]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/__init__.py
9bb952457e149f3687efd0ca925aed8d69996366
[youtubedl] / youtube_dl / __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 sys
13
14
15 from .options import (
16 parseOpts,
17 )
18 from .compat import (
19 compat_getpass,
20 compat_shlex_split,
21 workaround_optparse_bug9161,
22 )
23 from .utils import (
24 DateRange,
25 decodeOption,
26 DEFAULT_OUTTMPL,
27 DownloadError,
28 expand_path,
29 match_filter_func,
30 MaxDownloadsReached,
31 preferredencoding,
32 read_batch_urls,
33 SameFileError,
34 setproctitle,
35 std_headers,
36 write_string,
37 render_table,
38 )
39 from .update import update_self
40 from .downloader import (
41 FileDownloader,
42 )
43 from .extractor import gen_extractors, list_extractors
44 from .extractor.adobepass import MSO_INFO
45 from .YoutubeDL import YoutubeDL
46
47
48 def _real_main(argv=None):
49 # Compatibility fixes for Windows
50 if sys.platform == 'win32':
51 # https://github.com/rg3/youtube-dl/issues/820
52 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
53
54 workaround_optparse_bug9161()
55
56 setproctitle('youtube-dl')
57
58 parser, opts, args = parseOpts(argv)
59
60 # Set user agent
61 if opts.user_agent is not None:
62 std_headers['User-Agent'] = opts.user_agent
63
64 # Set referer
65 if opts.referer is not None:
66 std_headers['Referer'] = opts.referer
67
68 # Custom HTTP headers
69 if opts.headers is not None:
70 for h in opts.headers:
71 if ':' not in h:
72 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
73 key, value = h.split(':', 1)
74 if opts.verbose:
75 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
76 std_headers[key] = value
77
78 # Dump user agent
79 if opts.dump_user_agent:
80 write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
81 sys.exit(0)
82
83 # Batch file verification
84 batch_urls = []
85 if opts.batchfile is not None:
86 try:
87 if opts.batchfile == '-':
88 batchfd = sys.stdin
89 else:
90 batchfd = io.open(
91 expand_path(opts.batchfile),
92 'r', encoding='utf-8', errors='ignore')
93 batch_urls = read_batch_urls(batchfd)
94 if opts.verbose:
95 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
96 except IOError:
97 sys.exit('ERROR: batch file could not be read')
98 all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
99 _enc = preferredencoding()
100 all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
101
102 if opts.list_extractors:
103 for ie in list_extractors(opts.age_limit):
104 write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
105 matchedUrls = [url for url in all_urls if ie.suitable(url)]
106 for mu in matchedUrls:
107 write_string(' ' + mu + '\n', out=sys.stdout)
108 sys.exit(0)
109 if opts.list_extractor_descriptions:
110 for ie in list_extractors(opts.age_limit):
111 if not ie._WORKING:
112 continue
113 desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
114 if desc is False:
115 continue
116 if hasattr(ie, 'SEARCH_KEY'):
117 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
118 _COUNTS = ('', '5', '10', 'all')
119 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
120 write_string(desc + '\n', out=sys.stdout)
121 sys.exit(0)
122 if opts.ap_list_mso:
123 table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
124 write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
125 sys.exit(0)
126
127 # Conflicting, missing and erroneous options
128 if opts.usenetrc and (opts.username is not None or opts.password is not None):
129 parser.error('using .netrc conflicts with giving username/password')
130 if opts.password is not None and opts.username is None:
131 parser.error('account username missing\n')
132 if opts.ap_password is not None and opts.ap_username is None:
133 parser.error('TV Provider account username missing\n')
134 if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
135 parser.error('using output template conflicts with using title, video ID or auto number')
136 if opts.autonumber_size is not None:
137 if opts.autonumber_size <= 0:
138 parser.error('auto number size must be positive')
139 if opts.autonumber_start is not None:
140 if opts.autonumber_start < 0:
141 parser.error('auto number start must be positive or 0')
142 if opts.usetitle and opts.useid:
143 parser.error('using title conflicts with using video ID')
144 if opts.username is not None and opts.password is None:
145 opts.password = compat_getpass('Type account password and press [Return]: ')
146 if opts.ap_username is not None and opts.ap_password is None:
147 opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
148 if opts.ratelimit is not None:
149 numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
150 if numeric_limit is None:
151 parser.error('invalid rate limit specified')
152 opts.ratelimit = numeric_limit
153 if opts.min_filesize is not None:
154 numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
155 if numeric_limit is None:
156 parser.error('invalid min_filesize specified')
157 opts.min_filesize = numeric_limit
158 if opts.max_filesize is not None:
159 numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
160 if numeric_limit is None:
161 parser.error('invalid max_filesize specified')
162 opts.max_filesize = numeric_limit
163 if opts.sleep_interval is not None:
164 if opts.sleep_interval < 0:
165 parser.error('sleep interval must be positive or 0')
166 if opts.max_sleep_interval is not None:
167 if opts.max_sleep_interval < 0:
168 parser.error('max sleep interval must be positive or 0')
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
176 def parse_retries(retries):
177 if retries in ('inf', 'infinite'):
178 parsed_retries = float('inf')
179 else:
180 try:
181 parsed_retries = int(retries)
182 except (TypeError, ValueError):
183 parser.error('invalid retry count specified')
184 return parsed_retries
185 if opts.retries is not None:
186 opts.retries = parse_retries(opts.retries)
187 if opts.fragment_retries is not None:
188 opts.fragment_retries = parse_retries(opts.fragment_retries)
189 if opts.buffersize is not None:
190 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
191 if numeric_buffersize is None:
192 parser.error('invalid buffer size specified')
193 opts.buffersize = numeric_buffersize
194 if opts.http_chunk_size is not None:
195 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
196 if not numeric_chunksize:
197 parser.error('invalid http chunk size specified')
198 opts.http_chunk_size = numeric_chunksize
199 if opts.playliststart <= 0:
200 raise ValueError('Playlist start must be positive')
201 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
202 raise ValueError('Playlist end must be greater than playlist start')
203 if opts.extractaudio:
204 if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
205 parser.error('invalid audio format specified')
206 if opts.audioquality:
207 opts.audioquality = opts.audioquality.strip('k').strip('K')
208 if not opts.audioquality.isdigit():
209 parser.error('invalid audio quality specified')
210 if opts.recodevideo is not None:
211 if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
212 parser.error('invalid video recode format specified')
213 if opts.convertsubtitles is not None:
214 if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
215 parser.error('invalid subtitle format specified')
216
217 if opts.date is not None:
218 date = DateRange.day(opts.date)
219 else:
220 date = DateRange(opts.dateafter, opts.datebefore)
221
222 # Do not download videos when there are audio-only formats
223 if opts.extractaudio and not opts.keepvideo and opts.format is None:
224 opts.format = 'bestaudio/best'
225
226 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
227 # this was the old behaviour if only --all-sub was given.
228 if opts.allsubtitles and not opts.writeautomaticsub:
229 opts.writesubtitles = True
230
231 outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
232 (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
233 (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
234 (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
235 (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
236 (opts.useid and '%(id)s.%(ext)s') or
237 (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
238 DEFAULT_OUTTMPL)
239 if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
240 parser.error('Cannot download a video and extract audio into the same'
241 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
242 ' template'.format(outtmpl))
243
244 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
245 any_printing = opts.print_json
246 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
247
248 # PostProcessors
249 postprocessors = []
250 if opts.metafromtitle:
251 postprocessors.append({
252 'key': 'MetadataFromTitle',
253 'titleformat': opts.metafromtitle
254 })
255 if opts.extractaudio:
256 postprocessors.append({
257 'key': 'FFmpegExtractAudio',
258 'preferredcodec': opts.audioformat,
259 'preferredquality': opts.audioquality,
260 'nopostoverwrites': opts.nopostoverwrites,
261 })
262 if opts.recodevideo:
263 postprocessors.append({
264 'key': 'FFmpegVideoConvertor',
265 'preferedformat': opts.recodevideo,
266 })
267 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
268 # FFmpegExtractAudioPP as containers before conversion may not support
269 # metadata (3gp, webm, etc.)
270 # And this post-processor should be placed before other metadata
271 # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
272 # extra metadata. By default ffmpeg preserves metadata applicable for both
273 # source and target containers. From this point the container won't change,
274 # so metadata can be added here.
275 if opts.addmetadata:
276 postprocessors.append({'key': 'FFmpegMetadata'})
277 if opts.convertsubtitles:
278 postprocessors.append({
279 'key': 'FFmpegSubtitlesConvertor',
280 'format': opts.convertsubtitles,
281 })
282 if opts.embedsubtitles:
283 postprocessors.append({
284 'key': 'FFmpegEmbedSubtitle',
285 })
286 if opts.embedthumbnail:
287 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
288 postprocessors.append({
289 'key': 'EmbedThumbnail',
290 'already_have_thumbnail': already_have_thumbnail
291 })
292 if not already_have_thumbnail:
293 opts.writethumbnail = True
294 # XAttrMetadataPP should be run after post-processors that may change file
295 # contents
296 if opts.xattrs:
297 postprocessors.append({'key': 'XAttrMetadata'})
298 # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
299 # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
300 if opts.exec_cmd:
301 postprocessors.append({
302 'key': 'ExecAfterDownload',
303 'exec_cmd': opts.exec_cmd,
304 })
305 external_downloader_args = None
306 if opts.external_downloader_args:
307 external_downloader_args = compat_shlex_split(opts.external_downloader_args)
308 postprocessor_args = None
309 if opts.postprocessor_args:
310 postprocessor_args = compat_shlex_split(opts.postprocessor_args)
311 match_filter = (
312 None if opts.match_filter is None
313 else match_filter_func(opts.match_filter))
314
315 ydl_opts = {
316 'usenetrc': opts.usenetrc,
317 'username': opts.username,
318 'password': opts.password,
319 'twofactor': opts.twofactor,
320 'videopassword': opts.videopassword,
321 'ap_mso': opts.ap_mso,
322 'ap_username': opts.ap_username,
323 'ap_password': opts.ap_password,
324 'quiet': (opts.quiet or any_getting or any_printing),
325 'no_warnings': opts.no_warnings,
326 'forceurl': opts.geturl,
327 'forcetitle': opts.gettitle,
328 'forceid': opts.getid,
329 'forcethumbnail': opts.getthumbnail,
330 'forcedescription': opts.getdescription,
331 'forceduration': opts.getduration,
332 'forcefilename': opts.getfilename,
333 'forceformat': opts.getformat,
334 'forcejson': opts.dumpjson or opts.print_json,
335 'dump_single_json': opts.dump_single_json,
336 'simulate': opts.simulate or any_getting,
337 'skip_download': opts.skip_download,
338 'format': opts.format,
339 'listformats': opts.listformats,
340 'outtmpl': outtmpl,
341 'autonumber_size': opts.autonumber_size,
342 'autonumber_start': opts.autonumber_start,
343 'restrictfilenames': opts.restrictfilenames,
344 'ignoreerrors': opts.ignoreerrors,
345 'force_generic_extractor': opts.force_generic_extractor,
346 'ratelimit': opts.ratelimit,
347 'nooverwrites': opts.nooverwrites,
348 'retries': opts.retries,
349 'fragment_retries': opts.fragment_retries,
350 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
351 'keep_fragments': opts.keep_fragments,
352 'buffersize': opts.buffersize,
353 'noresizebuffer': opts.noresizebuffer,
354 'http_chunk_size': opts.http_chunk_size,
355 'continuedl': opts.continue_dl,
356 'noprogress': opts.noprogress,
357 'progress_with_newline': opts.progress_with_newline,
358 'playliststart': opts.playliststart,
359 'playlistend': opts.playlistend,
360 'playlistreverse': opts.playlist_reverse,
361 'playlistrandom': opts.playlist_random,
362 'noplaylist': opts.noplaylist,
363 'logtostderr': opts.outtmpl == '-',
364 'consoletitle': opts.consoletitle,
365 'nopart': opts.nopart,
366 'updatetime': opts.updatetime,
367 'writedescription': opts.writedescription,
368 'writeannotations': opts.writeannotations,
369 'writeinfojson': opts.writeinfojson,
370 'writethumbnail': opts.writethumbnail,
371 'write_all_thumbnails': opts.write_all_thumbnails,
372 'writesubtitles': opts.writesubtitles,
373 'writeautomaticsub': opts.writeautomaticsub,
374 'allsubtitles': opts.allsubtitles,
375 'listsubtitles': opts.listsubtitles,
376 'subtitlesformat': opts.subtitlesformat,
377 'subtitleslangs': opts.subtitleslangs,
378 'matchtitle': decodeOption(opts.matchtitle),
379 'rejecttitle': decodeOption(opts.rejecttitle),
380 'max_downloads': opts.max_downloads,
381 'prefer_free_formats': opts.prefer_free_formats,
382 'verbose': opts.verbose,
383 'dump_intermediate_pages': opts.dump_intermediate_pages,
384 'write_pages': opts.write_pages,
385 'test': opts.test,
386 'keepvideo': opts.keepvideo,
387 'min_filesize': opts.min_filesize,
388 'max_filesize': opts.max_filesize,
389 'min_views': opts.min_views,
390 'max_views': opts.max_views,
391 'daterange': date,
392 'cachedir': opts.cachedir,
393 'youtube_print_sig_code': opts.youtube_print_sig_code,
394 'age_limit': opts.age_limit,
395 'download_archive': download_archive_fn,
396 'cookiefile': opts.cookiefile,
397 'nocheckcertificate': opts.no_check_certificate,
398 'prefer_insecure': opts.prefer_insecure,
399 'proxy': opts.proxy,
400 'socket_timeout': opts.socket_timeout,
401 'bidi_workaround': opts.bidi_workaround,
402 'debug_printtraffic': opts.debug_printtraffic,
403 'prefer_ffmpeg': opts.prefer_ffmpeg,
404 'include_ads': opts.include_ads,
405 'default_search': opts.default_search,
406 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
407 'encoding': opts.encoding,
408 'extract_flat': opts.extract_flat,
409 'mark_watched': opts.mark_watched,
410 'merge_output_format': opts.merge_output_format,
411 'postprocessors': postprocessors,
412 'fixup': opts.fixup,
413 'source_address': opts.source_address,
414 'call_home': opts.call_home,
415 'sleep_interval': opts.sleep_interval,
416 'max_sleep_interval': opts.max_sleep_interval,
417 'external_downloader': opts.external_downloader,
418 'list_thumbnails': opts.list_thumbnails,
419 'playlist_items': opts.playlist_items,
420 'xattr_set_filesize': opts.xattr_set_filesize,
421 'match_filter': match_filter,
422 'no_color': opts.no_color,
423 'ffmpeg_location': opts.ffmpeg_location,
424 'hls_prefer_native': opts.hls_prefer_native,
425 'hls_use_mpegts': opts.hls_use_mpegts,
426 'external_downloader_args': external_downloader_args,
427 'postprocessor_args': postprocessor_args,
428 'cn_verification_proxy': opts.cn_verification_proxy,
429 'geo_verification_proxy': opts.geo_verification_proxy,
430 'config_location': opts.config_location,
431 'geo_bypass': opts.geo_bypass,
432 'geo_bypass_country': opts.geo_bypass_country,
433 # just for deprecation check
434 'autonumber': opts.autonumber if opts.autonumber is True else None,
435 'usetitle': opts.usetitle if opts.usetitle is True else None,
436 }
437
438 with YoutubeDL(ydl_opts) as ydl:
439 # Update version
440 if opts.update_self:
441 update_self(ydl.to_screen, opts.verbose, ydl._opener)
442
443 # Remove cache dir
444 if opts.rm_cachedir:
445 ydl.cache.remove()
446
447 # Maybe do nothing
448 if (len(all_urls) < 1) and (opts.load_info_filename is None):
449 if opts.update_self or opts.rm_cachedir:
450 sys.exit()
451
452 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
453 parser.error(
454 'You must provide at least one URL.\n'
455 'Type youtube-dl --help to see a list of all options.')
456
457 try:
458 if opts.load_info_filename is not None:
459 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
460 else:
461 retcode = ydl.download(all_urls)
462 except MaxDownloadsReached:
463 ydl.to_screen('--max-download limit reached, aborting.')
464 retcode = 101
465
466 sys.exit(retcode)
467
468
469 def main(argv=None):
470 try:
471 _real_main(argv)
472 except DownloadError:
473 sys.exit(1)
474 except SameFileError:
475 sys.exit('ERROR: fixed output name but more than one file to download')
476 except KeyboardInterrupt:
477 sys.exit('\nERROR: Interrupted by user')
478
479
480 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']