudio:
246 opts.audioformat = opts.audioformat.lower()
247 if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
248 parser.error('invalid audio format specified')
249 if opts.audioquality:
250 opts.audioquality = opts.audioquality.strip('k').strip('K')
251 audioquality = int_or_none(float_or_none(opts.audioquality)) # int_or_none prevents inf, nan
252 if audioquality is None or audioquality < 0:
253 parser.error('invalid audio quality specified')
254 if opts.recodevideo is not None:
255 opts.recodevideo = opts.recodevideo.replace(' ', '')
256 if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
257 parser.error('invalid video remux format specified')
258 if opts.remuxvideo is not None:
259 opts.remuxvideo = opts.remuxvideo.replace(' ', '')
260 if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
261 parser.error('invalid video remux format specified')
262 if opts.convertsubtitles is not None:
263 if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
264 parser.error('invalid subtitle format specified')
265 if opts.convertthumbnails is not None:
266 if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
267 parser.error('invalid thumbnail format specified')
268 if opts.cookiesfrombrowser is not None:
269 opts.cookiesfrombrowser = [
270 part.strip() or None for part in opts.cookiesfrombrowser.split(':', 1)]
271 if opts.cookiesfrombrowser[0].lower() not in SUPPORTED_BROWSERS:
272 parser.error('unsupported browser specified for cookies')
273 geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
274 if geo_bypass_code is not None:
275 try:
276 GeoUtils.random_ipv4(geo_bypass_code)
277 except Exception:
278 parser.error('unsupported geo-bypass country or ip-block')
279
280 if opts.date is not None:
281 date = DateRange.day(opts.date)
282 else:
283 date = DateRange(opts.dateafter, opts.datebefore)
284
285 compat_opts = opts.compat_opts
286
287 def report_conflict(arg1, arg2):
288 warnings.append(f'{arg2} is ignored since {arg1} was given')
289
290 def _unused_compat_opt(name):
291 if name not in compat_opts:
292 return False
293 compat_opts.discard(name)
294 compat_opts.update(['*%s' % name])
295 return True
296
297 def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
298 attr = getattr(opts, opt_name)
299 if compat_name in compat_opts:
300 if attr is None:
301 setattr(opts, opt_name, not default)
302 return True
303 else:
304 if remove_compat:
305 _unused_compat_opt(compat_name)
306 return False
307 elif attr is None:
308 setattr(opts, opt_name, default)
309 return None
310
311 set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
312 set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
313 set_default_compat('no-clean-infojson', 'clean_infojson')
314 if 'no-attach-info-json' in compat_opts:
315 if opts.embed_infojson:
316 _unused_compat_opt('no-attach-info-json')
317 else:
318 opts.embed_infojson = False
319 if 'format-sort' in compat_opts:
320 opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
321 _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
322 _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
323 if _video_multistreams_set is False and _audio_multistreams_set is False:
324 _unused_compat_opt('multistreams')
325 outtmpl_default = opts.outtmpl.get('default')
326 if opts.useid:
327 if outtmpl_default is None:
328 outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
329 else:
330 report_conflict('--output', '--id')
331 if 'filename' in compat_opts:
332 if outtmpl_default is None:
333 outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
334 else:
335 _unused_compat_opt('filename')
336
337 def validate_outtmpl(tmpl, msg):
338 err = YoutubeDL.validate_outtmpl(tmpl)
339 if err:
340 parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
341
342 for k, tmpl in opts.outtmpl.items():
343 validate_outtmpl(tmpl, f'{k} output template')
344 opts.forceprint = opts.forceprint or []
345 for tmpl in opts.forceprint or []:
346 validate_outtmpl(tmpl, 'print template')
347 validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
348 for k, tmpl in opts.progress_template.items():
349 k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
350 validate_outtmpl(tmpl, f'{k} template')
351
352 if opts.extractaudio and not opts.keepvideo and opts.format is None:
353 opts.format = 'bestaudio/best'
354
355 if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
356 parser.error('Cannot download a video and extract audio into the same'
357 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
358 ' template'.format(outtmpl_default))
359
360 for f in opts.format_sort:
361 if re.match(InfoExtractor.FormatSort.regex, f) is None:
362 parser.error('invalid format sort string "%s" specified' % f)
363
364 def metadataparser_actions(f):
365 if isinstance(f, str):
366 cmd = '--parse-metadata %s' % compat_shlex_quote(f)
367 try:
368 actions = [MetadataFromFieldPP.to_action(f)]
369 except Exception as err:
370 parser.error(f'{cmd} is invalid; {err}')
371 else:
372 cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
373 actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
374
375 for action in actions:
376 try:
377 MetadataParserPP.validate_action(*action)
378 except Exception as err:
379 parser.error(f'{cmd} is invalid; {err}')
380 yield action
381
382 if opts.parse_metadata is None:
383 opts.parse_metadata = []
384 if opts.metafromtitle is not None:
385 opts.parse_metadata.append('title:%s' % opts.metafromtitle)
386 opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
387
388 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
389 any_printing = opts.print_json
390 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
391
392 # If JSON is not printed anywhere, but comments are requested, save it to file
393 printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
394 if opts.getcomments and not printing_json:
395 opts.writeinfojson = True
396
397 if opts.no_sponsorblock:
398 opts.sponsorblock_mark = set()
399 opts.sponsorblock_remove = set()
400 sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
401
402 opts.remove_chapters = opts.remove_chapters or []
403
404 if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
405 if opts.sponskrub:
406 if opts.remove_chapters:
407 report_conflict('--remove-chapters', '--sponskrub')
408 if opts.sponsorblock_mark:
409 report_conflict('--sponsorblock-mark', '--sponskrub')
410 if opts.sponsorblock_remove:
411 report_conflict('--sponsorblock-remove', '--sponskrub')
412 opts.sponskrub = False
413 if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
414 report_conflict('--split-chapter', '--sponskrub-cut')
415 opts.sponskrub_cut = False
416
417 if opts.remuxvideo and opts.recodevideo:
418 report_conflict('--recode-video', '--remux-video')
419 opts.remuxvideo = False
420
421 if opts.allow_unplayable_formats:
422 def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
423 val = getattr(opts, opt_name)
424 if (not allowed and val) or (allowed and not allowed(val)):
425 report_conflict('--allow-unplayable-formats', arg)
426 setattr(opts, opt_name, default)
427
428 report_unplayable_conflict('extractaudio', '--extract-audio')
429 report_unplayable_conflict('remuxvideo', '--remux-video')
430 report_unplayable_conflict('recodevideo', '--recode-video')
431 report_unplayable_conflict('addmetadata', '--embed-metadata')
432 report_unplayable_conflict('addchapters', '--embed-chapters')
433 report_unplayable_conflict('embed_infojson', '--embed-info-json')
434 opts.embed_infojson = False
435 report_unplayable_conflict('embedsubtitles', '--embed-subs')
436 report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
437 report_unplayable_conflict('xattrs', '--xattrs')
438 report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
439 opts.fixup = 'never'
440 report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
441 report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
442 report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
443 opts.sponskrub = False
444
445 if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
446 opts.addchapters = True
447
448 # PostProcessors
449 postprocessors = list(opts.add_postprocessors)
450 if sponsorblock_query:
451 postprocessors.append({
452 'key': 'SponsorBlock',
453 'categories': sponsorblock_query,
454 'api': opts.sponsorblock_api,
455 # Run this immediately after extraction is complete
456 'when': 'pre_process'
457 })
458 if opts.parse_metadata:
459 postprocessors.append({
460 'key': 'MetadataParser',
461 'actions': opts.parse_metadata,
462 # Run this immediately after extraction is complete
463 'when': 'pre_process'
464 })
465 if opts.convertsubtitles:
466 postprocessors.append({
467 'key': 'FFmpegSubtitlesConvertor',
468 'format': opts.convertsubtitles,
469 # Run this before the actual video download
470 'when': 'before_dl'
471 })
472 if opts.convertthumbnails:
473 postprocessors.append({
474 'key': 'FFmpegThumbnailsConvertor',
475 'format': opts.convertthumbnails,
476 # Run this before the actual video download
477 'when': 'before_dl'
478 })
479 # Must be after all other before_dl
480 if opts.exec_before_dl_cmd:
481 postprocessors.append({
482 'key': 'Exec',
483 'exec_cmd': opts.exec_before_dl_cmd,
484 'when': 'before_dl'
485 })
486 if opts.extractaudio:
487 postprocessors.append({
488 'key': 'FFmpegExtractAudio',
489 'preferredcodec': opts.audioformat,
490 'preferredquality': opts.audioquality,
491 'nopostoverwrites': opts.nopostoverwrites,
492 })
493 if opts.remuxvideo:
494 postprocessors.append({
495 'key': 'FFmpegVideoRemuxer',
496 'preferedformat': opts.remuxvideo,
497 })
498 if opts.recodevideo:
499 postprocessors.append({
500 'key': 'FFmpegVideoConvertor',
501 'preferedformat': opts.recodevideo,
502 })
503 # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
504 if opts.embedsubtitles:
505 already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
506 postprocessors.append({
507 'key': 'FFmpegEmbedSubtitle',
508 # already_have_subtitle = True prevents the file from being deleted after embedding
509 'already_have_subtitle': already_have_subtitle
510 })
511 if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
512 opts.writesubtitles = True
513 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
514 # this was the old behaviour if only --all-sub was given.
515 if opts.allsubtitles and not opts.writeautomaticsub:
516 opts.writesubtitles = True
517 # ModifyChapters must run before FFmpegMetadataPP
518 remove_chapters_patterns, remove_ranges = [], []
519 for regex in opts.remove_chapters:
520 if regex.startswith('*'):
521 dur = list(map(parse_duration, regex[1:].split('-')))
522 if len(dur) == 2 and all(t is not None for t in dur):
523 remove_ranges.append(tuple(dur))
524 continue
525 parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
526 try:
527 remove_chapters_patterns.append(re.compile(regex))
528 except re.error as err:
529 parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
530 if opts.remove_chapters or sponsorblock_query:
531 postprocessors.append({
532 'key': 'ModifyChapters',
533 'remove_chapters_patterns': remove_chapters_patterns,
534 'remove_sponsor_segments': opts.sponsorblock_remove,
535 'remove_ranges': remove_ranges,
536 'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
537 'force_keyframes': opts.force_keyframes_at_cuts
538 })
539 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
540 # FFmpegExtractAudioPP as containers before conversion may not support
541 # metadata (3gp, webm, etc.)
542 # By default ffmpeg preserves metadata applicable for both
543 # source and target containers. From this point the container won't change,
544 # so metadata can be added here.
545 if opts.addmetadata or opts.addchapters or opts.embed_infojson:
546 if opts.embed_infojson is None:
547 opts.embed_infojson = 'if_exists'
548 postprocessors.append({
549 'key': 'FFmpegMetadata',
550 'add_chapters': opts.addchapters,
551 'add_metadata': opts.addmetadata,
552 'add_infojson': opts.embed_infojson,
553 })
554 # Deprecated
555 # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
556 # but must be below EmbedSubtitle and FFmpegMetadata
557 # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
558 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
559 if opts.sponskrub is not False:
560 postprocessors.append({
561 'key': 'SponSkrub',
562 'path': opts.sponskrub_path,
563 'args': opts.sponskrub_args,
564 'cut': opts.sponskrub_cut,
565 'force': opts.sponskrub_force,
566 'ignoreerror': opts.sponskrub is None,
567 '_from_cli': True,
568 })
569 if opts.embedthumbnail:
570 postprocessors.append({
571 'key': 'EmbedThumbnail',
572 # already_have_thumbnail = True prevents the file from being deleted after embedding
573 'already_have_thumbnail': opts.writethumbnail
574 })
575 if not opts.writethumbnail:
576 opts.writethumbnail = True
577 opts.outtmpl['pl_thumbnail'] = ''
578 if opts.split_chapters:
579 postprocessors.append({
580 'key': 'FFmpegSplitChapters',
581 'force_keyframes': opts.force_keyframes_at_cuts,
582 })
583 # XAttrMetadataPP should be run after post-processors that may change file contents
584 if opts.xattrs:
585 postprocessors.append({'key': 'XAttrMetadata'})
586 # Exec must be the last PP
587 if opts.exec_cmd:
588 postprocessors.append({
589 'key': 'Exec',
590 'exec_cmd': opts.exec_cmd,
591 # Run this only after the files have been moved to their final locations
592 'when': 'after_move'
593 })
594
595 def report_args_compat(arg, name):
596 warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
597
598 if 'default' in opts.external_downloader_args:
599 report_args_compat('--downloader-args', 'external downloaders')
600
601 if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
602 report_args_compat('--post-processor-args', 'post-processors')
603 opts.postprocessor_args.setdefault('sponskrub', [])
604 opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
605
606 def report_deprecation(val, old, new=None):
607 if not val:
608 return
609 deprecation_warnings.append(
610 f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
611 else f'{old} is deprecated and may not work as expected')
612
613 report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
614 report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
615 report_deprecation(opts.include_ads, '--include-ads')
616 # report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
617 # report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
618
619 final_ext = (
620 opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
621 else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
622 else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
623 else None)
624
625 match_filter = (
626 None if opts.match_filter is None
627 else match_filter_func(opts.match_filter))
628
629 ydl_opts = {
630 'usenetrc': opts.usenetrc,
631 'netrc_location': opts.netrc_location,
632 'username': opts.username,
633 'password': opts.password,
634 'twofactor': opts.twofactor,
635 'videopassword': opts.videopassword,
636 'ap_mso': opts.ap_mso,
637 'ap_username': opts.ap_username,
638 'ap_password': opts.ap_password,
639 'quiet': (opts.quiet or any_getting or any_printing),
640 'no_warnings': opts.no_warnings,
641 'forceurl': opts.geturl,
642 'forcetitle': opts.gettitle,
643 'forceid': opts.getid,
644 'forcethumbnail': opts.getthumbnail,
645 'forcedescription': opts.getdescription,
646 'forceduration': opts.getduration,
647 'forcefilename': opts.getfilename,
648 'forceformat': opts.getformat,
649 'forceprint': opts.forceprint,
650 'forcejson': opts.dumpjson or opts.print_json,
651 'dump_single_json': opts.dump_single_json,
652 'force_write_download_archive': opts.force_write_download_archive,
653 'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
654 'skip_download': opts.skip_download,
655 'format': opts.format,
656 'allow_unplayable_formats': opts.allow_unplayable_formats,
657 'ignore_no_formats_error': opts.ignore_no_formats_error,
658 'format_sort': opts.format_sort,
659 'format_sort_force': opts.format_sort_force,
660 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
661 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
662 'check_formats': opts.check_formats,
663 'listformats': opts.listformats,
664 'listformats_table': opts.listformats_table,
665 'outtmpl': opts.outtmpl,
666 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
667 'paths': opts.paths,
668 'autonumber_size': opts.autonumber_size,
669 'autonumber_start': opts.autonumber_start,
670 'restrictfilenames': opts.restrictfilenames,
671 'windowsfilenames': opts.windowsfilenames,
672 'ignoreerrors': opts.ignoreerrors,
673 'force_generic_extractor': opts.force_generic_extractor,
674 'ratelimit': opts.ratelimit,
675 'throttledratelimit': opts.throttledratelimit,
676 'overwrites': opts.overwrites,
677 'retries': opts.retries,
678 'file_access_retries': opts.file_access_retries,
679 'fragment_retries': opts.fragment_retries,
680 'extractor_retries': opts.extractor_retries,
681 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
682 'keep_fragments': opts.keep_fragments,
683 'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
684 'buffersize': opts.buffersize,
685 'noresizebuffer': opts.noresizebuffer,
686 'http_chunk_size': opts.http_chunk_size,
687 'continuedl': opts.continue_dl,
688 'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
689 'progress_with_newline': opts.progress_with_newline,
690 'progress_template': opts.progress_template,
691 'playliststart': opts.playliststart,
692 'playlistend': opts.playlistend,
693 'playlistreverse': opts.playlist_reverse,
694 'playlistrandom': opts.playlist_random,
695 'noplaylist': opts.noplaylist,
696 'logtostderr': outtmpl_default == '-',
697 'consoletitle': opts.consoletitle,
698 'nopart': opts.nopart,
699 'updatetime': opts.updatetime,
700 'writedescription': opts.writedescription,
701 'writeannotations': opts.writeannotations,
702 'writeinfojson': opts.writeinfojson,
703 'allow_playlist_files': opts.allow_playlist_files,
704 'clean_infojson': opts.clean_infojson,
705 'getcomments': opts.getcomments,
706 'writethumbnail': opts.writethumbnail is True,
707 'write_all_thumbnails': opts.writethumbnail == 'all',
708 'writelink': opts.writelink,
709 'writeurllink': opts.writeurllink,
710 'writewebloclink': opts.writewebloclink,
711 'writedesktoplink': opts.writedesktoplink,
712 'writesubtitles': opts.writesubtitles,
713 'writeautomaticsub': opts.writeautomaticsub,
714 'allsubtitles': opts.allsubtitles,
715 'listsubtitles': opts.listsubtitles,
716 'subtitlesformat': opts.subtitlesformat,
717 'subtitleslangs': opts.subtitleslangs,
718 'matchtitle': decodeOption(opts.matchtitle),
719 'rejecttitle': decodeOption(opts.rejecttitle),
720 'max_downloads': opts.max_downloads,
721 'prefer_free_formats': opts.prefer_free_formats,
722 'trim_file_name': opts.trim_file_name,
723 'verbose': opts.verbose,
724 'dump_intermediate_pages': opts.dump_intermediate_pages,
725 'write_pages': opts.write_pages,
726 'test': opts.test,
727 'keepvideo': opts.keepvideo,
728 'min_filesize': opts.min_filesize,
729 'max_filesize': opts.max_filesize,
730 'min_views': opts.min_views,
731 'max_views': opts.max_views,
732 'daterange': date,
733 'cachedir': opts.cachedir,
734 'youtube_print_sig_code': opts.youtube_print_sig_code,
735 'age_limit': opts.age_limit,
736 'download_archive': download_archive_fn,
737 'break_on_existing': opts.break_on_existing,
738 'break_on_reject': opts.break_on_reject,
739 'break_per_url': opts.break_per_url,
740 'skip_playlist_after_errors': opts.skip_playlist_after_errors,
741 'cookiefile': opts.cookiefile,
742 'cookiesfrombrowser': opts.cookiesfrombrowser,
743 'nocheckcertificate': opts.no_check_certificate,
744 'prefer_insecure': opts.prefer_insecure,
745 'proxy': opts.proxy,
746 'socket_timeout': opts.socket_timeout,
747 'bidi_workaround': opts.bidi_workaround,
748 'debug_printtraffic': opts.debug_printtraffic,
749 'prefer_ffmpeg': opts.prefer_ffmpeg,
750 'include_ads': opts.include_ads,
751 'default_search': opts.default_search,
752 'dynamic_mpd': opts.dynamic_mpd,
753 'extractor_args': opts.extractor_args,
754 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
755 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
756 'encoding': opts.encoding,
757 'extract_flat': opts.extract_flat,
758 'live_from_start': opts.live_from_start,
759 'wait_for_video': opts.wait_for_video,
760 'mark_watched': opts.mark_watched,
761 'merge_output_format': opts.merge_output_format,
762 'final_ext': final_ext,
763 'postprocessors': postprocessors,
764 'fixup': opts.fixup,
765 'source_address': opts.source_address,
766 'call_home': opts.call_home,
767 'sleep_interval_requests': opts.sleep_interval_requests,
768 'sleep_interval': opts.sleep_interval,
769 'max_sleep_interval': opts.max_sleep_interval,
770 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
771 'external_downloader': opts.external_downloader,
772 'list_thumbnails': opts.list_thumbnails,
773 'playlist_items': opts.playlist_items,
774 'xattr_set_filesize': opts.xattr_set_filesize,
775 'match_filter': match_filter,
776 'no_color': opts.no_color,
777 'ffmpeg_location': opts.ffmpeg_location,
778 'hls_prefer_native': opts.hls_prefer_native,
779 'hls_use_mpegts': opts.hls_use_mpegts,
780 'hls_split_discontinuity': opts.hls_split_discontinuity,
781 'external_downloader_args': opts.external_downloader_args,
782 'postprocessor_args': opts.postprocessor_args,
783 'cn_verification_proxy': opts.cn_verification_proxy,
784 'geo_verification_proxy': opts.geo_verification_proxy,
785 'geo_bypass': opts.geo_bypass,
786 'geo_bypass_country': opts.geo_bypass_country,
787 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
788 '_warnings': warnings,
789 '_deprecation_warnings': deprecation_warnings,
790 'compat_opts': compat_opts,
791 }
792
793 with YoutubeDL(ydl_opts) as ydl:
794 actual_use = all_urls or opts.load_info_filename
795
796 # Remove cache dir
797 if opts.rm_cachedir:
798 ydl.cache.remove()
799
800 # Update version
801 if opts.update_self:
802 # If updater returns True, exit. Required for windows
803 if run_update(ydl):
804 if actual_use:
805 sys.exit('ERROR: The program must exit for the update to complete')
806 sys.exit()
807
808 # Maybe do nothing
809 if not actual_use:
810 if opts.update_self or opts.rm_cachedir:
811 sys.exit()
812
813 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
814 parser.error(
815 'You must provide at least one URL.\n'
816 'Type yt-dlp --help to see a list of all options.')
817
818 try:
819 if opts.load_info_filename is not None:
820 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
821 else:
822 retcode = ydl.download(all_urls)
823 except DownloadCancelled:
824 ydl.to_screen('Aborting remaining downloads')
825 retcode = 101
826
827 sys.exit(retcode)
828
829
830 def main(argv=None):
831 try:
832 _real_main(argv)
833 except DownloadError:
834 sys.exit(1)
835 except SameFileError as e:
836 sys.exit(f'ERROR: {e}')
837 except KeyboardInterrupt:
838 sys.exit('\nERROR: Interrupted by user')
839 except BrokenPipeError as e:
840 # https://docs.python.org/3/library/signal.html#note-on-sigpipe
841 devnull = os.open(os.devnull, os.O_WRONLY)
842 os.dup2(devnull, sys.stdout.fileno())
843 sys.exit(f'\nERROR: {e}')
844
845
846 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']