]> jfr.im git - yt-dlp.git/blob - yt_dlp/__init__.py
Release 2021.12.01
[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_shlex_quote,
22 workaround_optparse_bug9161,
23 )
24 from .cookies import SUPPORTED_BROWSERS
25 from .utils import (
26 DateRange,
27 decodeOption,
28 DownloadCancelled,
29 DownloadError,
30 error_to_compat_str,
31 expand_path,
32 GeoUtils,
33 float_or_none,
34 int_or_none,
35 match_filter_func,
36 parse_duration,
37 preferredencoding,
38 read_batch_urls,
39 render_table,
40 SameFileError,
41 setproctitle,
42 std_headers,
43 write_string,
44 )
45 from .update import run_update
46 from .downloader import (
47 FileDownloader,
48 )
49 from .extractor import gen_extractors, list_extractors
50 from .extractor.common import InfoExtractor
51 from .extractor.adobepass import MSO_INFO
52 from .postprocessor import (
53 FFmpegExtractAudioPP,
54 FFmpegSubtitlesConvertorPP,
55 FFmpegThumbnailsConvertorPP,
56 FFmpegVideoConvertorPP,
57 FFmpegVideoRemuxerPP,
58 MetadataFromFieldPP,
59 MetadataParserPP,
60 )
61 from .YoutubeDL import YoutubeDL
62
63
64 def _real_main(argv=None):
65 # Compatibility fixes for Windows
66 if sys.platform == 'win32':
67 # https://github.com/ytdl-org/youtube-dl/issues/820
68 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
69
70 workaround_optparse_bug9161()
71
72 setproctitle('yt-dlp')
73
74 parser, opts, args = parseOpts(argv)
75 warnings, deprecation_warnings = [], []
76
77 # Set user agent
78 if opts.user_agent is not None:
79 std_headers['User-Agent'] = opts.user_agent
80
81 # Set referer
82 if opts.referer is not None:
83 std_headers['Referer'] = opts.referer
84
85 # Custom HTTP headers
86 std_headers.update(opts.headers)
87
88 # Dump user agent
89 if opts.dump_user_agent:
90 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
91 sys.exit(0)
92
93 # Batch file verification
94 batch_urls = []
95 if opts.batchfile is not None:
96 try:
97 if opts.batchfile == '-':
98 write_string('Reading URLs from stdin:\n')
99 batchfd = sys.stdin
100 else:
101 batchfd = io.open(
102 expand_path(opts.batchfile),
103 'r', encoding='utf-8', errors='ignore')
104 batch_urls = read_batch_urls(batchfd)
105 if opts.verbose:
106 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
107 except IOError:
108 sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
109 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
110 _enc = preferredencoding()
111 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
112
113 if opts.list_extractors:
114 for ie in list_extractors(opts.age_limit):
115 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n', out=sys.stdout)
116 matchedUrls = [url for url in all_urls if ie.suitable(url)]
117 for mu in matchedUrls:
118 write_string(' ' + mu + '\n', out=sys.stdout)
119 sys.exit(0)
120 if opts.list_extractor_descriptions:
121 for ie in list_extractors(opts.age_limit):
122 if not ie.working():
123 continue
124 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
125 if desc is False:
126 continue
127 if getattr(ie, 'SEARCH_KEY', None) is not None:
128 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
129 _COUNTS = ('', '5', '10', 'all')
130 desc += f'; "{ie.SEARCH_KEY}:" prefix (Example: "{ie.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(_SEARCHES)}")'
131 write_string(desc + '\n', out=sys.stdout)
132 sys.exit(0)
133 if opts.ap_list_mso:
134 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
135 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
136 sys.exit(0)
137
138 # Conflicting, missing and erroneous options
139 if opts.usenetrc and (opts.username is not None or opts.password is not None):
140 parser.error('using .netrc conflicts with giving username/password')
141 if opts.password is not None and opts.username is None:
142 parser.error('account username missing\n')
143 if opts.ap_password is not None and opts.ap_username is None:
144 parser.error('TV Provider account username missing\n')
145 if opts.autonumber_size is not None:
146 if opts.autonumber_size <= 0:
147 parser.error('auto number size must be positive')
148 if opts.autonumber_start is not None:
149 if opts.autonumber_start < 0:
150 parser.error('auto number start must be positive or 0')
151 if opts.username is not None and opts.password is None:
152 opts.password = compat_getpass('Type account password and press [Return]: ')
153 if opts.ap_username is not None and opts.ap_password is None:
154 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
155 if opts.ratelimit is not None:
156 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
157 if numeric_limit is None:
158 parser.error('invalid rate limit specified')
159 opts.ratelimit = numeric_limit
160 if opts.throttledratelimit is not None:
161 numeric_limit = FileDownloader.parse_bytes(opts.throttledratelimit)
162 if numeric_limit is None:
163 parser.error('invalid rate limit specified')
164 opts.throttledratelimit = numeric_limit
165 if opts.min_filesize is not None:
166 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
167 if numeric_limit is None:
168 parser.error('invalid min_filesize specified')
169 opts.min_filesize = numeric_limit
170 if opts.max_filesize is not None:
171 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
172 if numeric_limit is None:
173 parser.error('invalid max_filesize specified')
174 opts.max_filesize = numeric_limit
175 if opts.sleep_interval is not None:
176 if opts.sleep_interval < 0:
177 parser.error('sleep interval must be positive or 0')
178 if opts.max_sleep_interval is not None:
179 if opts.max_sleep_interval < 0:
180 parser.error('max sleep interval must be positive or 0')
181 if opts.sleep_interval is None:
182 parser.error('min sleep interval must be specified, use --min-sleep-interval')
183 if opts.max_sleep_interval < opts.sleep_interval:
184 parser.error('max sleep interval must be greater than or equal to min sleep interval')
185 else:
186 opts.max_sleep_interval = opts.sleep_interval
187 if opts.sleep_interval_subtitles is not None:
188 if opts.sleep_interval_subtitles < 0:
189 parser.error('subtitles sleep interval must be positive or 0')
190 if opts.sleep_interval_requests is not None:
191 if opts.sleep_interval_requests < 0:
192 parser.error('requests sleep interval must be positive or 0')
193 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
194 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
195 if opts.overwrites: # --yes-overwrites implies --no-continue
196 opts.continue_dl = False
197 if opts.concurrent_fragment_downloads <= 0:
198 parser.error('Concurrent fragments must be positive')
199 if opts.wait_for_video is not None:
200 mobj = re.match(r'(?P<min>\d+)(?:-(?P<max>\d+))?$', opts.wait_for_video)
201 if not mobj:
202 parser.error('Invalid time range to wait')
203 min_wait, max_wait = map(int_or_none, mobj.group('min', 'max'))
204 if max_wait is not None and max_wait < min_wait:
205 parser.error('Invalid time range to wait')
206 opts.wait_for_video = (min_wait, max_wait)
207
208 def parse_retries(retries, name=''):
209 if retries in ('inf', 'infinite'):
210 parsed_retries = float('inf')
211 else:
212 try:
213 parsed_retries = int(retries)
214 except (TypeError, ValueError):
215 parser.error('invalid %sretry count specified' % name)
216 return parsed_retries
217 if opts.retries is not None:
218 opts.retries = parse_retries(opts.retries)
219 if opts.fragment_retries is not None:
220 opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
221 if opts.extractor_retries is not None:
222 opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
223 if opts.buffersize is not None:
224 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
225 if numeric_buffersize is None:
226 parser.error('invalid buffer size specified')
227 opts.buffersize = numeric_buffersize
228 if opts.http_chunk_size is not None:
229 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
230 if not numeric_chunksize:
231 parser.error('invalid http chunk size specified')
232 opts.http_chunk_size = numeric_chunksize
233 if opts.playliststart <= 0:
234 raise parser.error('Playlist start must be positive')
235 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
236 raise parser.error('Playlist end must be greater than playlist start')
237 if opts.extractaudio:
238 opts.audioformat = opts.audioformat.lower()
239 if opts.audioformat not in ['best'] + list(FFmpegExtractAudioPP.SUPPORTED_EXTS):
240 parser.error('invalid audio format specified')
241 if opts.audioquality:
242 opts.audioquality = opts.audioquality.strip('k').strip('K')
243 audioquality = int_or_none(float_or_none(opts.audioquality)) # int_or_none prevents inf, nan
244 if audioquality is None or audioquality < 0:
245 parser.error('invalid audio quality specified')
246 if opts.recodevideo is not None:
247 opts.recodevideo = opts.recodevideo.replace(' ', '')
248 if not re.match(FFmpegVideoConvertorPP.FORMAT_RE, opts.recodevideo):
249 parser.error('invalid video remux format specified')
250 if opts.remuxvideo is not None:
251 opts.remuxvideo = opts.remuxvideo.replace(' ', '')
252 if not re.match(FFmpegVideoRemuxerPP.FORMAT_RE, opts.remuxvideo):
253 parser.error('invalid video remux format specified')
254 if opts.convertsubtitles is not None:
255 if opts.convertsubtitles not in FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS:
256 parser.error('invalid subtitle format specified')
257 if opts.convertthumbnails is not None:
258 if opts.convertthumbnails not in FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS:
259 parser.error('invalid thumbnail format specified')
260 if opts.cookiesfrombrowser is not None:
261 opts.cookiesfrombrowser = [
262 part.strip() or None for part in opts.cookiesfrombrowser.split(':', 1)]
263 if opts.cookiesfrombrowser[0].lower() not in SUPPORTED_BROWSERS:
264 parser.error('unsupported browser specified for cookies')
265 geo_bypass_code = opts.geo_bypass_ip_block or opts.geo_bypass_country
266 if geo_bypass_code is not None:
267 try:
268 GeoUtils.random_ipv4(geo_bypass_code)
269 except Exception:
270 parser.error('unsupported geo-bypass country or ip-block')
271
272 if opts.date is not None:
273 date = DateRange.day(opts.date)
274 else:
275 date = DateRange(opts.dateafter, opts.datebefore)
276
277 compat_opts = opts.compat_opts
278
279 def report_conflict(arg1, arg2):
280 warnings.append(f'{arg2} is ignored since {arg1} was given')
281
282 def _unused_compat_opt(name):
283 if name not in compat_opts:
284 return False
285 compat_opts.discard(name)
286 compat_opts.update(['*%s' % name])
287 return True
288
289 def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
290 attr = getattr(opts, opt_name)
291 if compat_name in compat_opts:
292 if attr is None:
293 setattr(opts, opt_name, not default)
294 return True
295 else:
296 if remove_compat:
297 _unused_compat_opt(compat_name)
298 return False
299 elif attr is None:
300 setattr(opts, opt_name, default)
301 return None
302
303 set_default_compat('abort-on-error', 'ignoreerrors', 'only_download')
304 set_default_compat('no-playlist-metafiles', 'allow_playlist_files')
305 set_default_compat('no-clean-infojson', 'clean_infojson')
306 if 'no-attach-info-json' in compat_opts:
307 if opts.embed_infojson:
308 _unused_compat_opt('no-attach-info-json')
309 else:
310 opts.embed_infojson = False
311 if 'format-sort' in compat_opts:
312 opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
313 _video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
314 _audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
315 if _video_multistreams_set is False and _audio_multistreams_set is False:
316 _unused_compat_opt('multistreams')
317 outtmpl_default = opts.outtmpl.get('default')
318 if opts.useid:
319 if outtmpl_default is None:
320 outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
321 else:
322 report_conflict('--output', '--id')
323 if 'filename' in compat_opts:
324 if outtmpl_default is None:
325 outtmpl_default = opts.outtmpl['default'] = '%(title)s-%(id)s.%(ext)s'
326 else:
327 _unused_compat_opt('filename')
328
329 def validate_outtmpl(tmpl, msg):
330 err = YoutubeDL.validate_outtmpl(tmpl)
331 if err:
332 parser.error('invalid %s %r: %s' % (msg, tmpl, error_to_compat_str(err)))
333
334 for k, tmpl in opts.outtmpl.items():
335 validate_outtmpl(tmpl, f'{k} output template')
336 opts.forceprint = opts.forceprint or []
337 for tmpl in opts.forceprint or []:
338 validate_outtmpl(tmpl, 'print template')
339 validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
340 for k, tmpl in opts.progress_template.items():
341 k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
342 validate_outtmpl(tmpl, f'{k} template')
343
344 if opts.extractaudio and not opts.keepvideo and opts.format is None:
345 opts.format = 'bestaudio/best'
346
347 if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
348 parser.error('Cannot download a video and extract audio into the same'
349 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
350 ' template'.format(outtmpl_default))
351
352 for f in opts.format_sort:
353 if re.match(InfoExtractor.FormatSort.regex, f) is None:
354 parser.error('invalid format sort string "%s" specified' % f)
355
356 def metadataparser_actions(f):
357 if isinstance(f, str):
358 cmd = '--parse-metadata %s' % compat_shlex_quote(f)
359 try:
360 actions = [MetadataFromFieldPP.to_action(f)]
361 except Exception as err:
362 parser.error(f'{cmd} is invalid; {err}')
363 else:
364 cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
365 actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
366
367 for action in actions:
368 try:
369 MetadataParserPP.validate_action(*action)
370 except Exception as err:
371 parser.error(f'{cmd} is invalid; {err}')
372 yield action
373
374 if opts.parse_metadata is None:
375 opts.parse_metadata = []
376 if opts.metafromtitle is not None:
377 opts.parse_metadata.append('title:%s' % opts.metafromtitle)
378 opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, opts.parse_metadata)))
379
380 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
381 any_printing = opts.print_json
382 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
383
384 # If JSON is not printed anywhere, but comments are requested, save it to file
385 printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
386 if opts.getcomments and not printing_json:
387 opts.writeinfojson = True
388
389 if opts.no_sponsorblock:
390 opts.sponsorblock_mark = set()
391 opts.sponsorblock_remove = set()
392 sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
393
394 opts.remove_chapters = opts.remove_chapters or []
395
396 if (opts.remove_chapters or sponsorblock_query) and opts.sponskrub is not False:
397 if opts.sponskrub:
398 if opts.remove_chapters:
399 report_conflict('--remove-chapters', '--sponskrub')
400 if opts.sponsorblock_mark:
401 report_conflict('--sponsorblock-mark', '--sponskrub')
402 if opts.sponsorblock_remove:
403 report_conflict('--sponsorblock-remove', '--sponskrub')
404 opts.sponskrub = False
405 if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
406 report_conflict('--split-chapter', '--sponskrub-cut')
407 opts.sponskrub_cut = False
408
409 if opts.remuxvideo and opts.recodevideo:
410 report_conflict('--recode-video', '--remux-video')
411 opts.remuxvideo = False
412
413 if opts.allow_unplayable_formats:
414 def report_unplayable_conflict(opt_name, arg, default=False, allowed=None):
415 val = getattr(opts, opt_name)
416 if (not allowed and val) or (allowed and not allowed(val)):
417 report_conflict('--allow-unplayable-formats', arg)
418 setattr(opts, opt_name, default)
419
420 report_unplayable_conflict('extractaudio', '--extract-audio')
421 report_unplayable_conflict('remuxvideo', '--remux-video')
422 report_unplayable_conflict('recodevideo', '--recode-video')
423 report_unplayable_conflict('addmetadata', '--embed-metadata')
424 report_unplayable_conflict('addchapters', '--embed-chapters')
425 report_unplayable_conflict('embed_infojson', '--embed-info-json')
426 opts.embed_infojson = False
427 report_unplayable_conflict('embedsubtitles', '--embed-subs')
428 report_unplayable_conflict('embedthumbnail', '--embed-thumbnail')
429 report_unplayable_conflict('xattrs', '--xattrs')
430 report_unplayable_conflict('fixup', '--fixup', default='never', allowed=lambda x: x in (None, 'never', 'ignore'))
431 opts.fixup = 'never'
432 report_unplayable_conflict('remove_chapters', '--remove-chapters', default=[])
433 report_unplayable_conflict('sponsorblock_remove', '--sponsorblock-remove', default=set())
434 report_unplayable_conflict('sponskrub', '--sponskrub', default=set())
435 opts.sponskrub = False
436
437 if (opts.addmetadata or opts.sponsorblock_mark) and opts.addchapters is None:
438 opts.addchapters = True
439
440 # PostProcessors
441 postprocessors = list(opts.add_postprocessors)
442 if sponsorblock_query:
443 postprocessors.append({
444 'key': 'SponsorBlock',
445 'categories': sponsorblock_query,
446 'api': opts.sponsorblock_api,
447 # Run this immediately after extraction is complete
448 'when': 'pre_process'
449 })
450 if opts.parse_metadata:
451 postprocessors.append({
452 'key': 'MetadataParser',
453 'actions': opts.parse_metadata,
454 # Run this immediately after extraction is complete
455 'when': 'pre_process'
456 })
457 if opts.convertsubtitles:
458 postprocessors.append({
459 'key': 'FFmpegSubtitlesConvertor',
460 'format': opts.convertsubtitles,
461 # Run this before the actual video download
462 'when': 'before_dl'
463 })
464 if opts.convertthumbnails:
465 postprocessors.append({
466 'key': 'FFmpegThumbnailsConvertor',
467 'format': opts.convertthumbnails,
468 # Run this before the actual video download
469 'when': 'before_dl'
470 })
471 # Must be after all other before_dl
472 if opts.exec_before_dl_cmd:
473 postprocessors.append({
474 'key': 'Exec',
475 'exec_cmd': opts.exec_before_dl_cmd,
476 'when': 'before_dl'
477 })
478 if opts.extractaudio:
479 postprocessors.append({
480 'key': 'FFmpegExtractAudio',
481 'preferredcodec': opts.audioformat,
482 'preferredquality': opts.audioquality,
483 'nopostoverwrites': opts.nopostoverwrites,
484 })
485 if opts.remuxvideo:
486 postprocessors.append({
487 'key': 'FFmpegVideoRemuxer',
488 'preferedformat': opts.remuxvideo,
489 })
490 if opts.recodevideo:
491 postprocessors.append({
492 'key': 'FFmpegVideoConvertor',
493 'preferedformat': opts.recodevideo,
494 })
495 # If ModifyChapters is going to remove chapters, subtitles must already be in the container.
496 if opts.embedsubtitles:
497 already_have_subtitle = opts.writesubtitles and 'no-keep-subs' not in compat_opts
498 postprocessors.append({
499 'key': 'FFmpegEmbedSubtitle',
500 # already_have_subtitle = True prevents the file from being deleted after embedding
501 'already_have_subtitle': already_have_subtitle
502 })
503 if not opts.writeautomaticsub and 'no-keep-subs' not in compat_opts:
504 opts.writesubtitles = True
505 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
506 # this was the old behaviour if only --all-sub was given.
507 if opts.allsubtitles and not opts.writeautomaticsub:
508 opts.writesubtitles = True
509 # ModifyChapters must run before FFmpegMetadataPP
510 remove_chapters_patterns, remove_ranges = [], []
511 for regex in opts.remove_chapters:
512 if regex.startswith('*'):
513 dur = list(map(parse_duration, regex[1:].split('-')))
514 if len(dur) == 2 and all(t is not None for t in dur):
515 remove_ranges.append(tuple(dur))
516 continue
517 parser.error(f'invalid --remove-chapters time range {regex!r}. Must be of the form ?start-end')
518 try:
519 remove_chapters_patterns.append(re.compile(regex))
520 except re.error as err:
521 parser.error(f'invalid --remove-chapters regex {regex!r} - {err}')
522 if opts.remove_chapters or sponsorblock_query:
523 postprocessors.append({
524 'key': 'ModifyChapters',
525 'remove_chapters_patterns': remove_chapters_patterns,
526 'remove_sponsor_segments': opts.sponsorblock_remove,
527 'remove_ranges': remove_ranges,
528 'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
529 'force_keyframes': opts.force_keyframes_at_cuts
530 })
531 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
532 # FFmpegExtractAudioPP as containers before conversion may not support
533 # metadata (3gp, webm, etc.)
534 # By default ffmpeg preserves metadata applicable for both
535 # source and target containers. From this point the container won't change,
536 # so metadata can be added here.
537 if opts.addmetadata or opts.addchapters or opts.embed_infojson:
538 if opts.embed_infojson is None:
539 opts.embed_infojson = 'if_exists'
540 postprocessors.append({
541 'key': 'FFmpegMetadata',
542 'add_chapters': opts.addchapters,
543 'add_metadata': opts.addmetadata,
544 'add_infojson': opts.embed_infojson,
545 })
546 # Deprecated
547 # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
548 # but must be below EmbedSubtitle and FFmpegMetadata
549 # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
550 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
551 if opts.sponskrub is not False:
552 postprocessors.append({
553 'key': 'SponSkrub',
554 'path': opts.sponskrub_path,
555 'args': opts.sponskrub_args,
556 'cut': opts.sponskrub_cut,
557 'force': opts.sponskrub_force,
558 'ignoreerror': opts.sponskrub is None,
559 '_from_cli': True,
560 })
561 if opts.embedthumbnail:
562 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
563 postprocessors.append({
564 'key': 'EmbedThumbnail',
565 # already_have_thumbnail = True prevents the file from being deleted after embedding
566 'already_have_thumbnail': already_have_thumbnail
567 })
568 if not already_have_thumbnail:
569 opts.writethumbnail = True
570 opts.outtmpl['pl_thumbnail'] = ''
571 if opts.split_chapters:
572 postprocessors.append({
573 'key': 'FFmpegSplitChapters',
574 'force_keyframes': opts.force_keyframes_at_cuts,
575 })
576 # XAttrMetadataPP should be run after post-processors that may change file contents
577 if opts.xattrs:
578 postprocessors.append({'key': 'XAttrMetadata'})
579 # Exec must be the last PP
580 if opts.exec_cmd:
581 postprocessors.append({
582 'key': 'Exec',
583 'exec_cmd': opts.exec_cmd,
584 # Run this only after the files have been moved to their final locations
585 'when': 'after_move'
586 })
587
588 def report_args_compat(arg, name):
589 warnings.append('%s given without specifying name. The arguments will be given to all %s' % (arg, name))
590
591 if 'default' in opts.external_downloader_args:
592 report_args_compat('--downloader-args', 'external downloaders')
593
594 if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
595 report_args_compat('--post-processor-args', 'post-processors')
596 opts.postprocessor_args.setdefault('sponskrub', [])
597 opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
598
599 def report_deprecation(val, old, new=None):
600 if not val:
601 return
602 deprecation_warnings.append(
603 f'{old} is deprecated and may be removed in a future version. Use {new} instead' if new
604 else f'{old} is deprecated and may not work as expected')
605
606 report_deprecation(opts.sponskrub, '--sponskrub', '--sponsorblock-mark or --sponsorblock-remove')
607 report_deprecation(not opts.prefer_ffmpeg, '--prefer-avconv', 'ffmpeg')
608 report_deprecation(opts.include_ads, '--include-ads')
609 # report_deprecation(opts.call_home, '--call-home') # We may re-implement this in future
610 # report_deprecation(opts.writeannotations, '--write-annotations') # It's just that no website has it
611
612 final_ext = (
613 opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
614 else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
615 else opts.audioformat if (opts.extractaudio and opts.audioformat != 'best')
616 else None)
617
618 match_filter = (
619 None if opts.match_filter is None
620 else match_filter_func(opts.match_filter))
621
622 ydl_opts = {
623 'usenetrc': opts.usenetrc,
624 'netrc_location': opts.netrc_location,
625 'username': opts.username,
626 'password': opts.password,
627 'twofactor': opts.twofactor,
628 'videopassword': opts.videopassword,
629 'ap_mso': opts.ap_mso,
630 'ap_username': opts.ap_username,
631 'ap_password': opts.ap_password,
632 'quiet': (opts.quiet or any_getting or any_printing),
633 'no_warnings': opts.no_warnings,
634 'forceurl': opts.geturl,
635 'forcetitle': opts.gettitle,
636 'forceid': opts.getid,
637 'forcethumbnail': opts.getthumbnail,
638 'forcedescription': opts.getdescription,
639 'forceduration': opts.getduration,
640 'forcefilename': opts.getfilename,
641 'forceformat': opts.getformat,
642 'forceprint': opts.forceprint,
643 'forcejson': opts.dumpjson or opts.print_json,
644 'dump_single_json': opts.dump_single_json,
645 'force_write_download_archive': opts.force_write_download_archive,
646 'simulate': (any_getting or None) if opts.simulate is None else opts.simulate,
647 'skip_download': opts.skip_download,
648 'format': opts.format,
649 'allow_unplayable_formats': opts.allow_unplayable_formats,
650 'ignore_no_formats_error': opts.ignore_no_formats_error,
651 'format_sort': opts.format_sort,
652 'format_sort_force': opts.format_sort_force,
653 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
654 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
655 'check_formats': opts.check_formats,
656 'listformats': opts.listformats,
657 'listformats_table': opts.listformats_table,
658 'outtmpl': opts.outtmpl,
659 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
660 'paths': opts.paths,
661 'autonumber_size': opts.autonumber_size,
662 'autonumber_start': opts.autonumber_start,
663 'restrictfilenames': opts.restrictfilenames,
664 'windowsfilenames': opts.windowsfilenames,
665 'ignoreerrors': opts.ignoreerrors,
666 'force_generic_extractor': opts.force_generic_extractor,
667 'ratelimit': opts.ratelimit,
668 'throttledratelimit': opts.throttledratelimit,
669 'overwrites': opts.overwrites,
670 'retries': opts.retries,
671 'fragment_retries': opts.fragment_retries,
672 'extractor_retries': opts.extractor_retries,
673 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
674 'keep_fragments': opts.keep_fragments,
675 'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
676 'buffersize': opts.buffersize,
677 'noresizebuffer': opts.noresizebuffer,
678 'http_chunk_size': opts.http_chunk_size,
679 'continuedl': opts.continue_dl,
680 'noprogress': opts.quiet if opts.noprogress is None else opts.noprogress,
681 'progress_with_newline': opts.progress_with_newline,
682 'progress_template': opts.progress_template,
683 'playliststart': opts.playliststart,
684 'playlistend': opts.playlistend,
685 'playlistreverse': opts.playlist_reverse,
686 'playlistrandom': opts.playlist_random,
687 'noplaylist': opts.noplaylist,
688 'logtostderr': outtmpl_default == '-',
689 'consoletitle': opts.consoletitle,
690 'nopart': opts.nopart,
691 'updatetime': opts.updatetime,
692 'writedescription': opts.writedescription,
693 'writeannotations': opts.writeannotations,
694 'writeinfojson': opts.writeinfojson,
695 'allow_playlist_files': opts.allow_playlist_files,
696 'clean_infojson': opts.clean_infojson,
697 'getcomments': opts.getcomments,
698 'writethumbnail': opts.writethumbnail,
699 'write_all_thumbnails': opts.write_all_thumbnails,
700 'writelink': opts.writelink,
701 'writeurllink': opts.writeurllink,
702 'writewebloclink': opts.writewebloclink,
703 'writedesktoplink': opts.writedesktoplink,
704 'writesubtitles': opts.writesubtitles,
705 'writeautomaticsub': opts.writeautomaticsub,
706 'allsubtitles': opts.allsubtitles,
707 'listsubtitles': opts.listsubtitles,
708 'subtitlesformat': opts.subtitlesformat,
709 'subtitleslangs': opts.subtitleslangs,
710 'matchtitle': decodeOption(opts.matchtitle),
711 'rejecttitle': decodeOption(opts.rejecttitle),
712 'max_downloads': opts.max_downloads,
713 'prefer_free_formats': opts.prefer_free_formats,
714 'trim_file_name': opts.trim_file_name,
715 'verbose': opts.verbose,
716 'dump_intermediate_pages': opts.dump_intermediate_pages,
717 'write_pages': opts.write_pages,
718 'test': opts.test,
719 'keepvideo': opts.keepvideo,
720 'min_filesize': opts.min_filesize,
721 'max_filesize': opts.max_filesize,
722 'min_views': opts.min_views,
723 'max_views': opts.max_views,
724 'daterange': date,
725 'cachedir': opts.cachedir,
726 'youtube_print_sig_code': opts.youtube_print_sig_code,
727 'age_limit': opts.age_limit,
728 'download_archive': download_archive_fn,
729 'break_on_existing': opts.break_on_existing,
730 'break_on_reject': opts.break_on_reject,
731 'break_per_url': opts.break_per_url,
732 'skip_playlist_after_errors': opts.skip_playlist_after_errors,
733 'cookiefile': opts.cookiefile,
734 'cookiesfrombrowser': opts.cookiesfrombrowser,
735 'nocheckcertificate': opts.no_check_certificate,
736 'prefer_insecure': opts.prefer_insecure,
737 'proxy': opts.proxy,
738 'socket_timeout': opts.socket_timeout,
739 'bidi_workaround': opts.bidi_workaround,
740 'debug_printtraffic': opts.debug_printtraffic,
741 'prefer_ffmpeg': opts.prefer_ffmpeg,
742 'include_ads': opts.include_ads,
743 'default_search': opts.default_search,
744 'dynamic_mpd': opts.dynamic_mpd,
745 'extractor_args': opts.extractor_args,
746 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
747 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
748 'encoding': opts.encoding,
749 'extract_flat': opts.extract_flat,
750 'wait_for_video': opts.wait_for_video,
751 'mark_watched': opts.mark_watched,
752 'merge_output_format': opts.merge_output_format,
753 'final_ext': final_ext,
754 'postprocessors': postprocessors,
755 'fixup': opts.fixup,
756 'source_address': opts.source_address,
757 'call_home': opts.call_home,
758 'sleep_interval_requests': opts.sleep_interval_requests,
759 'sleep_interval': opts.sleep_interval,
760 'max_sleep_interval': opts.max_sleep_interval,
761 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
762 'external_downloader': opts.external_downloader,
763 'list_thumbnails': opts.list_thumbnails,
764 'playlist_items': opts.playlist_items,
765 'xattr_set_filesize': opts.xattr_set_filesize,
766 'match_filter': match_filter,
767 'no_color': opts.no_color,
768 'ffmpeg_location': opts.ffmpeg_location,
769 'hls_prefer_native': opts.hls_prefer_native,
770 'hls_use_mpegts': opts.hls_use_mpegts,
771 'hls_split_discontinuity': opts.hls_split_discontinuity,
772 'external_downloader_args': opts.external_downloader_args,
773 'postprocessor_args': opts.postprocessor_args,
774 'cn_verification_proxy': opts.cn_verification_proxy,
775 'geo_verification_proxy': opts.geo_verification_proxy,
776 'geo_bypass': opts.geo_bypass,
777 'geo_bypass_country': opts.geo_bypass_country,
778 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
779 '_warnings': warnings,
780 '_deprecation_warnings': deprecation_warnings,
781 'compat_opts': compat_opts,
782 }
783
784 with YoutubeDL(ydl_opts) as ydl:
785 actual_use = all_urls or opts.load_info_filename
786
787 # Remove cache dir
788 if opts.rm_cachedir:
789 ydl.cache.remove()
790
791 # Update version
792 if opts.update_self:
793 # If updater returns True, exit. Required for windows
794 if run_update(ydl):
795 if actual_use:
796 sys.exit('ERROR: The program must exit for the update to complete')
797 sys.exit()
798
799 # Maybe do nothing
800 if not actual_use:
801 if opts.update_self or opts.rm_cachedir:
802 sys.exit()
803
804 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
805 parser.error(
806 'You must provide at least one URL.\n'
807 'Type yt-dlp --help to see a list of all options.')
808
809 try:
810 if opts.load_info_filename is not None:
811 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
812 else:
813 retcode = ydl.download(all_urls)
814 except DownloadCancelled:
815 ydl.to_screen('Aborting remaining downloads')
816 retcode = 101
817
818 sys.exit(retcode)
819
820
821 def main(argv=None):
822 try:
823 _real_main(argv)
824 except DownloadError:
825 sys.exit(1)
826 except SameFileError as e:
827 sys.exit(f'ERROR: {e}')
828 except KeyboardInterrupt:
829 sys.exit('\nERROR: Interrupted by user')
830 except BrokenPipeError as e:
831 # https://docs.python.org/3/library/signal.html#note-on-sigpipe
832 devnull = os.open(os.devnull, os.O_WRONLY)
833 os.dup2(devnull, sys.stdout.fileno())
834 sys.exit(f'\nERROR: {e}')
835
836
837 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']