]> jfr.im git - yt-dlp.git/blob - yt_dlp/__init__.py
Add pre-processor stage `after_filter`
[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, SUPPORTED_KEYRINGS
26 from .utils import (
27 DateRange,
28 decodeOption,
29 DownloadCancelled,
30 DownloadError,
31 error_to_compat_str,
32 expand_path,
33 GeoUtils,
34 float_or_none,
35 int_or_none,
36 match_filter_func,
37 parse_duration,
38 preferredencoding,
39 read_batch_urls,
40 render_table,
41 SameFileError,
42 setproctitle,
43 std_headers,
44 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.exec_cmd.get('before_dl') and opts.exec_before_dl_cmd:
147 parser.error('using "--exec-before-download" conflicts with "--exec before_dl:"')
148 if opts.usenetrc and (opts.username is not None or opts.password is not None):
149 parser.error('using .netrc conflicts with giving username/password')
150 if opts.password is not None and opts.username is None:
151 parser.error('account username missing\n')
152 if opts.ap_password is not None and opts.ap_username is None:
153 parser.error('TV Provider account username missing\n')
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')
160 if opts.username is not None and opts.password is None:
161 opts.password = compat_getpass('Type account password and press [Return]: ')
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]: ')
164 if opts.ratelimit is not None:
165 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
166 if numeric_limit is None:
167 parser.error('invalid rate limit specified')
168 opts.ratelimit = numeric_limit
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
174 if opts.min_filesize is not None:
175 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
176 if numeric_limit is None:
177 parser.error('invalid min_filesize specified')
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:
182 parser.error('invalid max_filesize specified')
183 opts.max_filesize = numeric_limit
184 if opts.sleep_interval is not None:
185 if opts.sleep_interval < 0:
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')
190 if opts.sleep_interval is None:
191 parser.error('min sleep interval must be specified, use --min-sleep-interval')
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
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')
202 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
203 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
204 if opts.overwrites: # --yes-overwrites implies --no-continue
205 opts.continue_dl = False
206 if opts.concurrent_fragment_downloads <= 0:
207 parser.error('Concurrent fragments must be positive')
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 if min_wait is None or (max_wait is None and '-' in opts.wait_for_video):
211 parser.error('Invalid time range to wait')
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')
214 opts.wait_for_video = (min_wait, max_wait)
215
216 def parse_retries(retries, name=''):
217 if retries in ('inf', 'infinite'):
218 parsed_retries = float('inf')
219 else:
220 try:
221 parsed_retries = int(retries)
222 except (TypeError, ValueError):
223 parser.error('invalid %sretry count specified' % name)
224 return parsed_retries
225 if opts.retries is not None:
226 opts.retries = parse_retries(opts.retries)
227 if opts.file_access_retries is not None:
228 opts.file_access_retries = parse_retries(opts.file_access_retries, 'file access ')
229 if opts.fragment_retries is not None:
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 ')
233 if opts.buffersize is not None:
234 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
235 if numeric_buffersize is None:
236 parser.error('invalid buffer size specified')
237 opts.buffersize = numeric_buffersize
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
243 if opts.playliststart <= 0:
244 raise parser.error('Playlist start must be positive')
245 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
246 raise parser.error('Playlist end must be greater than playlist start')
247 if opts.extractaudio:
248 opts.audioformat = opts.audioformat.lower()
249 if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
250 parser.error('invalid audio format specified')
251 if opts.audioquality:
252 opts.audioquality = opts.audioquality.strip('k').strip('K')
253 audioquality = int_or_none(float_or_none(opts.audioquality)) # int_or_none prevents inf, nan
254 if audioquality is None or audioquality < 0:
255 parser.error('invalid audio quality specified')
256 if opts.recodevideo is not None:
257 opts.recodevideo = opts.recodevideo.replace(' ', '')
258 if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
259 parser.error('invalid video remux format specified')
260 if opts.remuxvideo is not None:
261 opts.remuxvideo = opts.remuxvideo.replace(' ', '')
262 if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
263 parser.error('invalid video remux format specified')
264 if opts.convertsubtitles is not None:
265 if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
266 parser.error('invalid subtitle format specified')
267 if opts.convertthumbnails is not None:
268 if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
269 parser.error('invalid thumbnail format specified')
270 if opts.cookiesfrombrowser is not None:
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)
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')
291
292 if opts.date is not None:
293 date = DateRange.day(opts.date)
294 else:
295 date = DateRange(opts.dateafter, opts.datebefore)
296
297 compat_opts = opts.compat_opts
298
299 def report_conflict(arg1, arg2):
300 warnings.append(f'{arg2} is ignored since {arg1} was given')
301
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
309 def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
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
323 set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
324 set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
325 set_default_compat('no-clean-infojson', 'clean_infojson')
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
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')
338 if outtmpl_default == '':
339 outtmpl_default, opts.skip_download = None, True
340 del opts.outtmpl['default']
341 if opts.useid:
342 if outtmpl_default is None:
343 outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
344 else:
345 report_conflict('--output', '--id')
346 if 'filename' in compat_opts:
347 if outtmpl_default is None:
348 outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
349 else:
350 _unused_compat_opt('filename')
351
352 def validate_outtmpl(tmpl, msg):
353 err = YoutubeDL.validate_outtmpl(tmpl)
354 if err:
355 parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
356
357 for k, tmpl in opts.outtmpl.items():
358 validate_outtmpl(tmpl, f'{k} output template')
359 for type_, tmpl_list in opts.forceprint.items():
360 for tmpl in tmpl_list:
361 validate_outtmpl(tmpl, f'{type_} print template')
362 for type_, tmpl_list in opts.print_to_file.items():
363 for tmpl, file in tmpl_list:
364 validate_outtmpl(tmpl, f'{type_} print-to-file template')
365 validate_outtmpl(file, f'{type_} print-to-file filename')
366 validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
367 for k, tmpl in opts.progress_template.items():
368 k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
369 validate_outtmpl(tmpl, f'{k} template')
370
371 if opts.extractaudio and not opts.keepvideo and opts.format is None:
372 opts.format = 'bestaudio/best'
373
374 if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
375 parser.error('Cannot download a video and extract audio into the same'
376 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
377 ' template'.format(outtmpl_default))
378
379 for f in opts.format_sort:
380 if re.match(InfoExtractor.FormatSort.regex, f) is None:
381 parser.error('invalid format sort string "%s" specified' % f)
382
383 def metadataparser_actions(f):
384 if isinstance(f, str):
385 cmd = '--parse-metadata %s' % compat_shlex_quote(f)
386 try:
387 actions = [MetadataFromFieldPP.to_action(f)]
388 except Exception as err:
389 parser.error(f'{cmd} is invalid; {err}')
390 else:
391 cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
392 actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
393
394 for action in actions:
395 try:
396 MetadataParserPP.validate_action(*action)
397 except Exception as err:
398 parser.error(f'{cmd} is invalid; {err}')
399 yield action
400
401 if opts.parse_metadata is None:
402 opts.parse_metadata = []
403 if opts.metafromtitle is not None:
404 opts.parse_metadata.append('title:%s' % opts.metafromtitle)
405 opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
406
407 any_getting = (any(opts.forceprint.values()) or opts.dumpjson or opts.dump_single_json
408 or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail
409 or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration)
410
411 any_printing = opts.print_json
412 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
413
414 # If JSON is not printed anywhere, but comments are requested, save it to file
415 printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
416 if opts.getcomments and not printing_json:
417 opts.writeinfojson = True
418
419 if opts.no_sponsorblock:
420 opts.sponsorblock_mark = set()
421 opts.sponsorblock_remove = set()
422 sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
423
424 opts.remove_chapters = opts.remove_chapters or []
425
426 if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
427 if opts.sponskrub:
428 if opts.remove_chapters:
429 report_conflict('--remove-chapters', '--sponskrub')
430 if opts.sponsorblock_mark:
431 report_conflict('--sponsorblock-mark', '--sponskrub')
432 if opts.sponsorblock_remove:
433 report_conflict('--sponsorblock-remove', '--sponskrub')
434 opts.sponskrub = False
435 if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
436 report_conflict('--split-chapter', '--sponskrub-cut')
437 opts.sponskrub_cut = False
438
439 if opts.remuxvideo and opts.recodevideo:
440 report_conflict('--recode-video', '--remux-video')
441 opts.remuxvideo = False
442
443 if opts.allow_unplayable_formats:
444 def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
445 val = getattr(opts, opt_name)
446 if (not allowed and val) or (allowed and not allowed(val)):
447 report_conflict('--allow-unplayable-formats', arg)
448 setattr(opts, opt_name, default)
449
450 report_unplayable_conflict('extractaudio', '--extract-audio')
451 report_unplayable_conflict('remuxvideo', '--remux-video')
452 report_unplayable_conflict('recodevideo', '--recode-video')
453 report_unplayable_conflict('addmetadata', '--embed-metadata')
454 report_unplayable_conflict('addchapters', '--embed-chapters')
455 report_unplayable_conflict('embed_infojson', '--embed-info-json')
456 opts.embed_infojson = False
457 report_unplayable_conflict('embedsubtitles', '--embed-subs')
458 report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
459 report_unplayable_conflict('xattrs', '--xattrs')
460 report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
461 opts.fixup = 'never'
462 report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
463 report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
464 report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
465 opts.sponskrub = False
466
467 if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
468 opts.addchapters = True
469
470 # PostProcessors
471 postprocessors = list(opts.add_postprocessors)
472 if sponsorblock_query:
473 postprocessors.append({
474 'key': 'SponsorBlock',
475 'categories': sponsorblock_query,
476 'api': opts.sponsorblock_api,
477 # Run this after filtering videos
478 'when': 'after_filter'
479 })
480 if opts.parse_metadata:
481 postprocessors.append({
482 'key': 'MetadataParser',
483 'actions': opts.parse_metadata,
484 # Run this immediately after extraction is complete
485 'when': 'pre_process'
486 })
487 if opts.convertsubtitles:
488 postprocessors.append({
489 'key': 'FFmpegSubtitlesConvertor',
490 'format': opts.convertsubtitles,
491 # Run this before the actual video download
492 'when': 'before_dl'
493 })
494 if opts.convertthumbnails:
495 postprocessors.append({
496 'key': 'FFmpegThumbnailsConvertor',
497 'format': opts.convertthumbnails,
498 # Run this before the actual video download
499 'when': 'before_dl'
500 })
501 if opts.extractaudio:
502 postprocessors.append({
503 'key': 'FFmpegExtractAudio',
504 'preferredcodec': opts.audioformat,
505 'preferredquality': opts.audioquality,
506 'nopostoverwrites': opts.nopostoverwrites,
507 })
508 if opts.remuxvideo:
509 postprocessors.append({
510 'key': 'FFmpegVideoRemuxer',
511 'preferedformat': opts.remuxvideo,
512 })
513 if opts.recodevideo:
514 postprocessors.append({
515 'key': 'FFmpegVideoConvertor',
516 'preferedformat': opts.recodevideo,
517 })
518 # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
519 if opts.embedsubtitles:
520 already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
521 postprocessors.append({
522 'key': 'FFmpegEmbedSubtitle',
523 # already_have_subtitle = True prevents the file from being deleted after embedding
524 'already_have_subtitle': already_have_subtitle
525 })
526 if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
527 opts.writesubtitles = True
528 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
529 # this was the old behaviour if only --all-sub was given.
530 if opts.allsubtitles and not opts.writeautomaticsub:
531 opts.writesubtitles = True
532 # ModifyChapters must run before FFmpegMetadataPP
533 remove_chapters_patterns, remove_ranges = [], []
534 for regex in opts.remove_chapters:
535 if regex.startswith('*'):
536 dur = list(map(parse_duration, regex[1:].split('-')))
537 if len(dur) == 2 and all(t is not None for t in dur):
538 remove_ranges.append(tuple(dur))
539 continue
540 parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form *start-end')
541 try:
542 remove_chapters_patterns.append(re.compile(regex))
543 except re.error as err:
544 parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
545 if opts.remove_chapters or sponsorblock_query:
546 postprocessors.append({
547 'key': 'ModifyChapters',
548 'remove_chapters_patterns': remove_chapters_patterns,
549 'remove_sponsor_segments': opts.sponsorblock_remove,
550 'remove_ranges': remove_ranges,
551 'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
552 'force_keyframes': opts.force_keyframes_at_cuts
553 })
554 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
555 # FFmpegExtractAudioPP as containers before conversion may not support
556 # metadata (3gp, webm, etc.)
557 # By default ffmpeg preserves metadata applicable for both
558 # source and target containers. From this point the container won't change,
559 # so metadata can be added here.
560 if opts.addmetadata or opts.addchapters or opts.embed_infojson:
561 if opts.embed_infojson is None:
562 opts.embed_infojson = 'if_exists'
563 postprocessors.append({
564 'key': 'FFmpegMetadata',
565 'add_chapters': opts.addchapters,
566 'add_metadata': opts.addmetadata,
567 'add_infojson': opts.embed_infojson,
568 })
569 # Deprecated
570 # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
571 # but must be below EmbedSubtitle and FFmpegMetadata
572 # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
573 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
574 if opts.sponskrub is not False:
575 postprocessors.append({
576 'key': 'SponSkrub',
577 'path': opts.sponskrub_path,
578 'args': opts.sponskrub_args,
579 'cut': opts.sponskrub_cut,
580 'force': opts.sponskrub_force,
581 'ignoreerror': opts.sponskrub is None,
582 '_from_cli': True,
583 })
584 if opts.embedthumbnail:
585 postprocessors.append({
586 'key': 'EmbedThumbnail',
587 # already_have_thumbnail = True prevents the file from being deleted after embedding
588 'already_have_thumbnail': opts.writethumbnail
589 })
590 if not opts.writethumbnail:
591 opts.writethumbnail = True
592 opts.outtmpl['pl_thumbnail'] = ''
593 if opts.split_chapters:
594 postprocessors.append({
595 'key': 'FFmpegSplitChapters',
596 'force_keyframes': opts.force_keyframes_at_cuts,
597 })
598 # XAttrMetadataPP should be run after post-processors that may change file contents
599 if opts.xattrs:
600 postprocessors.append({'key': 'XAttrMetadata'})
601 if opts.concat_playlist != 'never':
602 postprocessors.append({
603 'key': 'FFmpegConcat',
604 'only_multi_video': opts.concat_playlist != 'always',
605 'when': 'playlist',
606 })
607 # Exec must be the last PP of each category
608 if opts.exec_before_dl_cmd:
609 opts.exec_cmd.setdefault('before_dl', opts.exec_before_dl_cmd)
610 for when, exec_cmd in opts.exec_cmd.items():
611 postprocessors.append({
612 'key': 'Exec',
613 'exec_cmd': exec_cmd,
614 # Run this only after the files have been moved to their final locations
615 'when': when,
616 })
617
618 def report_args_compat(arg, name):
619 warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
620
621 if 'default' in opts.external_downloader_args:
622 report_args_compat('--downloader-args', 'external downloaders')
623
624 if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
625 report_args_compat('--post-processor-args', 'post-processors')
626 opts.postprocessor_args.setdefault('sponskrub', [])
627 opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
628
629 def report_deprecation(val, old, new=None):
630 if not val:
631 return
632 deprecation_warnings.append(
633 f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
634 else f'{old} is deprecated and may not work as expected')
635
636 report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
637 report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
638 report_deprecation(opts.include_ads, '--include-ads')
639 # report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
640 # report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
641
642 final_ext = (
643 opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
644 else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
645 else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
646 else None)
647
648 match_filter = (
649 None if opts.match_filter is None
650 else match_filter_func(opts.match_filter))
651
652 ydl_opts = {
653 'usenetrc': opts.usenetrc,
654 'netrc_location': opts.netrc_location,
655 'username': opts.username,
656 'password': opts.password,
657 'twofactor': opts.twofactor,
658 'videopassword': opts.videopassword,
659 'ap_mso': opts.ap_mso,
660 'ap_username': opts.ap_username,
661 'ap_password': opts.ap_password,
662 'quiet': (opts.quiet or any_getting or any_printing),
663 'no_warnings': opts.no_warnings,
664 'forceurl': opts.geturl,
665 'forcetitle': opts.gettitle,
666 'forceid': opts.getid,
667 'forcethumbnail': opts.getthumbnail,
668 'forcedescription': opts.getdescription,
669 'forceduration': opts.getduration,
670 'forcefilename': opts.getfilename,
671 'forceformat': opts.getformat,
672 'forceprint': opts.forceprint,
673 'print_to_file': opts.print_to_file,
674 'forcejson': opts.dumpjson or opts.print_json,
675 'dump_single_json': opts.dump_single_json,
676 'force_write_download_archive': opts.force_write_download_archive,
677 'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
678 'skip_download': opts.skip_download,
679 'format': opts.format,
680 'allow_unplayable_formats': opts.allow_unplayable_formats,
681 'ignore_no_formats_error': opts.ignore_no_formats_error,
682 'format_sort': opts.format_sort,
683 'format_sort_force': opts.format_sort_force,
684 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
685 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
686 'check_formats': opts.check_formats,
687 'listformats': opts.listformats,
688 'listformats_table': opts.listformats_table,
689 'outtmpl': opts.outtmpl,
690 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
691 'paths': opts.paths,
692 'autonumber_size': opts.autonumber_size,
693 'autonumber_start': opts.autonumber_start,
694 'restrictfilenames': opts.restrictfilenames,
695 'windowsfilenames': opts.windowsfilenames,
696 'ignoreerrors': opts.ignoreerrors,
697 'force_generic_extractor': opts.force_generic_extractor,
698 'ratelimit': opts.ratelimit,
699 'throttledratelimit': opts.throttledratelimit,
700 'overwrites': opts.overwrites,
701 'retries': opts.retries,
702 'file_access_retries': opts.file_access_retries,
703 'fragment_retries': opts.fragment_retries,
704 'extractor_retries': opts.extractor_retries,
705 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
706 'keep_fragments': opts.keep_fragments,
707 'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
708 'buffersize': opts.buffersize,
709 'noresizebuffer': opts.noresizebuffer,
710 'http_chunk_size': opts.http_chunk_size,
711 'continuedl': opts.continue_dl,
712 'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
713 'progress_with_newline': opts.progress_with_newline,
714 'progress_template': opts.progress_template,
715 'playliststart': opts.playliststart,
716 'playlistend': opts.playlistend,
717 'playlistreverse': opts.playlist_reverse,
718 'playlistrandom': opts.playlist_random,
719 'noplaylist': opts.noplaylist,
720 'logtostderr': outtmpl_default == '-',
721 'consoletitle': opts.consoletitle,
722 'nopart': opts.nopart,
723 'updatetime': opts.updatetime,
724 'writedescription': opts.writedescription,
725 'writeannotations': opts.writeannotations,
726 'writeinfojson': opts.writeinfojson,
727 'allow_playlist_files': opts.allow_playlist_files,
728 'clean_infojson': opts.clean_infojson,
729 'getcomments': opts.getcomments,
730 'writethumbnail': opts.writethumbnail is True,
731 'write_all_thumbnails': opts.writethumbnail == 'all',
732 'writelink': opts.writelink,
733 'writeurllink': opts.writeurllink,
734 'writewebloclink': opts.writewebloclink,
735 'writedesktoplink': opts.writedesktoplink,
736 'writesubtitles': opts.writesubtitles,
737 'writeautomaticsub': opts.writeautomaticsub,
738 'allsubtitles': opts.allsubtitles,
739 'listsubtitles': opts.listsubtitles,
740 'subtitlesformat': opts.subtitlesformat,
741 'subtitleslangs': opts.subtitleslangs,
742 'matchtitle': decodeOption(opts.matchtitle),
743 'rejecttitle': decodeOption(opts.rejecttitle),
744 'max_downloads': opts.max_downloads,
745 'prefer_free_formats': opts.prefer_free_formats,
746 'trim_file_name': opts.trim_file_name,
747 'verbose': opts.verbose,
748 'dump_intermediate_pages': opts.dump_intermediate_pages,
749 'write_pages': opts.write_pages,
750 'test': opts.test,
751 'keepvideo': opts.keepvideo,
752 'min_filesize': opts.min_filesize,
753 'max_filesize': opts.max_filesize,
754 'min_views': opts.min_views,
755 'max_views': opts.max_views,
756 'daterange': date,
757 'cachedir': opts.cachedir,
758 'youtube_print_sig_code': opts.youtube_print_sig_code,
759 'age_limit': opts.age_limit,
760 'download_archive': download_archive_fn,
761 'break_on_existing': opts.break_on_existing,
762 'break_on_reject': opts.break_on_reject,
763 'break_per_url': opts.break_per_url,
764 'skip_playlist_after_errors': opts.skip_playlist_after_errors,
765 'cookiefile': opts.cookiefile,
766 'cookiesfrombrowser': opts.cookiesfrombrowser,
767 'legacyserverconnect': opts.legacy_server_connect,
768 'nocheckcertificate': opts.no_check_certificate,
769 'prefer_insecure': opts.prefer_insecure,
770 'proxy': opts.proxy,
771 'socket_timeout': opts.socket_timeout,
772 'bidi_workaround': opts.bidi_workaround,
773 'debug_printtraffic': opts.debug_printtraffic,
774 'prefer_ffmpeg': opts.prefer_ffmpeg,
775 'include_ads': opts.include_ads,
776 'default_search': opts.default_search,
777 'dynamic_mpd': opts.dynamic_mpd,
778 'extractor_args': opts.extractor_args,
779 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
780 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
781 'encoding': opts.encoding,
782 'extract_flat': opts.extract_flat,
783 'live_from_start': opts.live_from_start,
784 'wait_for_video': opts.wait_for_video,
785 'mark_watched': opts.mark_watched,
786 'merge_output_format': opts.merge_output_format,
787 'final_ext': final_ext,
788 'postprocessors': postprocessors,
789 'fixup': opts.fixup,
790 'source_address': opts.source_address,
791 'call_home': opts.call_home,
792 'sleep_interval_requests': opts.sleep_interval_requests,
793 'sleep_interval': opts.sleep_interval,
794 'max_sleep_interval': opts.max_sleep_interval,
795 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
796 'external_downloader': opts.external_downloader,
797 'list_thumbnails': opts.list_thumbnails,
798 'playlist_items': opts.playlist_items,
799 'xattr_set_filesize': opts.xattr_set_filesize,
800 'match_filter': match_filter,
801 'no_color': opts.no_color,
802 'ffmpeg_location': opts.ffmpeg_location,
803 'hls_prefer_native': opts.hls_prefer_native,
804 'hls_use_mpegts': opts.hls_use_mpegts,
805 'hls_split_discontinuity': opts.hls_split_discontinuity,
806 'external_downloader_args': opts.external_downloader_args,
807 'postprocessor_args': opts.postprocessor_args,
808 'cn_verification_proxy': opts.cn_verification_proxy,
809 'geo_verification_proxy': opts.geo_verification_proxy,
810 'geo_bypass': opts.geo_bypass,
811 'geo_bypass_country': opts.geo_bypass_country,
812 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
813 '_warnings': warnings,
814 '_deprecation_warnings': deprecation_warnings,
815 'compat_opts': compat_opts,
816 }
817
818 with YoutubeDL(ydl_opts) as ydl:
819 actual_use = all_urls or opts.load_info_filename
820
821 # Remove cache dir
822 if opts.rm_cachedir:
823 ydl.cache.remove()
824
825 # Update version
826 if opts.update_self:
827 # If updater returns True, exit. Required for windows
828 if run_update(ydl):
829 if actual_use:
830 sys.exit('ERROR: The program must exit for the update to complete')
831 sys.exit()
832
833 # Maybe do nothing
834 if not actual_use:
835 if opts.update_self or opts.rm_cachedir:
836 sys.exit()
837
838 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
839 parser.error(
840 'You must provide at least one URL.\n'
841 'Type yt-dlp --help to see a list of all options.')
842
843 try:
844 if opts.load_info_filename is not None:
845 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
846 else:
847 retcode = ydl.download(all_urls)
848 except DownloadCancelled:
849 ydl.to_screen('Aborting remaining downloads')
850 retcode = 101
851
852 sys.exit(retcode)
853
854
855 def main(argv=None):
856 try:
857 _real_main(argv)
858 except DownloadError:
859 sys.exit(1)
860 except SameFileError as e:
861 sys.exit(f'ERROR: {e}')
862 except KeyboardInterrupt:
863 sys.exit('\nERROR: Interrupted by user')
864 except BrokenPipeError as e:
865 # https://docs.python.org/3/library/signal.html#note-on-sigpipe
866 devnull = os.open(os.devnull, os.O_WRONLY)
867 os.dup2(devnull, sys.stdout.fileno())
868 sys.exit(f'\nERROR: {e}')
869
870
871 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']