]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/__init__.py
Prepare to upload
[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.playliststart <= 0:
195 raise ValueError('Playlist start must be positive')
196 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
197 raise ValueError('Playlist end must be greater than playlist start')
198 if opts.extractaudio:
199 if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
200 parser.error('invalid audio format specified')
201 if opts.audioquality:
202 opts.audioquality = opts.audioquality.strip('k').strip('K')
203 if not opts.audioquality.isdigit():
204 parser.error('invalid audio quality specified')
205 if opts.recodevideo is not None:
206 if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
207 parser.error('invalid video recode format specified')
208 if opts.convertsubtitles is not None:
209 if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
210 parser.error('invalid subtitle format specified')
211
212 if opts.date is not None:
213 date = DateRange.day(opts.date)
214 else:
215 date = DateRange(opts.dateafter, opts.datebefore)
216
217 # Do not download videos when there are audio-only formats
218 if opts.extractaudio and not opts.keepvideo and opts.format is None:
219 opts.format = 'bestaudio/best'
220
221 # --all-sub automatically sets --write-sub if --write-auto-sub is not given
222 # this was the old behaviour if only --all-sub was given.
223 if opts.allsubtitles and not opts.writeautomaticsub:
224 opts.writesubtitles = True
225
226 outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
227 (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
228 (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
229 (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
230 (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
231 (opts.useid and '%(id)s.%(ext)s') or
232 (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
233 DEFAULT_OUTTMPL)
234 if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
235 parser.error('Cannot download a video and extract audio into the same'
236 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
237 ' template'.format(outtmpl))
238
239 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
240 any_printing = opts.print_json
241 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
242
243 # PostProcessors
244 postprocessors = []
245 if opts.metafromtitle:
246 postprocessors.append({
247 'key': 'MetadataFromTitle',
248 'titleformat': opts.metafromtitle
249 })
250 if opts.extractaudio:
251 postprocessors.append({
252 'key': 'FFmpegExtractAudio',
253 'preferredcodec': opts.audioformat,
254 'preferredquality': opts.audioquality,
255 'nopostoverwrites': opts.nopostoverwrites,
256 })
257 if opts.recodevideo:
258 postprocessors.append({
259 'key': 'FFmpegVideoConvertor',
260 'preferedformat': opts.recodevideo,
261 })
262 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
263 # FFmpegExtractAudioPP as containers before conversion may not support
264 # metadata (3gp, webm, etc.)
265 # And this post-processor should be placed before other metadata
266 # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
267 # extra metadata. By default ffmpeg preserves metadata applicable for both
268 # source and target containers. From this point the container won't change,
269 # so metadata can be added here.
270 if opts.addmetadata:
271 postprocessors.append({'key': 'FFmpegMetadata'})
272 if opts.convertsubtitles:
273 postprocessors.append({
274 'key': 'FFmpegSubtitlesConvertor',
275 'format': opts.convertsubtitles,
276 })
277 if opts.embedsubtitles:
278 postprocessors.append({
279 'key': 'FFmpegEmbedSubtitle',
280 })
281 if opts.embedthumbnail:
282 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
283 postprocessors.append({
284 'key': 'EmbedThumbnail',
285 'already_have_thumbnail': already_have_thumbnail
286 })
287 if not already_have_thumbnail:
288 opts.writethumbnail = True
289 # XAttrMetadataPP should be run after post-processors that may change file
290 # contents
291 if opts.xattrs:
292 postprocessors.append({'key': 'XAttrMetadata'})
293 # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
294 # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
295 if opts.exec_cmd:
296 postprocessors.append({
297 'key': 'ExecAfterDownload',
298 'exec_cmd': opts.exec_cmd,
299 })
300 external_downloader_args = None
301 if opts.external_downloader_args:
302 external_downloader_args = compat_shlex_split(opts.external_downloader_args)
303 postprocessor_args = None
304 if opts.postprocessor_args:
305 postprocessor_args = compat_shlex_split(opts.postprocessor_args)
306 match_filter = (
307 None if opts.match_filter is None
308 else match_filter_func(opts.match_filter))
309
310 ydl_opts = {
311 'usenetrc': opts.usenetrc,
312 'username': opts.username,
313 'password': opts.password,
314 'twofactor': opts.twofactor,
315 'videopassword': opts.videopassword,
316 'ap_mso': opts.ap_mso,
317 'ap_username': opts.ap_username,
318 'ap_password': opts.ap_password,
319 'quiet': (opts.quiet or any_getting or any_printing),
320 'no_warnings': opts.no_warnings,
321 'forceurl': opts.geturl,
322 'forcetitle': opts.gettitle,
323 'forceid': opts.getid,
324 'forcethumbnail': opts.getthumbnail,
325 'forcedescription': opts.getdescription,
326 'forceduration': opts.getduration,
327 'forcefilename': opts.getfilename,
328 'forceformat': opts.getformat,
329 'forcejson': opts.dumpjson or opts.print_json,
330 'dump_single_json': opts.dump_single_json,
331 'simulate': opts.simulate or any_getting,
332 'skip_download': opts.skip_download,
333 'format': opts.format,
334 'listformats': opts.listformats,
335 'outtmpl': outtmpl,
336 'autonumber_size': opts.autonumber_size,
337 'autonumber_start': opts.autonumber_start,
338 'restrictfilenames': opts.restrictfilenames,
339 'ignoreerrors': opts.ignoreerrors,
340 'force_generic_extractor': opts.force_generic_extractor,
341 'ratelimit': opts.ratelimit,
342 'nooverwrites': opts.nooverwrites,
343 'retries': opts.retries,
344 'fragment_retries': opts.fragment_retries,
345 'skip_unavailable_fragments': opts.skip_unavailable_fragments,
346 'keep_fragments': opts.keep_fragments,
347 'buffersize': opts.buffersize,
348 'noresizebuffer': opts.noresizebuffer,
349 'continuedl': opts.continue_dl,
350 'noprogress': opts.noprogress,
351 'progress_with_newline': opts.progress_with_newline,
352 'playliststart': opts.playliststart,
353 'playlistend': opts.playlistend,
354 'playlistreverse': opts.playlist_reverse,
355 'playlistrandom': opts.playlist_random,
356 'noplaylist': opts.noplaylist,
357 'logtostderr': opts.outtmpl == '-',
358 'consoletitle': opts.consoletitle,
359 'nopart': opts.nopart,
360 'updatetime': opts.updatetime,
361 'writedescription': opts.writedescription,
362 'writeannotations': opts.writeannotations,
363 'writeinfojson': opts.writeinfojson,
364 'writethumbnail': opts.writethumbnail,
365 'write_all_thumbnails': opts.write_all_thumbnails,
366 'writesubtitles': opts.writesubtitles,
367 'writeautomaticsub': opts.writeautomaticsub,
368 'allsubtitles': opts.allsubtitles,
369 'listsubtitles': opts.listsubtitles,
370 'subtitlesformat': opts.subtitlesformat,
371 'subtitleslangs': opts.subtitleslangs,
372 'matchtitle': decodeOption(opts.matchtitle),
373 'rejecttitle': decodeOption(opts.rejecttitle),
374 'max_downloads': opts.max_downloads,
375 'prefer_free_formats': opts.prefer_free_formats,
376 'verbose': opts.verbose,
377 'dump_intermediate_pages': opts.dump_intermediate_pages,
378 'write_pages': opts.write_pages,
379 'test': opts.test,
380 'keepvideo': opts.keepvideo,
381 'min_filesize': opts.min_filesize,
382 'max_filesize': opts.max_filesize,
383 'min_views': opts.min_views,
384 'max_views': opts.max_views,
385 'daterange': date,
386 'cachedir': opts.cachedir,
387 'youtube_print_sig_code': opts.youtube_print_sig_code,
388 'age_limit': opts.age_limit,
389 'download_archive': download_archive_fn,
390 'cookiefile': opts.cookiefile,
391 'nocheckcertificate': opts.no_check_certificate,
392 'prefer_insecure': opts.prefer_insecure,
393 'proxy': opts.proxy,
394 'socket_timeout': opts.socket_timeout,
395 'bidi_workaround': opts.bidi_workaround,
396 'debug_printtraffic': opts.debug_printtraffic,
397 'prefer_ffmpeg': opts.prefer_ffmpeg,
398 'include_ads': opts.include_ads,
399 'default_search': opts.default_search,
400 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
401 'encoding': opts.encoding,
402 'extract_flat': opts.extract_flat,
403 'mark_watched': opts.mark_watched,
404 'merge_output_format': opts.merge_output_format,
405 'postprocessors': postprocessors,
406 'fixup': opts.fixup,
407 'source_address': opts.source_address,
408 'call_home': opts.call_home,
409 'sleep_interval': opts.sleep_interval,
410 'max_sleep_interval': opts.max_sleep_interval,
411 'external_downloader': opts.external_downloader,
412 'list_thumbnails': opts.list_thumbnails,
413 'playlist_items': opts.playlist_items,
414 'xattr_set_filesize': opts.xattr_set_filesize,
415 'match_filter': match_filter,
416 'no_color': opts.no_color,
417 'ffmpeg_location': opts.ffmpeg_location,
418 'hls_prefer_native': opts.hls_prefer_native,
419 'hls_use_mpegts': opts.hls_use_mpegts,
420 'external_downloader_args': external_downloader_args,
421 'postprocessor_args': postprocessor_args,
422 'cn_verification_proxy': opts.cn_verification_proxy,
423 'geo_verification_proxy': opts.geo_verification_proxy,
424 'config_location': opts.config_location,
425 'geo_bypass': opts.geo_bypass,
426 'geo_bypass_country': opts.geo_bypass_country,
427 # just for deprecation check
428 'autonumber': opts.autonumber if opts.autonumber is True else None,
429 'usetitle': opts.usetitle if opts.usetitle is True else None,
430 }
431
432 with YoutubeDL(ydl_opts) as ydl:
433 # Update version
434 if opts.update_self:
435 update_self(ydl.to_screen, opts.verbose, ydl._opener)
436
437 # Remove cache dir
438 if opts.rm_cachedir:
439 ydl.cache.remove()
440
441 # Maybe do nothing
442 if (len(all_urls) < 1) and (opts.load_info_filename is None):
443 if opts.update_self or opts.rm_cachedir:
444 sys.exit()
445
446 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
447 parser.error(
448 'You must provide at least one URL.\n'
449 'Type youtube-dl --help to see a list of all options.')
450
451 try:
452 if opts.load_info_filename is not None:
453 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
454 else:
455 retcode = ydl.download(all_urls)
456 except MaxDownloadsReached:
457 ydl.to_screen('--max-download limit reached, aborting.')
458 retcode = 101
459
460 sys.exit(retcode)
461
462
463 def main(argv=None):
464 try:
465 _real_main(argv)
466 except DownloadError:
467 sys.exit(1)
468 except SameFileError:
469 sys.exit('ERROR: fixed output name but more than one file to download')
470 except KeyboardInterrupt:
471 sys.exit('\nERROR: Interrupted by user')
472
473
474 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']