]> jfr.im git - yt-dlp.git/blob - youtube_dlc/__init__.py
Multiple output templates for different file types
[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 random
12 import re
13 import sys
14
15
16 from .options import (
17 parseOpts,
18 _remux_formats,
19 )
20 from .compat import (
21 compat_getpass,
22 workaround_optparse_bug9161,
23 )
24 from .utils import (
25 DateRange,
26 decodeOption,
27 DEFAULT_OUTTMPL,
28 DownloadError,
29 ExistingVideoReached,
30 expand_path,
31 match_filter_func,
32 MaxDownloadsReached,
33 preferredencoding,
34 read_batch_urls,
35 RejectedVideoReached,
36 SameFileError,
37 setproctitle,
38 std_headers,
39 write_string,
40 render_table,
41 )
42 from .update import update_self
43 from .downloader import (
44 FileDownloader,
45 )
46 from .extractor import gen_extractors, list_extractors
47 from .extractor.common import InfoExtractor
48 from .extractor.adobepass import MSO_INFO
49 from .postprocessor.metadatafromfield import MetadataFromFieldPP
50 from .YoutubeDL import YoutubeDL
51
52
53 def _real_main(argv=None):
54 # Compatibility fixes for Windows
55 if sys.platform == 'win32':
56 # https://github.com/ytdl-org/youtube-dl/issues/820
57 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
58
59 workaround_optparse_bug9161()
60
61 setproctitle('youtube-dlc')
62
63 parser, opts, args = parseOpts(argv)
64
65 # Set user agent
66 if opts.user_agent is not None:
67 std_headers['User-Agent'] = opts.user_agent
68
69 # Set referer
70 if opts.referer is not None:
71 std_headers['Referer'] = opts.referer
72
73 # Custom HTTP headers
74 std_headers.update(opts.headers)
75
76 # Dump user agent
77 if opts.dump_user_agent:
78 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
79 sys.exit(0)
80
81 # Batch file verification
82 batch_urls = []
83 if opts.batchfile is not None:
84 try:
85 if opts.batchfile == '-':
86 batchfd = sys.stdin
87 else:
88 batchfd = io.open(
89 expand_path(opts.batchfile),
90 'r', encoding='utf-8', errors='ignore')
91 batch_urls = read_batch_urls(batchfd)
92 if opts.verbose:
93 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
94 except IOError:
95 sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
96 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
97 _enc = preferredencoding()
98 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
99
100 if opts.list_extractors:
101 for ie in list_extractors(opts.age_limit):
102 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
103 matchedUrls = [url for url in all_urls if ie.suitable(url)]
104 for mu in matchedUrls:
105 write_string(' ' + mu + '\n', out=sys.stdout)
106 sys.exit(0)
107 if opts.list_extractor_descriptions:
108 for ie in list_extractors(opts.age_limit):
109 if not ie._WORKING:
110 continue
111 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
112 if desc is False:
113 continue
114 if hasattr(ie, 'SEARCH_KEY'):
115 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
116 _COUNTS = ('', '5', '10', 'all')
117 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
118 write_string(desc + '\n', out=sys.stdout)
119 sys.exit(0)
120 if opts.ap_list_mso:
121 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
122 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
123 sys.exit(0)
124
125 # Conflicting, missing and erroneous options
126 if opts.usenetrc and (opts.username is not None or opts.password is not None):
127 parser.error('using .netrc conflicts with giving username/password')
128 if opts.password is not None and opts.username is None:
129 parser.error('account username missing\n')
130 if opts.ap_password is not None and opts.ap_username is None:
131 parser.error('TV Provider account username missing\n')
132 if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
133 parser.error('using output template conflicts with using title, video ID or auto number')
134 if opts.autonumber_size is not None:
135 if opts.autonumber_size <= 0:
136 parser.error('auto number size must be positive')
137 if opts.autonumber_start is not None:
138 if opts.autonumber_start < 0:
139 parser.error('auto number start must be positive or 0')
140 if opts.usetitle and opts.useid:
141 parser.error('using title conflicts with using video ID')
142 if opts.username is not None and opts.password is None:
143 opts.password = compat_getpass('Type account password and press [Return]: ')
144 if opts.ap_username is not None and opts.ap_password is None:
145 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
146 if opts.ratelimit is not None:
147 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
148 if numeric_limit is None:
149 parser.error('invalid rate limit specified')
150 opts.ratelimit = numeric_limit
151 if opts.min_filesize is not None:
152 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
153 if numeric_limit is None:
154 parser.error('invalid min_filesize specified')
155 opts.min_filesize = numeric_limit
156 if opts.max_filesize is not None:
157 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
158 if numeric_limit is None:
159 parser.error('invalid max_filesize specified')
160 opts.max_filesize = numeric_limit
161 if opts.sleep_interval is not None:
162 if opts.sleep_interval < 0:
163 parser.error('sleep interval must be positive or 0')
164 if opts.max_sleep_interval is not None:
165 if opts.max_sleep_interval < 0:
166 parser.error('max sleep interval must be positive or 0')
167 if opts.sleep_interval is None:
168 parser.error('min sleep interval must be specified, use --min-sleep-interval')
169 if opts.max_sleep_interval < opts.sleep_interval:
170 parser.error('max sleep interval must be greater than or equal to min sleep interval')
171 else:
172 opts.max_sleep_interval = opts.sleep_interval
173 if opts.ap_mso and opts.ap_mso not in MSO_INFO:
174 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
175 if opts.overwrites:
176 # --yes-overwrites implies --no-continue
177 opts.continue_dl = False
178
179 def parse_retries(retries):
180 if retries in ('inf', 'infinite'):
181 parsed_retries = float('inf')
182 else:
183 try:
184 parsed_retries = int(retries)
185 except (TypeError, ValueError):
186 parser.error('invalid retry count specified')
187 return parsed_retries
188 if opts.retries is not None:
189 opts.retries = parse_retries(opts.retries)
190 if opts.fragment_retries is not None:
191 opts.fragment_retries = parse_retries(opts.fragment_retries)
192 if opts.buffersize is not None:
193 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
194 if numeric_buffersize is None:
195 parser.error('invalid buffer size specified')
196 opts.buffersize = numeric_buffersize
197 if opts.http_chunk_size is not None:
198 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
199 if not numeric_chunksize:
200 parser.error('invalid http chunk size specified')
201 opts.http_chunk_size = numeric_chunksize
202 if opts.playliststart <= 0:
203 raise ValueError('Playlist start must be positive')
204 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
205 raise ValueError('Playlist end must be greater than playlist start')
206 if opts.extractaudio:
207 if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
208 parser.error('invalid audio format specified')
209 if opts.audioquality:
210 opts.audioquality = opts.audioquality.strip('k').strip('K')
211 if not opts.audioquality.isdigit():
212 parser.error('invalid audio quality specified')
213 if opts.recodevideo is not None:
214 if opts.recodevideo not in _remux_formats:
215 parser.error('invalid video recode format specified')
216 if opts.remuxvideo and opts.recodevideo:
217 opts.remuxvideo = None
218 write_string('WARNING: --remux-video is ignored since --recode-video was given\n', out=sys.stderr)
219 if opts.remuxvideo is not None:
220 if opts.remuxvideo not in _remux_formats:
221 parser.error('invalid video remux format specified')
222 if opts.convertsubtitles is not None:
223 if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
224 parser.error('invalid subtitle format specified')
225
226 if opts.date is not None:
227 date = DateRange.day(opts.date)
228 else:
229 date = DateRange(opts.dateafter, opts.datebefore)
230
231 # Do not download videos when there are audio-only formats
232 if opts.extractaudio and not opts.keepvideo and opts.format is None:
233 opts.format = 'bestaudio/best'
234
235 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
236 # this was the old behaviour if only --all-sub was given.
237 if opts.allsubtitles and not opts.writeautomaticsub:
238 opts.writesubtitles = True
239
240 outtmpl = opts.outtmpl
241 if not outtmpl:
242 outtmpl = {'default': (
243 '%(title)s-%(id)s-%(format)s.%(ext)s' if opts.format == '-1' and opts.usetitle
244 else '%(id)s-%(format)s.%(ext)s' if opts.format == '-1'
245 else '%(autonumber)s-%(title)s-%(id)s.%(ext)s' if opts.usetitle and opts.autonumber
246 else '%(title)s-%(id)s.%(ext)s' if opts.usetitle
247 else '%(id)s.%(ext)s' if opts.useid
248 else '%(autonumber)s-%(id)s.%(ext)s' if opts.autonumber
249 else None)}
250 outtmpl_default = outtmpl.get('default')
251 if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
252 parser.error('Cannot download a video and extract audio into the same'
253 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
254 ' template'.format(outtmpl_default))
255
256 for f in opts.format_sort:
257 if re.match(InfoExtractor.FormatSort.regex, f) is None:
258 parser.error('invalid format sort string "%s" specified' % f)
259
260 if opts.metafromfield is None:
261 opts.metafromfield = []
262 if opts.metafromtitle is not None:
263 opts.metafromfield.append('title:%s' % opts.metafromtitle)
264 for f in opts.metafromfield:
265 if re.match(MetadataFromFieldPP.regex, f) is None:
266 parser.error('invalid format string "%s" specified for --parse-metadata' % f)
267
268 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
269 any_printing = opts.print_json
270 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
271
272 # PostProcessors
273 postprocessors = []
274 if opts.metafromfield:
275 postprocessors.append({
276 'key': 'MetadataFromField',
277 'formats': opts.metafromfield,
278 'when': 'beforedl'
279 })
280 if opts.extractaudio:
281 postprocessors.append({
282 'key': 'FFmpegExtractAudio',
283 'preferredcodec': opts.audioformat,
284 'preferredquality': opts.audioquality,
285 'nopostoverwrites': opts.nopostoverwrites,
286 })
287 if opts.remuxvideo:
288 postprocessors.append({
289 'key': 'FFmpegVideoRemuxer',
290 'preferedformat': opts.remuxvideo,
291 })
292 if opts.recodevideo:
293 postprocessors.append({
294 'key': 'FFmpegVideoConvertor',
295 'preferedformat': opts.recodevideo,
296 })
297 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
298 # FFmpegExtractAudioPP as containers before conversion may not support
299 # metadata (3gp, webm, etc.)
300 # And this post-processor should be placed before other metadata
301 # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
302 # extra metadata. By default ffmpeg preserves metadata applicable for both
303 # source and target containers. From this point the container won't change,
304 # so metadata can be added here.
305 if opts.addmetadata:
306 postprocessors.append({'key': 'FFmpegMetadata'})
307 if opts.convertsubtitles:
308 postprocessors.append({
309 'key': 'FFmpegSubtitlesConvertor',
310 'format': opts.convertsubtitles,
311 })
312 if opts.embedsubtitles:
313 postprocessors.append({
314 'key': 'FFmpegEmbedSubtitle',
315 })
316 if opts.embedthumbnail:
317 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
318 postprocessors.append({
319 'key': 'EmbedThumbnail',
320 'already_have_thumbnail': already_have_thumbnail
321 })
322 if not already_have_thumbnail:
323 opts.writethumbnail = True
324 # XAttrMetadataPP should be run after post-processors that may change file
325 # contents
326 if opts.xattrs:
327 postprocessors.append({'key': 'XAttrMetadata'})
328 # This should be below all ffmpeg PP because it may cut parts out from the video
329 # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
330 if opts.sponskrub is not False:
331 postprocessors.append({
332 'key': 'SponSkrub',
333 'path': opts.sponskrub_path,
334 'args': opts.sponskrub_args,
335 'cut': opts.sponskrub_cut,
336 'force': opts.sponskrub_force,
337 'ignoreerror': opts.sponskrub is None,
338 })
339 # ExecAfterDownload must be the last PP
340 if opts.exec_cmd:
341 postprocessors.append({
342 'key': 'ExecAfterDownload',
343 'exec_cmd': opts.exec_cmd,
344 'when': 'aftermove'
345 })
346
347 _args_compat_warning = 'WARNING: %s given without specifying name. The arguments will be given to all %s\n'
348 if 'default' in opts.external_downloader_args:
349 write_string(_args_compat_warning % ('--external-downloader-args', 'external downloaders'), out=sys.stderr),
350
351 if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
352 write_string(_args_compat_warning % ('--post-processor-args', 'post-processors'), out=sys.stderr),
353 opts.postprocessor_args.setdefault('sponskrub', [])
354 opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
355
356 audio_ext = opts.audioformat if (opts.extractaudio and opts.audioformat != 'best') else None
357
358 match_filter = (
359 None if opts.match_filter is None
360 else match_filter_func(opts.match_filter))
361
362 ydl_opts = {
363 'convertsubtitles': opts.convertsubtitles,
364 'usenetrc': opts.usenetrc,
365 'username': opts.username,
366 'password': opts.password,
367 'twofactor': opts.twofactor,
368 'videopassword': opts.videopassword,
369 'ap_mso': opts.ap_mso,
370 'ap_username': opts.ap_username,
371 'ap_password': opts.ap_password,
372 'quiet': (opts.quiet or any_getting or any_printing),
373 'no_warnings': opts.no_warnings,
374 'forceurl': opts.geturl,
375 'forcetitle': opts.gettitle,
376 'forceid': opts.getid,
377 'forcethumbnail': opts.getthumbnail,
378 'forcedescription': opts.getdescription,
379 'forceduration': opts.getduration,
380 'forcefilename': opts.getfilename,
381 'forceformat': opts.getformat,
382 'forcejson': opts.dumpjson or opts.print_json,
383 'dump_single_json': opts.dump_single_json,
384 'force_write_download_archive': opts.force_write_download_archive,
385 'simulate': opts.simulate or any_getting,
386 'skip_download': opts.skip_download,
387 'format': opts.format,
388 'format_sort': opts.format_sort,
389 'format_sort_force': opts.format_sort_force,
390 'allow_multiple_video_streams': opts.allow_multiple_video_streams,
391 'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
392 'listformats': opts.listformats,
393 'listformats_table': opts.listformats_table,
394 'outtmpl': outtmpl,
395 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
396 'paths': opts.paths,
397 'autonumber_size': opts.autonumber_size,
398 'autonumber_start': opts.autonumber_start,
399 'restrictfilenames': opts.restrictfilenames,
400 'ignoreerrors': opts.ignoreerrors,
401 'force_generic_extractor': opts.force_generic_extractor,
402 'ratelimit': opts.ratelimit,
403 'overwrites': opts.overwrites,
404 'retries': opts.retries,
405 'fragment_retries': opts.fragment_retries,
406 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
407 'keep_fragments': opts.keep_fragments,
408 'buffersize': opts.buffersize,
409 'noresizebuffer': opts.noresizebuffer,
410 'http_chunk_size': opts.http_chunk_size,
411 'continuedl': opts.continue_dl,
412 'noprogress': opts.noprogress,
413 'progress_with_newline': opts.progress_with_newline,
414 'playliststart': opts.playliststart,
415 'playlistend': opts.playlistend,
416 'playlistreverse': opts.playlist_reverse,
417 'playlistrandom': opts.playlist_random,
418 'noplaylist': opts.noplaylist,
419 'logtostderr': outtmpl_default == '-',
420 'consoletitle': opts.consoletitle,
421 'nopart': opts.nopart,
422 'updatetime': opts.updatetime,
423 'writedescription': opts.writedescription,
424 'writeannotations': opts.writeannotations,
425 'writeinfojson': opts.writeinfojson or opts.getcomments,
426 'getcomments': opts.getcomments,
427 'writethumbnail': opts.writethumbnail,
428 'write_all_thumbnails': opts.write_all_thumbnails,
429 'writelink': opts.writelink,
430 'writeurllink': opts.writeurllink,
431 'writewebloclink': opts.writewebloclink,
432 'writedesktoplink': opts.writedesktoplink,
433 'writesubtitles': opts.writesubtitles,
434 'writeautomaticsub': opts.writeautomaticsub,
435 'allsubtitles': opts.allsubtitles,
436 'listsubtitles': opts.listsubtitles,
437 'subtitlesformat': opts.subtitlesformat,
438 'subtitleslangs': opts.subtitleslangs,
439 'matchtitle': decodeOption(opts.matchtitle),
440 'rejecttitle': decodeOption(opts.rejecttitle),
441 'max_downloads': opts.max_downloads,
442 'prefer_free_formats': opts.prefer_free_formats,
443 'trim_file_name': opts.trim_file_name,
444 'verbose': opts.verbose,
445 'dump_intermediate_pages': opts.dump_intermediate_pages,
446 'write_pages': opts.write_pages,
447 'test': opts.test,
448 'keepvideo': opts.keepvideo,
449 'min_filesize': opts.min_filesize,
450 'max_filesize': opts.max_filesize,
451 'min_views': opts.min_views,
452 'max_views': opts.max_views,
453 'daterange': date,
454 'cachedir': opts.cachedir,
455 'youtube_print_sig_code': opts.youtube_print_sig_code,
456 'age_limit': opts.age_limit,
457 'download_archive': download_archive_fn,
458 'break_on_existing': opts.break_on_existing,
459 'break_on_reject': opts.break_on_reject,
460 'cookiefile': opts.cookiefile,
461 'nocheckcertificate': opts.no_check_certificate,
462 'prefer_insecure': opts.prefer_insecure,
463 'proxy': opts.proxy,
464 'socket_timeout': opts.socket_timeout,
465 'bidi_workaround': opts.bidi_workaround,
466 'debug_printtraffic': opts.debug_printtraffic,
467 'prefer_ffmpeg': opts.prefer_ffmpeg,
468 'include_ads': opts.include_ads,
469 'default_search': opts.default_search,
470 'dynamic_mpd': opts.dynamic_mpd,
471 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
472 'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
473 'encoding': opts.encoding,
474 'extract_flat': opts.extract_flat,
475 'mark_watched': opts.mark_watched,
476 'merge_output_format': opts.merge_output_format,
477 'final_ext': opts.recodevideo or opts.remuxvideo or audio_ext,
478 'postprocessors': postprocessors,
479 'fixup': opts.fixup,
480 'source_address': opts.source_address,
481 'call_home': opts.call_home,
482 'sleep_interval': opts.sleep_interval,
483 'max_sleep_interval': opts.max_sleep_interval,
484 'sleep_interval_subtitles': opts.sleep_interval_subtitles,
485 'external_downloader': opts.external_downloader,
486 'list_thumbnails': opts.list_thumbnails,
487 'playlist_items': opts.playlist_items,
488 'xattr_set_filesize': opts.xattr_set_filesize,
489 'match_filter': match_filter,
490 'no_color': opts.no_color,
491 'ffmpeg_location': opts.ffmpeg_location,
492 'hls_prefer_native': opts.hls_prefer_native,
493 'hls_use_mpegts': opts.hls_use_mpegts,
494 'external_downloader_args': opts.external_downloader_args,
495 'postprocessor_args': opts.postprocessor_args,
496 'cn_verification_proxy': opts.cn_verification_proxy,
497 'geo_verification_proxy': opts.geo_verification_proxy,
498 'config_location': opts.config_location,
499 'geo_bypass': opts.geo_bypass,
500 'geo_bypass_country': opts.geo_bypass_country,
501 'geo_bypass_ip_block': opts.geo_bypass_ip_block,
502 # just for deprecation check
503 'autonumber': opts.autonumber if opts.autonumber is True else None,
504 'usetitle': opts.usetitle if opts.usetitle is True else None,
505 }
506
507 with YoutubeDL(ydl_opts) as ydl:
508 # Update version
509 if opts.update_self:
510 update_self(ydl.to_screen, opts.verbose, ydl._opener)
511
512 # Remove cache dir
513 if opts.rm_cachedir:
514 ydl.cache.remove()
515
516 # Maybe do nothing
517 if (len(all_urls) < 1) and (opts.load_info_filename is None):
518 if opts.update_self or opts.rm_cachedir:
519 sys.exit()
520
521 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
522 parser.error(
523 'You must provide at least one URL.\n'
524 'Type youtube-dlc --help to see a list of all options.')
525
526 try:
527 if opts.load_info_filename is not None:
528 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
529 else:
530 retcode = ydl.download(all_urls)
531 except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
532 ydl.to_screen('Aborting remaining downloads')
533 retcode = 101
534
535 sys.exit(retcode)
536
537
538 def main(argv=None):
539 try:
540 _real_main(argv)
541 except DownloadError:
542 sys.exit(1)
543 except SameFileError:
544 sys.exit('ERROR: fixed output name but more than one file to download')
545 except KeyboardInterrupt:
546 sys.exit('\nERROR: Interrupted by user')
547
548
549 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']