]> jfr.im git - yt-dlp.git/blob - youtube_dlc/__init__.py
Added `--force-overwrites` option (https://github.com/ytdl-org/youtube-dl/pull/20405)
[yt-dlp.git] / youtube_dlc / __init__.py
1 #!/usr/bin/env python
2 # coding: utf-8
3
4 from __future__ import unicode_literals
5
6 __license__ = 'Public Domain'
7
8 import codecs
9 import io
10 import os
11 import re
12 import random
13 import sys
14
15
16 from .options import (
17 parseOpts,
18 )
19 from .compat import (
20 compat_getpass,
21 compat_shlex_split,
22 workaround_optparse_bug9161,
23 )
24 from .utils import (
25 DateRange,
26 decodeOption,
27 DEFAULT_OUTTMPL,
28 DownloadError,
29 expand_path,
30 match_filter_func,
31 MaxDownloadsReached,
32 preferredencoding,
33 read_batch_urls,
34 SameFileError,
35 setproctitle,
36 std_headers,
37 write_string,
38 render_table,
39 )
40 from .update import update_self
41 from .downloader import (
42 FileDownloader,
43 )
44 from .extractor import gen_extractors, list_extractors
45 from .extractor.common import InfoExtractor
46 from .extractor.adobepass import MSO_INFO
47 from .YoutubeDL import YoutubeDL
48
49
50 def _real_main(argv=None):
51 # Compatibility fixes for Windows
52 if sys.platform == 'win32':
53 # https://github.com/ytdl-org/youtube-dl/issues/820
54 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
55
56 workaround_optparse_bug9161()
57
58 setproctitle('youtube-dlc')
59
60 parser, opts, args = parseOpts(argv)
61
62 # Set user agent
63 if opts.user_agent is not None:
64 std_headers['User-Agent'] = opts.user_agent
65
66 # Set referer
67 if opts.referer is not None:
68 std_headers['Referer'] = opts.referer
69
70 # Custom HTTP headers
71 if opts.headers is not None:
72 for h in opts.headers:
73 if ':' not in h:
74 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
75 key, value = h.split(':', 1)
76 if opts.verbose:
77 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
78 std_headers[key] = value
79
80 # Dump user agent
81 if opts.dump_user_agent:
82 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
83 sys.exit(0)
84
85 # Batch file verification
86 batch_urls = []
87 if opts.batchfile is not None:
88 try:
89 if opts.batchfile == '-':
90 batchfd = sys.stdin
91 else:
92 batchfd = io.open(
93 expand_path(opts.batchfile),
94 'r', encoding='utf-8', errors='ignore')
95 batch_urls = read_batch_urls(batchfd)
96 if opts.verbose:
97 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
98 except IOError:
99 sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
100 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
101 _enc = preferredencoding()
102 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
103
104 if opts.list_extractors:
105 for ie in list_extractors(opts.age_limit):
106 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
107 matchedUrls = [url for url in all_urls if ie.suitable(url)]
108 for mu in matchedUrls:
109 write_string(' ' + mu + '\n', out=sys.stdout)
110 sys.exit(0)
111 if opts.list_extractor_descriptions:
112 for ie in list_extractors(opts.age_limit):
113 if not ie._WORKING:
114 continue
115 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
116 if desc is False:
117 continue
118 if hasattr(ie, 'SEARCH_KEY'):
119 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
120 _COUNTS = ('', '5', '10', 'all')
121 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
122 write_string(desc + '\n', out=sys.stdout)
123 sys.exit(0)
124 if opts.ap_list_mso:
125 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
126 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
127 sys.exit(0)
128
129 # Conflicting, missing and erroneous options
130 if opts.usenetrc and (opts.username is not None or opts.password is not None):
131 parser.error('using .netrc conflicts with giving username/password')
132 if opts.password is not None and opts.username is None:
133 parser.error('account username missing\n')
134 if opts.ap_password is not None and opts.ap_username is None:
135 parser.error('TV Provider account username missing\n')
136 if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
137 parser.error('using output template conflicts with using title, video ID or auto number')
138 if opts.autonumber_size is not None:
139 if opts.autonumber_size <= 0:
140 parser.error('auto number size must be positive')
141 if opts.autonumber_start is not None:
142 if opts.autonumber_start < 0:
143 parser.error('auto number start must be positive or 0')
144 if opts.usetitle and opts.useid:
145 parser.error('using title conflicts with using video ID')
146 if opts.username is not None and opts.password is None:
147 opts.password = compat_getpass('Type account password and press [Return]: ')
148 if opts.ap_username is not None and opts.ap_password is None:
149 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
150 if opts.ratelimit is not None:
151 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
152 if numeric_limit is None:
153 parser.error('invalid rate limit specified')
154 opts.ratelimit = numeric_limit
155 if opts.min_filesize is not None:
156 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
157 if numeric_limit is None:
158 parser.error('invalid min_filesize specified')
159 opts.min_filesize = numeric_limit
160 if opts.max_filesize is not None:
161 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
162 if numeric_limit is None:
163 parser.error('invalid max_filesize specified')
164 opts.max_filesize = numeric_limit
165 if opts.sleep_interval is not None:
166 if opts.sleep_interval < 0:
167 parser.error('sleep interval must be positive or 0')
168 if opts.max_sleep_interval is not None:
169 if opts.max_sleep_interval < 0:
170 parser.error('max sleep interval must be positive or 0')
171 if opts.sleep_interval is None:
172 parser.error('min sleep interval must be specified, use --min-sleep-interval')
173 if opts.max_sleep_interval < opts.sleep_interval:
174 parser.error('max sleep interval must be greater than or equal to min sleep interval')
175 else:
176 opts.max_sleep_interval = opts.sleep_interval
177 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
178 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
179 if opts.overwrites:
180 # --yes-overwrites implies --no-continue
181 opts.continue_dl = False
182
183 def parse_retries(retries):
184 if retries in ('inf', 'infinite'):
185 parsed_retries = float('inf')
186 else:
187 try:
188 parsed_retries = int(retries)
189 except (TypeError, ValueError):
190 parser.error('invalid retry count specified')
191 return parsed_retries
192 if opts.retries is not None:
193 opts.retries = parse_retries(opts.retries)
194 if opts.fragment_retries is not None:
195 opts.fragment_retries = parse_retries(opts.fragment_retries)
196 if opts.buffersize is not None:
197 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
198 if numeric_buffersize is None:
199 parser.error('invalid buffer size specified')
200 opts.buffersize = numeric_buffersize
201 if opts.http_chunk_size is not None:
202 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
203 if not numeric_chunksize:
204 parser.error('invalid http chunk size specified')
205 opts.http_chunk_size = numeric_chunksize
206 if opts.playliststart <= 0:
207 raise ValueError('Playlist start must be positive')
208 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
209 raise ValueError('Playlist end must be greater than playlist start')
210 if opts.extractaudio:
211 if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
212 parser.error('invalid audio format specified')
213 if opts.audioquality:
214 opts.audioquality = opts.audioquality.strip('k').strip('K')
215 if not opts.audioquality.isdigit():
216 parser.error('invalid audio quality specified')
217 if opts.remuxvideo is not None:
218 if opts.remuxvideo not in ['mp4', 'mkv']:
219 parser.error('invalid video container format specified')
220 if opts.recodevideo is not None:
221 if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
222 parser.error('invalid video recode format specified')
223 if opts.convertsubtitles is not None:
224 if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
225 parser.error('invalid subtitle format specified')
226
227 if opts.date is not None:
228 date = DateRange.day(opts.date)
229 else:
230 date = DateRange(opts.dateafter, opts.datebefore)
231
232 # Do not download videos when there are audio-only formats
233 if opts.extractaudio and not opts.keepvideo and opts.format is None:
234 opts.format = 'bestaudio/best'
235
236 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
237 # this was the old behaviour if only --all-sub was given.
238 if opts.allsubtitles and not opts.writeautomaticsub:
239 opts.writesubtitles = True
240
241 outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
242 or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
243 or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
244 or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
245 or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
246 or (opts.useid and '%(id)s.%(ext)s')
247 or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
248 or DEFAULT_OUTTMPL)
249 if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
250 parser.error('Cannot download a video and extract audio into the same'
251 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
252 ' template'.format(outtmpl))
253 for f in opts.format_sort:
254 if re.match(InfoExtractor.FormatSort.regex, f) is None:
255 parser.error('invalid format sort string "%s" specified' % f)
256
257 any_getting = 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
258 any_printing = opts.print_json
259 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
260
261 # PostProcessors
262 postprocessors = []
263 if opts.metafromtitle:
264 postprocessors.append({
265 'key': 'MetadataFromTitle',
266 'titleformat': opts.metafromtitle
267 })
268 if opts.extractaudio:
269 postprocessors.append({
270 'key': 'FFmpegExtractAudio',
271 'preferredcodec': opts.audioformat,
272 'preferredquality': opts.audioquality,
273 'nopostoverwrites': opts.nopostoverwrites,
274 })
275 if opts.remuxvideo:
276 postprocessors.append({
277 'key': 'FFmpegVideoRemuxer',
278 'preferedformat': opts.remuxvideo,
279 })
280 if opts.recodevideo:
281 postprocessors.append({
282 'key': 'FFmpegVideoConvertor',
283 'preferedformat': opts.recodevideo,
284 })
285 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
286 # FFmpegExtractAudioPP as containers before conversion may not support
287 # metadata (3gp, webm, etc.)
288 # And this post-processor should be placed before other metadata
289 # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
290 # extra metadata. By default ffmpeg preserves metadata applicable for both
291 # source and target containers. From this point the container won't change,
292 # so metadata can be added here.
293 if opts.addmetadata:
294 postprocessors.append({'key': 'FFmpegMetadata'})
295 if opts.convertsubtitles:
296 postprocessors.append({
297 'key': 'FFmpegSubtitlesConvertor',
298 'format': opts.convertsubtitles,
299 })
300 if opts.embedsubtitles:
301 postprocessors.append({
302 'key': 'FFmpegEmbedSubtitle',
303 })
304 if opts.embedthumbnail:
305 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
306 postprocessors.append({
307 'key': 'EmbedThumbnail',
308 'already_have_thumbnail': already_have_thumbnail
309 })
310 if not already_have_thumbnail:
311 opts.writethumbnail = True
312 # XAttrMetadataPP should be run after post-processors that may change file
313 # contents
314 if opts.xattrs:
315 postprocessors.append({'key': 'XAttrMetadata'})
316 # This should be below all ffmpeg PP because it may cut parts out from the video
317 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
318 if opts.sponskrub is not False:
319 postprocessors.append({
320 'key': 'SponSkrub',
321 'path': opts.sponskrub_path,
322 'args': opts.sponskrub_args,
323 'cut': opts.sponskrub_cut,
324 'force': opts.sponskrub_force,
325 'ignoreerror': opts.sponskrub is None,
326 })
327 # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
328 # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
329 if opts.exec_cmd:
330 postprocessors.append({
331 'key': 'ExecAfterDownload',
332 'exec_cmd': opts.exec_cmd,
333 })
334 external_downloader_args = None
335 if opts.external_downloader_args:
336 external_downloader_args = compat_shlex_split(opts.external_downloader_args)
337
338 postprocessor_args = {}
339 if opts.postprocessor_args is not None:
340 for string in opts.postprocessor_args:
341 mobj = re.match(r'(?P<pp>\w+):(?P<args>.*)$', string)
342 if mobj is None:
343 if 'sponskrub' not in postprocessor_args: # for backward compatibility
344 postprocessor_args['sponskrub'] = []
345 if opts.verbose:
346 write_string('[debug] Adding postprocessor args from command line option sponskrub:\n')
347 pp_name, pp_args = 'default', string
348 else:
349 pp_name, pp_args = mobj.group('pp').lower(), mobj.group('args')
350 if opts.verbose:
351 write_string('[debug] Adding postprocessor args from command line option %s:%s\n' % (pp_name, pp_args))
352 postprocessor_args[pp_name] = compat_shlex_split(pp_args)
353
354 match_filter = (
355 None if opts.match_filter is None
356 else match_filter_func(opts.match_filter))
357
358 ydl_opts = {
359 'convertsubtitles': opts.convertsubtitles,
360 'usenetrc': opts.usenetrc,
361 'username': opts.username,
362 'password': opts.password,
363 'twofactor': opts.twofactor,
364 'videopassword': opts.videopassword,
365 'ap_mso': opts.ap_mso,
366 'ap_username': opts.ap_username,
367 'ap_password': opts.ap_password,
368 'quiet': (opts.quiet or any_getting or any_printing),
369 'no_warnings': opts.no_warnings,
370 'forceurl': opts.geturl,
371 'forcetitle': opts.gettitle,
372 'forceid': opts.getid,
373 'forcethumbnail': opts.getthumbnail,
374 'forcedescription': opts.getdescription,
375 'forceduration': opts.getduration,
376 'forcefilename': opts.getfilename,
377 'forceformat': opts.getformat,
378 'forcejson': opts.dumpjson or opts.print_json,
379 'dump_single_json': opts.dump_single_json,
380 'force_write_download_archive': opts.force_write_download_archive,
381 'simulate': opts.simulate or any_getting,
382 'skip_download': opts.skip_download,
383 'format': opts.format,
384 'format_sort': opts.format_sort,
385 'format_sort_force': opts.format_sort_force,
386 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
387 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
388 'listformats': opts.listformats,
389 'listformats_table': opts.listformats_table,
390 'outtmpl': outtmpl,
391 'autonumber_size': opts.autonumber_size,
392 'autonumber_start': opts.autonumber_start,
393 'restrictfilenames': opts.restrictfilenames,
394 'ignoreerrors': opts.ignoreerrors,
395 'force_generic_extractor': opts.force_generic_extractor,
396 'ratelimit': opts.ratelimit,
397 'overwrites': opts.overwrites,
398 'retries': opts.retries,
399 'fragment_retries': opts.fragment_retries,
400 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
401 'keep_fragments': opts.keep_fragments,
402 'buffersize': opts.buffersize,
403 'noresizebuffer': opts.noresizebuffer,
404 'http_chunk_size': opts.http_chunk_size,
405 'continuedl': opts.continue_dl,
406 'noprogress': opts.noprogress,
407 'progress_with_newline': opts.progress_with_newline,
408 'playliststart': opts.playliststart,
409 'playlistend': opts.playlistend,
410 'playlistreverse': opts.playlist_reverse,
411 'playlistrandom': opts.playlist_random,
412 'noplaylist': opts.noplaylist,
413 'logtostderr': opts.outtmpl == '-',
414 'consoletitle': opts.consoletitle,
415 'nopart': opts.nopart,
416 'updatetime': opts.updatetime,
417 'writedescription': opts.writedescription,
418 'writeannotations': opts.writeannotations,
419 'writeinfojson': opts.writeinfojson,
420 'writethumbnail': opts.writethumbnail,
421 'write_all_thumbnails': opts.write_all_thumbnails,
422 'writelink': opts.writelink,
423 'writeurllink': opts.writeurllink,
424 'writewebloclink': opts.writewebloclink,
425 'writedesktoplink': opts.writedesktoplink,
426 'writesubtitles': opts.writesubtitles,
427 'writeautomaticsub': opts.writeautomaticsub,
428 'allsubtitles': opts.allsubtitles,
429 'listsubtitles': opts.listsubtitles,
430 'subtitlesformat': opts.subtitlesformat,
431 'subtitleslangs': opts.subtitleslangs,
432 'matchtitle': decodeOption(opts.matchtitle),
433 'rejecttitle': decodeOption(opts.rejecttitle),
434 'max_downloads': opts.max_downloads,
435 'prefer_free_formats': opts.prefer_free_formats,
436 'trim_file_name': opts.trim_file_name,
437 'verbose': opts.verbose,
438 'dump_intermediate_pages': opts.dump_intermediate_pages,
439 'write_pages': opts.write_pages,
440 'test': opts.test,
441 'keepvideo': opts.keepvideo,
442 'min_filesize': opts.min_filesize,
443 'max_filesize': opts.max_filesize,
444 'min_views': opts.min_views,
445 'max_views': opts.max_views,
446 'daterange': date,
447 'cachedir': opts.cachedir,
448 'youtube_print_sig_code': opts.youtube_print_sig_code,
449 'age_limit': opts.age_limit,
450 'download_archive': download_archive_fn,
451 'break_on_existing': opts.break_on_existing,
452 'cookiefile': opts.cookiefile,
453 'nocheckcertificate': opts.no_check_certificate,
454 'prefer_insecure': opts.prefer_insecure,
455 'proxy': opts.proxy,
456 'socket_timeout': opts.socket_timeout,
457 'bidi_workaround': opts.bidi_workaround,
458 'debug_printtraffic': opts.debug_printtraffic,
459 'prefer_ffmpeg': opts.prefer_ffmpeg,
460 'include_ads': opts.include_ads,
461 'default_search': opts.default_search,
462 'dynamic_mpd': opts.dynamic_mpd,
463 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
464 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
465 'encoding': opts.encoding,
466 'extract_flat': opts.extract_flat,
467 'mark_watched': opts.mark_watched,
468 'merge_output_format': opts.merge_output_format,
469 'postprocessors': postprocessors,
470 'fixup': opts.fixup,
471 'source_address': opts.source_address,
472 'call_home': opts.call_home,
473 'sleep_interval': opts.sleep_interval,
474 'max_sleep_interval': opts.max_sleep_interval,
475 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
476 'external_downloader': opts.external_downloader,
477 'list_thumbnails': opts.list_thumbnails,
478 'playlist_items': opts.playlist_items,
479 'xattr_set_filesize': opts.xattr_set_filesize,
480 'match_filter': match_filter,
481 'no_color': opts.no_color,
482 'ffmpeg_location': opts.ffmpeg_location,
483 'hls_prefer_native': opts.hls_prefer_native,
484 'hls_use_mpegts': opts.hls_use_mpegts,
485 'external_downloader_args': external_downloader_args,
486 'postprocessor_args': postprocessor_args,
487 'cn_verification_proxy': opts.cn_verification_proxy,
488 'geo_verification_proxy': opts.geo_verification_proxy,
489 'config_location': opts.config_location,
490 'geo_bypass': opts.geo_bypass,
491 'geo_bypass_country': opts.geo_bypass_country,
492 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
493 # just for deprecation check
494 'autonumber': opts.autonumber if opts.autonumber is True else None,
495 'usetitle': opts.usetitle if opts.usetitle is True else None,
496 }
497
498 with YoutubeDL(ydl_opts) as ydl:
499 # Update version
500 if opts.update_self:
501 update_self(ydl.to_screen, opts.verbose, ydl._opener)
502
503 # Remove cache dir
504 if opts.rm_cachedir:
505 ydl.cache.remove()
506
507 # Maybe do nothing
508 if (len(all_urls) < 1) and (opts.load_info_filename is None):
509 if opts.update_self or opts.rm_cachedir:
510 sys.exit()
511
512 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
513 parser.error(
514 'You must provide at least one URL.\n'
515 'Type youtube-dlc --help to see a list of all options.')
516
517 try:
518 if opts.load_info_filename is not None:
519 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
520 else:
521 retcode = ydl.download(all_urls)
522 except MaxDownloadsReached:
523 ydl.to_screen('--max-download limit reached, aborting.')
524 retcode = 101
525
526 sys.exit(retcode)
527
528
529 def main(argv=None):
530 try:
531 _real_main(argv)
532 except DownloadError:
533 sys.exit(1)
534 except SameFileError:
535 sys.exit('ERROR: fixed output name but more than one file to download')
536 except KeyboardInterrupt:
537 sys.exit('\nERROR: Interrupted by user')
538
539
540 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']