]> jfr.im git - yt-dlp.git/blob - yt_dlp/__init__.py
[cleanup] Misc
[yt-dlp.git] / yt_dlp / __init__.py
1 #!/usr/bin/env python3
2 f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp' # noqa: F541
3
4 __license__ = 'Public Domain'
5
6 import itertools
7 import optparse
8 import os
9 import re
10 import sys
11
12 from .compat import compat_getpass, compat_os_name, compat_shlex_quote
13 from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
14 from .downloader import FileDownloader
15 from .extractor import GenericIE, list_extractor_classes
16 from .extractor.adobepass import MSO_INFO
17 from .extractor.common import InfoExtractor
18 from .options import parseOpts
19 from .postprocessor import (
20 FFmpegExtractAudioPP,
21 FFmpegSubtitlesConvertorPP,
22 FFmpegThumbnailsConvertorPP,
23 FFmpegVideoConvertorPP,
24 FFmpegVideoRemuxerPP,
25 MetadataFromFieldPP,
26 MetadataParserPP,
27 )
28 from .update import run_update
29 from .utils import (
30 NO_DEFAULT,
31 POSTPROCESS_WHEN,
32 DateRange,
33 DownloadCancelled,
34 DownloadError,
35 GeoUtils,
36 SameFileError,
37 decodeOption,
38 expand_path,
39 float_or_none,
40 int_or_none,
41 match_filter_func,
42 parse_duration,
43 preferredencoding,
44 read_batch_urls,
45 render_table,
46 setproctitle,
47 std_headers,
48 traverse_obj,
49 variadic,
50 write_string,
51 )
52 from .YoutubeDL import YoutubeDL
53
54
55 def _exit(status=0, *args):
56 for msg in args:
57 sys.stderr.write(msg)
58 raise SystemExit(status)
59
60
61 def get_urls(urls, batchfile, verbose):
62 # Batch file verification
63 batch_urls = []
64 if batchfile is not None:
65 try:
66 if batchfile == '-':
67 write_string('Reading URLs from stdin - EOF (%s) to end:\n' % (
68 'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'))
69 batchfd = sys.stdin
70 else:
71 batchfd = open(
72 expand_path(batchfile), encoding='utf-8', errors='ignore')
73 batch_urls = read_batch_urls(batchfd)
74 if verbose:
75 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
76 except OSError:
77 _exit(f'ERROR: batch file {batchfile} could not be read')
78 _enc = preferredencoding()
79 return [
80 url.strip().decode(_enc, 'ignore') if isinstance(url, bytes) else url.strip()
81 for url in batch_urls + urls]
82
83
84 def print_extractor_information(opts, urls):
85 out = ''
86 if opts.list_extractors:
87 urls = dict.fromkeys(urls, False)
88 for ie in list_extractor_classes(opts.age_limit):
89 out += ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n'
90 if ie == GenericIE:
91 matched_urls = [url for url, matched in urls.items() if not matched]
92 else:
93 matched_urls = tuple(filter(ie.suitable, urls.keys()))
94 urls.update(dict.fromkeys(matched_urls, True))
95 out += ''.join(f' {url}\n' for url in matched_urls)
96 elif opts.list_extractor_descriptions:
97 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
98 out = '\n'.join(
99 ie.description(markdown=False, search_examples=_SEARCHES)
100 for ie in list_extractor_classes(opts.age_limit) if ie.working() and ie.IE_DESC is not False)
101 elif opts.ap_list_mso:
102 out = 'Supported TV Providers:\n%s\n' % render_table(
103 ['mso', 'mso name'],
104 [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()])
105 else:
106 return False
107 write_string(out, out=sys.stdout)
108 return True
109
110
111 def set_compat_opts(opts):
112 def _unused_compat_opt(name):
113 if name not in opts.compat_opts:
114 return False
115 opts.compat_opts.discard(name)
116 opts.compat_opts.update(['*%s' % name])
117 return True
118
119 def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
120 attr = getattr(opts, opt_name)
121 if compat_name in opts.compat_opts:
122 if attr is None:
123 setattr(opts, opt_name, not default)
124 return True
125 else:
126 if remove_compat:
127 _unused_compat_opt(compat_name)
128 return False
129 elif attr is None:
130 setattr(opts, opt_name, default)
131 return None
132
133 set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
134 set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
135 set_default_compat('no-clean-infojson', 'clean_infojson')
136 if 'no-attach-info-json' in opts.compat_opts:
137 if opts.embed_infojson:
138 _unused_compat_opt('no-attach-info-json')
139 else:
140 opts.embed_infojson = False
141 if 'format-sort' in opts.compat_opts:
142 opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
143 _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
144 _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
145 if _video_multistreams_set is False and _audio_multistreams_set is False:
146 _unused_compat_opt('multistreams')
147 if 'filename' in opts.compat_opts:
148 if opts.outtmpl.get('default') is None:
149 opts.outtmpl.update({'default': '%(title)s-%(id)s.%(ext)s'})
150 else:
151 _unused_compat_opt('filename')
152
153
154 def validate_options(opts):
155 def validate(cndn, name, value=None, msg=None):
156 if cndn:
157 return True
158 raise ValueError((msg or 'invalid {name} "{value}" given').format(name=name, value=value))
159
160 def validate_in(name, value, items, msg=None):
161 return validate(value is None or value in items, name, value, msg)
162
163 def validate_regex(name, value, regex):
164 return validate(value is None or re.match(regex, value), name, value)
165
166 def validate_positive(name, value, strict=False):
167 return validate(value is None or value > 0 or (not strict and value == 0),
168 name, value, '{name} "{value}" must be positive' + ('' if strict else ' or 0'))
169
170 def validate_minmax(min_val, max_val, min_name, max_name=None):
171 if max_val is None or min_val is None or max_val >= min_val:
172 return
173 if not max_name:
174 min_name, max_name = f'min {min_name}', f'max {min_name}'
175 raise ValueError(f'{max_name} "{max_val}" must be must be greater than or equal to {min_name} "{min_val}"')
176
177 # Usernames and passwords
178 validate(not opts.usenetrc or (opts.username is None and opts.password is None),
179 '.netrc', msg='using {name} conflicts with giving username/password')
180 validate(opts.password is None or opts.username is not None, 'account username', msg='{name} missing')
181 validate(opts.ap_password is None or opts.ap_username is not None,
182 'TV Provider account username', msg='{name} missing')
183 validate_in('TV Provider', opts.ap_mso, MSO_INFO,
184 'Unsupported {name} "{value}", use --ap-list-mso to get a list of supported TV Providers')
185
186 # Numbers
187 validate_positive('autonumber start', opts.autonumber_start)
188 validate_positive('autonumber size', opts.autonumber_size, True)
189 validate_positive('concurrent fragments', opts.concurrent_fragment_downloads, True)
190 validate_positive('playlist start', opts.playliststart, True)
191 if opts.playlistend != -1:
192 validate_minmax(opts.playliststart, opts.playlistend, 'playlist start', 'playlist end')
193
194 # Time ranges
195 validate_positive('subtitles sleep interval', opts.sleep_interval_subtitles)
196 validate_positive('requests sleep interval', opts.sleep_interval_requests)
197 validate_positive('sleep interval', opts.sleep_interval)
198 validate_positive('max sleep interval', opts.max_sleep_interval)
199 if opts.sleep_interval is None:
200 validate(
201 opts.max_sleep_interval is None, 'min sleep interval',
202 msg='{name} must be specified; use --min-sleep-interval')
203 elif opts.max_sleep_interval is None:
204 opts.max_sleep_interval = opts.sleep_interval
205 else:
206 validate_minmax(opts.sleep_interval, opts.max_sleep_interval, 'sleep interval')
207
208 if opts.wait_for_video is not None:
209 min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
210 validate(min_wait is not None and not (max_wait is None and '-' in opts.wait_for_video),
211 'time range to wait for video', opts.wait_for_video)
212 validate_minmax(min_wait, max_wait, 'time range to wait for video')
213 opts.wait_for_video = (min_wait, max_wait)
214
215 # Format sort
216 for f in opts.format_sort:
217 validate_regex('format sorting', f, InfoExtractor.FormatSort.regex)
218
219 # Postprocessor formats
220 validate_in('audio format', opts.audioformat, ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS))
221 validate_in('subtitle format', opts.convertsubtitles, FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS)
222 validate_in('thumbnail format', opts.convertthumbnails, FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS)
223 if opts.recodevideo is not None:
224 opts.recodevideo = opts.recodevideo.replace(' ', '')
225 validate_regex('video recode format', opts.recodevideo, FFmpegVideoConvertorPP.FORMAT_RE)
226 if opts.remuxvideo is not None:
227 opts.remuxvideo = opts.remuxvideo.replace(' ', '')
228 validate_regex('video remux format', opts.remuxvideo, FFmpegVideoRemuxerPP.FORMAT_RE)
229 if opts.audioquality:
230 opts.audioquality = opts.audioquality.strip('k').strip('K')
231 # int_or_none prevents inf, nan
232 validate_positive('audio quality', int_or_none(float_or_none(opts.audioquality), default=0))
233
234 # Retries
235 def parse_retries(name, value):
236 if value is None:
237 return None
238 elif value in ('inf', 'infinite'):
239 return float('inf')
240 try:
241 return int(value)
242 except (TypeError, ValueError):
243 validate(False, f'{name} retry count', value)
244
245 opts.retries = parse_retries('download', opts.retries)
246 opts.fragment_retries = parse_retries('fragment', opts.fragment_retries)
247 opts.extractor_retries = parse_retries('extractor', opts.extractor_retries)
248 opts.file_access_retries = parse_retries('file access', opts.file_access_retries)
249
250 # Retry sleep function
251 def parse_sleep_func(expr):
252 NUMBER_RE = r'\d+(?:\.\d+)?'
253 op, start, limit, step, *_ = tuple(re.fullmatch(
254 rf'(?:(linear|exp)=)?({NUMBER_RE})(?::({NUMBER_RE}))?(?::({NUMBER_RE}))?',
255 expr.strip()).groups()) + (None, None)
256
257 if op == 'exp':
258 return lambda n: min(float(start) * (float(step or 2) ** n), float(limit or 'inf'))
259 else:
260 default_step = start if op or limit else 0
261 return lambda n: min(float(start) + float(step or default_step) * n, float(limit or 'inf'))
262
263 for key, expr in opts.retry_sleep.items():
264 if not expr:
265 del opts.retry_sleep[key]
266 continue
267 try:
268 opts.retry_sleep[key] = parse_sleep_func(expr)
269 except AttributeError as e:
270 raise ValueError(f'invalid {key} retry sleep expression {expr!r}: {e}')
271
272 # Bytes
273 def parse_bytes(name, value):
274 if value is None:
275 return None
276 numeric_limit = FileDownloader.parse_bytes(value)
277 validate(numeric_limit is not None, 'rate limit', value)
278 return numeric_limit
279
280 opts.ratelimit = parse_bytes('rate limit', opts.ratelimit)
281 opts.throttledratelimit = parse_bytes('throttled rate limit', opts.throttledratelimit)
282 opts.min_filesize = parse_bytes('min filesize', opts.min_filesize)
283 opts.max_filesize = parse_bytes('max filesize', opts.max_filesize)
284 opts.buffersize = parse_bytes('buffer size', opts.buffersize)
285 opts.http_chunk_size = parse_bytes('http chunk size', opts.http_chunk_size)
286
287 # Output templates
288 def validate_outtmpl(tmpl, msg):
289 err = YoutubeDL.validate_outtmpl(tmpl)
290 if err:
291 raise ValueError(f'invalid {msg} "{tmpl}": {err}')
292
293 for k, tmpl in opts.outtmpl.items():
294 validate_outtmpl(tmpl, f'{k} output template')
295 for type_, tmpl_list in opts.forceprint.items():
296 for tmpl in tmpl_list:
297 validate_outtmpl(tmpl, f'{type_} print template')
298 for type_, tmpl_list in opts.print_to_file.items():
299 for tmpl, file in tmpl_list:
300 validate_outtmpl(tmpl, f'{type_} print to file template')
301 validate_outtmpl(file, f'{type_} print to file filename')
302 validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
303 for k, tmpl in opts.progress_template.items():
304 k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
305 validate_outtmpl(tmpl, f'{k} template')
306
307 outtmpl_default = opts.outtmpl.get('default')
308 if outtmpl_default == '':
309 opts.skip_download = None
310 del opts.outtmpl['default']
311 if outtmpl_default and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
312 raise ValueError(
313 'Cannot download a video and extract audio into the same file! '
314 f'Use "{outtmpl_default}.%(ext)s" instead of "{outtmpl_default}" as the output template')
315
316 # Remove chapters
317 remove_chapters_patterns, opts.remove_ranges = [], []
318 for regex in opts.remove_chapters or []:
319 if regex.startswith('*'):
320 dur = list(map(parse_duration, regex[1:].split('-')))
321 if len(dur) == 2 and all(t is not None for t in dur):
322 opts.remove_ranges.append(tuple(dur))
323 continue
324 raise ValueError(f'invalid --remove-chapters time range "{regex}". Must be of the form *start-end')
325 try:
326 remove_chapters_patterns.append(re.compile(regex))
327 except re.error as err:
328 raise ValueError(f'invalid --remove-chapters regex "{regex}" - {err}')
329 opts.remove_chapters = remove_chapters_patterns
330
331 # Cookies from browser
332 if opts.cookiesfrombrowser:
333 mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
334 if mobj is None:
335 raise ValueError(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
336 browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
337 browser_name = browser_name.lower()
338 if browser_name not in SUPPORTED_BROWSERS:
339 raise ValueError(f'unsupported browser specified for cookies: "{browser_name}". '
340 f'Supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}')
341 if keyring is not None:
342 keyring = keyring.upper()
343 if keyring not in SUPPORTED_KEYRINGS:
344 raise ValueError(f'unsupported keyring specified for cookies: "{keyring}". '
345 f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
346 opts.cookiesfrombrowser = (browser_name, profile, keyring)
347
348 # MetadataParser
349 def metadataparser_actions(f):
350 if isinstance(f, str):
351 cmd = '--parse-metadata %s' % compat_shlex_quote(f)
352 try:
353 actions = [MetadataFromFieldPP.to_action(f)]
354 except Exception as err:
355 raise ValueError(f'{cmd} is invalid; {err}')
356 else:
357 cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
358 actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
359
360 for action in actions:
361 try:
362 MetadataParserPP.validate_action(*action)
363 except Exception as err:
364 raise ValueError(f'{cmd} is invalid; {err}')
365 yield action
366
367 parse_metadata = opts.parse_metadata or []
368 if opts.metafromtitle is not None:
369 parse_metadata.append('title:%s' % opts.metafromtitle)
370 opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, parse_metadata)))
371
372 # Other options
373 geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
374 if geo_bypass_code is not None:
375 try:
376 GeoUtils.random_ipv4(geo_bypass_code)
377 except Exception:
378 raise ValueError('unsupported geo-bypass country or ip-block')
379
380 opts.match_filter = match_filter_func(opts.match_filter)
381
382 if opts.download_archive is not None:
383 opts.download_archive = expand_path(opts.download_archive)
384
385 if opts.user_agent is not None:
386 opts.headers.setdefault('User-Agent', opts.user_agent)
387 if opts.referer is not None:
388 opts.headers.setdefault('Referer', opts.referer)
389
390 if opts.no_sponsorblock:
391 opts.sponsorblock_mark = opts.sponsorblock_remove = set()
392
393 warnings, deprecation_warnings = [], []
394
395 # Common mistake: -f best
396 if opts.format == 'best':
397 warnings.append('.\n '.join((
398 '"-f best" selects the best pre-merged format which is often not the best option',
399 'To let yt-dlp download and merge the best available formats, simply do not pass any format selection',
400 'If you know what you are doing and want only the best pre-merged format, use "-f b" instead to suppress this warning')))
401
402 # --(postprocessor/downloader)-args without name
403 def report_args_compat(name, value, key1, key2=None):
404 if key1 in value and key2 not in value:
405 warnings.append(f'{name} arguments given without specifying name. The arguments will be given to all {name}s')
406 return True
407 return False
408
409 report_args_compat('external downloader', opts.external_downloader_args, 'default')
410 if report_args_compat('post-processor', opts.postprocessor_args, 'default-compat', 'default'):
411 opts.postprocessor_args['default'] = opts.postprocessor_args.pop('default-compat')
412 opts.postprocessor_args.setdefault('sponskrub', [])
413
414 def report_conflict(arg1, opt1, arg2='--allow-unplayable-formats', opt2='allow_unplayable_formats',
415 val1=NO_DEFAULT, val2=NO_DEFAULT, default=False):
416 if val2 is NO_DEFAULT:
417 val2 = getattr(opts, opt2)
418 if not val2:
419 return
420
421 if val1 is NO_DEFAULT:
422 val1 = getattr(opts, opt1)
423 if val1:
424 warnings.append(f'{arg1} is ignored since {arg2} was given')
425 setattr(opts, opt1, default)
426
427 # Conflicting options
428 report_conflict('--dateafter', 'dateafter', '--date', 'date', default=None)
429 report_conflict('--datebefore', 'datebefore', '--date', 'date', default=None)
430 report_conflict('--exec-before-download', 'exec_before_dl_cmd',
431 '"--exec before_dl:"', 'exec_cmd', val2=opts.exec_cmd.get('before_dl'))
432 report_conflict('--id', 'useid', '--output', 'outtmpl', val2=opts.outtmpl.get('default'))
433 report_conflict('--remux-video', 'remuxvideo', '--recode-video', 'recodevideo')
434 report_conflict('--sponskrub', 'sponskrub', '--remove-chapters', 'remove_chapters')
435 report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-mark', 'sponsorblock_mark')
436 report_conflict('--sponskrub', 'sponskrub', '--sponsorblock-remove', 'sponsorblock_remove')
437 report_conflict('--sponskrub-cut', 'sponskrub_cut', '--split-chapter', 'split_chapters',
438 val1=opts.sponskrub and opts.sponskrub_cut)
439
440 # Conflicts with --allow-unplayable-formats
441 report_conflict('--add-metadata', 'addmetadata')
442 report_conflict('--embed-chapters', 'addchapters')
443 report_conflict('--embed-info-json', 'embed_infojson')
444 report_conflict('--embed-subs', 'embedsubtitles')
445 report_conflict('--embed-thumbnail', 'embedthumbnail')
446 report_conflict('--extract-audio', 'extractaudio')
447 report_conflict('--fixup', 'fixup', val1=opts.fixup not in (None, 'never', 'ignore'), default='never')
448 report_conflict('--recode-video', 'recodevideo')
449 report_conflict('--remove-chapters', 'remove_chapters', default=[])
450 report_conflict('--remux-video', 'remuxvideo')
451 report_conflict('--sponskrub', 'sponskrub')
452 report_conflict('--sponsorblock-remove', 'sponsorblock_remove', default=set())
453 report_conflict('--xattrs', 'xattrs')
454
455 # Fully deprecated options
456 def report_deprecation(val, old, new=None):
457 if not val:
458 return
459 deprecation_warnings.append(
460 f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
461 else f'{old} is deprecated and may not work as expected')
462
463 report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
464 report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
465 # report_deprecation(opts.include_ads, '--include-ads') # We may re-implement this in future
466 # report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
467 # report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
468
469 # Dependent options
470 opts.date = DateRange.day(opts.date) if opts.date else DateRange(opts.dateafter, opts.datebefore)
471
472 if opts.exec_before_dl_cmd:
473 opts.exec_cmd['before_dl'] = opts.exec_before_dl_cmd
474
475 if opts.useid: # --id is not deprecated in youtube-dl
476 opts.outtmpl['default'] = '%(id)s.%(ext)s'
477
478 if opts.overwrites: # --force-overwrites implies --no-continue
479 opts.continue_dl = False
480
481 if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
482 # Add chapters when adding metadata or marking sponsors
483 opts.addchapters = True
484
485 if opts.extractaudio and not opts.keepvideo and opts.format is None:
486 # Do not unnecessarily download audio
487 opts.format = 'bestaudio/best'
488
489 if opts.getcomments and opts.writeinfojson is None:
490 # If JSON is not printed anywhere, but comments are requested, save it to file
491 if not opts.dumpjson or opts.print_json or opts.dump_single_json:
492 opts.writeinfojson = True
493
494 if opts.allsubtitles and not (opts.embedsubtitles or opts.writeautomaticsub):
495 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
496 opts.writesubtitles = True
497
498 if opts.addmetadata and opts.embed_infojson is None:
499 # If embedding metadata and infojson is present, embed it
500 opts.embed_infojson = 'if_exists'
501
502 # Ask for passwords
503 if opts.username is not None and opts.password is None:
504 opts.password = compat_getpass('Type account password and press [Return]: ')
505 if opts.ap_username is not None and opts.ap_password is None:
506 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
507
508 return warnings, deprecation_warnings
509
510
511 def get_postprocessors(opts):
512 yield from opts.add_postprocessors
513
514 if opts.parse_metadata:
515 yield {
516 'key': 'MetadataParser',
517 'actions': opts.parse_metadata,
518 'when': 'pre_process'
519 }
520 sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
521 if sponsorblock_query:
522 yield {
523 'key': 'SponsorBlock',
524 'categories': sponsorblock_query,
525 'api': opts.sponsorblock_api,
526 'when': 'after_filter'
527 }
528 if opts.convertsubtitles:
529 yield {
530 'key': 'FFmpegSubtitlesConvertor',
531 'format': opts.convertsubtitles,
532 'when': 'before_dl'
533 }
534 if opts.convertthumbnails:
535 yield {
536 'key': 'FFmpegThumbnailsConvertor',
537 'format': opts.convertthumbnails,
538 'when': 'before_dl'
539 }
540 if opts.extractaudio:
541 yield {
542 'key': 'FFmpegExtractAudio',
543 'preferredcodec': opts.audioformat,
544 'preferredquality': opts.audioquality,
545 'nopostoverwrites': opts.nopostoverwrites,
546 }
547 if opts.remuxvideo:
548 yield {
549 'key': 'FFmpegVideoRemuxer',
550 'preferedformat': opts.remuxvideo,
551 }
552 if opts.recodevideo:
553 yield {
554 'key': 'FFmpegVideoConvertor',
555 'preferedformat': opts.recodevideo,
556 }
557 # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
558 if opts.embedsubtitles:
559 keep_subs = 'no-keep-subs' not in opts.compat_opts
560 yield {
561 'key': 'FFmpegEmbedSubtitle',
562 # already_have_subtitle = True prevents the file from being deleted after embedding
563 'already_have_subtitle': opts.writesubtitles and keep_subs
564 }
565 if not opts.writeautomaticsub and keep_subs:
566 opts.writesubtitles = True
567
568 # ModifyChapters must run before FFmpegMetadataPP
569 if opts.remove_chapters or sponsorblock_query:
570 yield {
571 'key': 'ModifyChapters',
572 'remove_chapters_patterns': opts.remove_chapters,
573 'remove_sponsor_segments': opts.sponsorblock_remove,
574 'remove_ranges': opts.remove_ranges,
575 'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
576 'force_keyframes': opts.force_keyframes_at_cuts
577 }
578 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
579 # FFmpegExtractAudioPP as containers before conversion may not support
580 # metadata (3gp, webm, etc.)
581 # By default ffmpeg preserves metadata applicable for both
582 # source and target containers. From this point the container won't change,
583 # so metadata can be added here.
584 if opts.addmetadata or opts.addchapters or opts.embed_infojson:
585 yield {
586 'key': 'FFmpegMetadata',
587 'add_chapters': opts.addchapters,
588 'add_metadata': opts.addmetadata,
589 'add_infojson': opts.embed_infojson,
590 }
591 # Deprecated
592 # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
593 # but must be below EmbedSubtitle and FFmpegMetadata
594 # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
595 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
596 if opts.sponskrub is not False:
597 yield {
598 'key': 'SponSkrub',
599 'path': opts.sponskrub_path,
600 'args': opts.sponskrub_args,
601 'cut': opts.sponskrub_cut,
602 'force': opts.sponskrub_force,
603 'ignoreerror': opts.sponskrub is None,
604 '_from_cli': True,
605 }
606 if opts.embedthumbnail:
607 yield {
608 'key': 'EmbedThumbnail',
609 # already_have_thumbnail = True prevents the file from being deleted after embedding
610 'already_have_thumbnail': opts.writethumbnail
611 }
612 if not opts.writethumbnail:
613 opts.writethumbnail = True
614 opts.outtmpl['pl_thumbnail'] = ''
615 if opts.split_chapters:
616 yield {
617 'key': 'FFmpegSplitChapters',
618 'force_keyframes': opts.force_keyframes_at_cuts,
619 }
620 # XAttrMetadataPP should be run after post-processors that may change file contents
621 if opts.xattrs:
622 yield {'key': 'XAttrMetadata'}
623 if opts.concat_playlist != 'never':
624 yield {
625 'key': 'FFmpegConcat',
626 'only_multi_video': opts.concat_playlist != 'always',
627 'when': 'playlist',
628 }
629 # Exec must be the last PP of each category
630 for when, exec_cmd in opts.exec_cmd.items():
631 yield {
632 'key': 'Exec',
633 'exec_cmd': exec_cmd,
634 'when': when,
635 }
636
637
638 def parse_options(argv=None):
639 """ @returns (parser, opts, urls, ydl_opts) """
640 parser, opts, urls = parseOpts(argv)
641 urls = get_urls(urls, opts.batchfile, opts.verbose)
642
643 set_compat_opts(opts)
644 try:
645 warnings, deprecation_warnings = validate_options(opts)
646 except ValueError as err:
647 parser.error(f'{err}\n')
648
649 postprocessors = list(get_postprocessors(opts))
650
651 print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[2:])
652 any_getting = any(getattr(opts, k) for k in (
653 'dumpjson', 'dump_single_json', 'getdescription', 'getduration', 'getfilename',
654 'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
655 ))
656
657 final_ext = (
658 opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
659 else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
660 else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
661 else None)
662
663 return parser, opts, urls, {
664 'usenetrc': opts.usenetrc,
665 'netrc_location': opts.netrc_location,
666 'username': opts.username,
667 'password': opts.password,
668 'twofactor': opts.twofactor,
669 'videopassword': opts.videopassword,
670 'ap_mso': opts.ap_mso,
671 'ap_username': opts.ap_username,
672 'ap_password': opts.ap_password,
673 'client_certificate': opts.client_certificate,
674 'client_certificate_key': opts.client_certificate_key,
675 'client_certificate_password': opts.client_certificate_password,
676 'quiet': opts.quiet or any_getting or opts.print_json or bool(opts.forceprint),
677 'no_warnings': opts.no_warnings,
678 'forceurl': opts.geturl,
679 'forcetitle': opts.gettitle,
680 'forceid': opts.getid,
681 'forcethumbnail': opts.getthumbnail,
682 'forcedescription': opts.getdescription,
683 'forceduration': opts.getduration,
684 'forcefilename': opts.getfilename,
685 'forceformat': opts.getformat,
686 'forceprint': opts.forceprint,
687 'print_to_file': opts.print_to_file,
688 'forcejson': opts.dumpjson or opts.print_json,
689 'dump_single_json': opts.dump_single_json,
690 'force_write_download_archive': opts.force_write_download_archive,
691 'simulate': (print_only or any_getting or None) if opts.simulate is None else opts.simulate,
692 'skip_download': opts.skip_download,
693 'format': opts.format,
694 'allow_unplayable_formats': opts.allow_unplayable_formats,
695 'ignore_no_formats_error': opts.ignore_no_formats_error,
696 'format_sort': opts.format_sort,
697 'format_sort_force': opts.format_sort_force,
698 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
699 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
700 'check_formats': opts.check_formats,
701 'listformats': opts.listformats,
702 'listformats_table': opts.listformats_table,
703 'outtmpl': opts.outtmpl,
704 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
705 'paths': opts.paths,
706 'autonumber_size': opts.autonumber_size,
707 'autonumber_start': opts.autonumber_start,
708 'restrictfilenames': opts.restrictfilenames,
709 'windowsfilenames': opts.windowsfilenames,
710 'ignoreerrors': opts.ignoreerrors,
711 'force_generic_extractor': opts.force_generic_extractor,
712 'ratelimit': opts.ratelimit,
713 'throttledratelimit': opts.throttledratelimit,
714 'overwrites': opts.overwrites,
715 'retries': opts.retries,
716 'file_access_retries': opts.file_access_retries,
717 'fragment_retries': opts.fragment_retries,
718 'extractor_retries': opts.extractor_retries,
719 'retry_sleep_functions': opts.retry_sleep,
720 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
721 'keep_fragments': opts.keep_fragments,
722 'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
723 'buffersize': opts.buffersize,
724 'noresizebuffer': opts.noresizebuffer,
725 'http_chunk_size': opts.http_chunk_size,
726 'continuedl': opts.continue_dl,
727 'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
728 'progress_with_newline': opts.progress_with_newline,
729 'progress_template': opts.progress_template,
730 'playliststart': opts.playliststart,
731 'playlistend': opts.playlistend,
732 'playlistreverse': opts.playlist_reverse,
733 'playlistrandom': opts.playlist_random,
734 'noplaylist': opts.noplaylist,
735 'logtostderr': opts.outtmpl.get('default') == '-',
736 'consoletitle': opts.consoletitle,
737 'nopart': opts.nopart,
738 'updatetime': opts.updatetime,
739 'writedescription': opts.writedescription,
740 'writeannotations': opts.writeannotations,
741 'writeinfojson': opts.writeinfojson,
742 'allow_playlist_files': opts.allow_playlist_files,
743 'clean_infojson': opts.clean_infojson,
744 'getcomments': opts.getcomments,
745 'writethumbnail': opts.writethumbnail is True,
746 'write_all_thumbnails': opts.writethumbnail == 'all',
747 'writelink': opts.writelink,
748 'writeurllink': opts.writeurllink,
749 'writewebloclink': opts.writewebloclink,
750 'writedesktoplink': opts.writedesktoplink,
751 'writesubtitles': opts.writesubtitles,
752 'writeautomaticsub': opts.writeautomaticsub,
753 'allsubtitles': opts.allsubtitles,
754 'listsubtitles': opts.listsubtitles,
755 'subtitlesformat': opts.subtitlesformat,
756 'subtitleslangs': opts.subtitleslangs,
757 'matchtitle': decodeOption(opts.matchtitle),
758 'rejecttitle': decodeOption(opts.rejecttitle),
759 'max_downloads': opts.max_downloads,
760 'prefer_free_formats': opts.prefer_free_formats,
761 'trim_file_name': opts.trim_file_name,
762 'verbose': opts.verbose,
763 'dump_intermediate_pages': opts.dump_intermediate_pages,
764 'write_pages': opts.write_pages,
765 'test': opts.test,
766 'keepvideo': opts.keepvideo,
767 'min_filesize': opts.min_filesize,
768 'max_filesize': opts.max_filesize,
769 'min_views': opts.min_views,
770 'max_views': opts.max_views,
771 'daterange': opts.date,
772 'cachedir': opts.cachedir,
773 'youtube_print_sig_code': opts.youtube_print_sig_code,
774 'age_limit': opts.age_limit,
775 'download_archive': opts.download_archive,
776 'break_on_existing': opts.break_on_existing,
777 'break_on_reject': opts.break_on_reject,
778 'break_per_url': opts.break_per_url,
779 'skip_playlist_after_errors': opts.skip_playlist_after_errors,
780 'cookiefile': opts.cookiefile,
781 'cookiesfrombrowser': opts.cookiesfrombrowser,
782 'legacyserverconnect': opts.legacy_server_connect,
783 'nocheckcertificate': opts.no_check_certificate,
784 'prefer_insecure': opts.prefer_insecure,
785 'http_headers': opts.headers,
786 'proxy': opts.proxy,
787 'socket_timeout': opts.socket_timeout,
788 'bidi_workaround': opts.bidi_workaround,
789 'debug_printtraffic': opts.debug_printtraffic,
790 'prefer_ffmpeg': opts.prefer_ffmpeg,
791 'include_ads': opts.include_ads,
792 'default_search': opts.default_search,
793 'dynamic_mpd': opts.dynamic_mpd,
794 'extractor_args': opts.extractor_args,
795 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
796 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
797 'encoding': opts.encoding,
798 'extract_flat': opts.extract_flat,
799 'live_from_start': opts.live_from_start,
800 'wait_for_video': opts.wait_for_video,
801 'mark_watched': opts.mark_watched,
802 'merge_output_format': opts.merge_output_format,
803 'final_ext': final_ext,
804 'postprocessors': postprocessors,
805 'fixup': opts.fixup,
806 'source_address': opts.source_address,
807 'call_home': opts.call_home,
808 'sleep_interval_requests': opts.sleep_interval_requests,
809 'sleep_interval': opts.sleep_interval,
810 'max_sleep_interval': opts.max_sleep_interval,
811 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
812 'external_downloader': opts.external_downloader,
813 'list_thumbnails': opts.list_thumbnails,
814 'playlist_items': opts.playlist_items,
815 'xattr_set_filesize': opts.xattr_set_filesize,
816 'match_filter': opts.match_filter,
817 'no_color': opts.no_color,
818 'ffmpeg_location': opts.ffmpeg_location,
819 'hls_prefer_native': opts.hls_prefer_native,
820 'hls_use_mpegts': opts.hls_use_mpegts,
821 'hls_split_discontinuity': opts.hls_split_discontinuity,
822 'external_downloader_args': opts.external_downloader_args,
823 'postprocessor_args': opts.postprocessor_args,
824 'cn_verification_proxy': opts.cn_verification_proxy,
825 'geo_verification_proxy': opts.geo_verification_proxy,
826 'geo_bypass': opts.geo_bypass,
827 'geo_bypass_country': opts.geo_bypass_country,
828 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
829 '_warnings': warnings,
830 '_deprecation_warnings': deprecation_warnings,
831 'compat_opts': opts.compat_opts,
832 }
833
834
835 def _real_main(argv=None):
836 setproctitle('yt-dlp')
837
838 parser, opts, all_urls, ydl_opts = parse_options(argv)
839
840 # Dump user agent
841 if opts.dump_user_agent:
842 ua = traverse_obj(opts.headers, 'User-Agent', casesense=False, default=std_headers['User-Agent'])
843 write_string(f'{ua}\n', out=sys.stdout)
844 return
845
846 if print_extractor_information(opts, all_urls):
847 return
848
849 with YoutubeDL(ydl_opts) as ydl:
850 actual_use = all_urls or opts.load_info_filename
851
852 if opts.rm_cachedir:
853 ydl.cache.remove()
854
855 if opts.update_self and run_update(ydl) and actual_use:
856 # If updater returns True, exit. Required for windows
857 return 100, 'ERROR: The program must exit for the update to complete'
858
859 if not actual_use:
860 if opts.update_self or opts.rm_cachedir:
861 return ydl._download_retcode
862
863 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
864 parser.error(
865 'You must provide at least one URL.\n'
866 'Type yt-dlp --help to see a list of all options.')
867
868 parser.destroy()
869 try:
870 if opts.load_info_filename is not None:
871 return ydl.download_with_info_file(expand_path(opts.load_info_filename))
872 else:
873 return ydl.download(all_urls)
874 except DownloadCancelled:
875 ydl.to_screen('Aborting remaining downloads')
876 return 101
877
878
879 def main(argv=None):
880 try:
881 _exit(*variadic(_real_main(argv)))
882 except DownloadError:
883 _exit(1)
884 except SameFileError as e:
885 _exit(f'ERROR: {e}')
886 except KeyboardInterrupt:
887 _exit('\nERROR: Interrupted by user')
888 except BrokenPipeError as e:
889 # https://docs.python.org/3/library/signal.html#note-on-sigpipe
890 devnull = os.open(os.devnull, os.O_WRONLY)
891 os.dup2(devnull, sys.stdout.fileno())
892 _exit(f'\nERROR: {e}')
893 except optparse.OptParseError as e:
894 _exit(2, f'\n{e}')
895
896
897 from .extractor import gen_extractors, list_extractors
898
899 __all__ = [
900 'main',
901 'YoutubeDL',
902 'parse_options',
903 'gen_extractors',
904 'list_extractors',
905 ]