__init__.py (20585B)
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/ytdl-org/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 %s could not be read' % opts.batchfile) 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.sleep_interval is None: 170 parser.error('min sleep interval must be specified, use --min-sleep-interval') 171 if opts.max_sleep_interval < opts.sleep_interval: 172 parser.error('max sleep interval must be greater than or equal to min sleep interval') 173 else: 174 opts.max_sleep_interval = opts.sleep_interval 175 if opts.ap_mso and opts.ap_mso not in MSO_INFO: 176 parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers') 177 178 def parse_retries(retries): 179 if retries in ('inf', 'infinite'): 180 parsed_retries = float('inf') 181 else: 182 try: 183 parsed_retries = int(retries) 184 except (TypeError, ValueError): 185 parser.error('invalid retry count specified') 186 return parsed_retries 187 if opts.retries is not None: 188 opts.retries = parse_retries(opts.retries) 189 if opts.fragment_retries is not None: 190 opts.fragment_retries = parse_retries(opts.fragment_retries) 191 if opts.buffersize is not None: 192 numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) 193 if numeric_buffersize is None: 194 parser.error('invalid buffer size specified') 195 opts.buffersize = numeric_buffersize 196 if opts.http_chunk_size is not None: 197 numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size) 198 if not numeric_chunksize: 199 parser.error('invalid http chunk size specified') 200 opts.http_chunk_size = numeric_chunksize 201 if opts.playliststart <= 0: 202 raise ValueError('Playlist start must be positive') 203 if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart: 204 raise ValueError('Playlist end must be greater than playlist start') 205 if opts.extractaudio: 206 if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']: 207 parser.error('invalid audio format specified') 208 if opts.audioquality: 209 opts.audioquality = opts.audioquality.strip('k').strip('K') 210 if not opts.audioquality.isdigit(): 211 parser.error('invalid audio quality specified') 212 if opts.recodevideo is not None: 213 if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']: 214 parser.error('invalid video recode format specified') 215 if opts.convertsubtitles is not None: 216 if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']: 217 parser.error('invalid subtitle format specified') 218 219 if opts.date is not None: 220 date = DateRange.day(opts.date) 221 else: 222 date = DateRange(opts.dateafter, opts.datebefore) 223 224 # Do not download videos when there are audio-only formats 225 if opts.extractaudio and not opts.keepvideo and opts.format is None: 226 opts.format = 'bestaudio/best' 227 228 # --all-sub automatically sets --write-sub if --write-auto-sub is not given 229 # this was the old behaviour if only --all-sub was given. 230 if opts.allsubtitles and not opts.writeautomaticsub: 231 opts.writesubtitles = True 232 233 outtmpl = ((opts.outtmpl is not None and opts.outtmpl) 234 or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') 235 or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') 236 or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') 237 or (opts.usetitle and '%(title)s-%(id)s.%(ext)s') 238 or (opts.useid and '%(id)s.%(ext)s') 239 or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') 240 or DEFAULT_OUTTMPL) 241 if not os.path.splitext(outtmpl)[1] and opts.extractaudio: 242 parser.error('Cannot download a video and extract audio into the same' 243 ' file! Use "{0}.%(ext)s" instead of "{0}" as the output' 244 ' template'.format(outtmpl)) 245 246 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 247 any_printing = opts.print_json 248 download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive 249 250 # PostProcessors 251 postprocessors = [] 252 if opts.metafromtitle: 253 postprocessors.append({ 254 'key': 'MetadataFromTitle', 255 'titleformat': opts.metafromtitle 256 }) 257 if opts.extractaudio: 258 postprocessors.append({ 259 'key': 'FFmpegExtractAudio', 260 'preferredcodec': opts.audioformat, 261 'preferredquality': opts.audioquality, 262 'nopostoverwrites': opts.nopostoverwrites, 263 }) 264 if opts.recodevideo: 265 postprocessors.append({ 266 'key': 'FFmpegVideoConvertor', 267 'preferedformat': opts.recodevideo, 268 }) 269 # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and 270 # FFmpegExtractAudioPP as containers before conversion may not support 271 # metadata (3gp, webm, etc.) 272 # And this post-processor should be placed before other metadata 273 # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of 274 # extra metadata. By default ffmpeg preserves metadata applicable for both 275 # source and target containers. From this point the container won't change, 276 # so metadata can be added here. 277 if opts.addmetadata: 278 postprocessors.append({'key': 'FFmpegMetadata'}) 279 if opts.convertsubtitles: 280 postprocessors.append({ 281 'key': 'FFmpegSubtitlesConvertor', 282 'format': opts.convertsubtitles, 283 }) 284 if opts.embedsubtitles: 285 postprocessors.append({ 286 'key': 'FFmpegEmbedSubtitle', 287 }) 288 if opts.embedthumbnail: 289 already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails 290 postprocessors.append({ 291 'key': 'EmbedThumbnail', 292 'already_have_thumbnail': already_have_thumbnail 293 }) 294 if not already_have_thumbnail: 295 opts.writethumbnail = True 296 # XAttrMetadataPP should be run after post-processors that may change file 297 # contents 298 if opts.xattrs: 299 postprocessors.append({'key': 'XAttrMetadata'}) 300 # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. 301 # So if the user is able to remove the file before your postprocessor runs it might cause a few problems. 302 if opts.exec_cmd: 303 postprocessors.append({ 304 'key': 'ExecAfterDownload', 305 'exec_cmd': opts.exec_cmd, 306 }) 307 external_downloader_args = None 308 if opts.external_downloader_args: 309 external_downloader_args = compat_shlex_split(opts.external_downloader_args) 310 postprocessor_args = None 311 if opts.postprocessor_args: 312 postprocessor_args = compat_shlex_split(opts.postprocessor_args) 313 match_filter = ( 314 None if opts.match_filter is None 315 else match_filter_func(opts.match_filter)) 316 317 ydl_opts = { 318 'usenetrc': opts.usenetrc, 319 'username': opts.username, 320 'password': opts.password, 321 'twofactor': opts.twofactor, 322 'videopassword': opts.videopassword, 323 'ap_mso': opts.ap_mso, 324 'ap_username': opts.ap_username, 325 'ap_password': opts.ap_password, 326 'quiet': (opts.quiet or any_getting or any_printing), 327 'no_warnings': opts.no_warnings, 328 'forceurl': opts.geturl, 329 'forcetitle': opts.gettitle, 330 'forceid': opts.getid, 331 'forcethumbnail': opts.getthumbnail, 332 'forcedescription': opts.getdescription, 333 'forceduration': opts.getduration, 334 'forcefilename': opts.getfilename, 335 'forceformat': opts.getformat, 336 'forcejson': opts.dumpjson or opts.print_json, 337 'dump_single_json': opts.dump_single_json, 338 'simulate': opts.simulate or any_getting, 339 'skip_download': opts.skip_download, 340 'format': opts.format, 341 'listformats': opts.listformats, 342 'outtmpl': outtmpl, 343 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder, 344 'autonumber_size': opts.autonumber_size, 345 'autonumber_start': opts.autonumber_start, 346 'restrictfilenames': opts.restrictfilenames, 347 'ignoreerrors': opts.ignoreerrors, 348 'force_generic_extractor': opts.force_generic_extractor, 349 'ratelimit': opts.ratelimit, 350 'nooverwrites': opts.nooverwrites, 351 'retries': opts.retries, 352 'fragment_retries': opts.fragment_retries, 353 'skip_unavailable_fragments': opts.skip_unavailable_fragments, 354 'keep_fragments': opts.keep_fragments, 355 'buffersize': opts.buffersize, 356 'noresizebuffer': opts.noresizebuffer, 357 'http_chunk_size': opts.http_chunk_size, 358 'continuedl': opts.continue_dl, 359 'noprogress': opts.noprogress, 360 'progress_with_newline': opts.progress_with_newline, 361 'playliststart': opts.playliststart, 362 'playlistend': opts.playlistend, 363 'playlistreverse': opts.playlist_reverse, 364 'playlistrandom': opts.playlist_random, 365 'noplaylist': opts.noplaylist, 366 'logtostderr': opts.outtmpl == '-', 367 'consoletitle': opts.consoletitle, 368 'nopart': opts.nopart, 369 'updatetime': opts.updatetime, 370 'writedescription': opts.writedescription, 371 'writeannotations': opts.writeannotations, 372 'writeinfojson': opts.writeinfojson, 373 'writethumbnail': opts.writethumbnail, 374 'write_all_thumbnails': opts.write_all_thumbnails, 375 'writesubtitles': opts.writesubtitles, 376 'writeautomaticsub': opts.writeautomaticsub, 377 'allsubtitles': opts.allsubtitles, 378 'listsubtitles': opts.listsubtitles, 379 'subtitlesformat': opts.subtitlesformat, 380 'subtitleslangs': opts.subtitleslangs, 381 'matchtitle': decodeOption(opts.matchtitle), 382 'rejecttitle': decodeOption(opts.rejecttitle), 383 'max_downloads': opts.max_downloads, 384 'prefer_free_formats': opts.prefer_free_formats, 385 'verbose': opts.verbose, 386 'dump_intermediate_pages': opts.dump_intermediate_pages, 387 'write_pages': opts.write_pages, 388 'test': opts.test, 389 'keepvideo': opts.keepvideo, 390 'min_filesize': opts.min_filesize, 391 'max_filesize': opts.max_filesize, 392 'min_views': opts.min_views, 393 'max_views': opts.max_views, 394 'daterange': date, 395 'cachedir': opts.cachedir, 396 'youtube_print_sig_code': opts.youtube_print_sig_code, 397 'age_limit': opts.age_limit, 398 'download_archive': download_archive_fn, 399 'cookiefile': opts.cookiefile, 400 'nocheckcertificate': opts.no_check_certificate, 401 'prefer_insecure': opts.prefer_insecure, 402 'proxy': opts.proxy, 403 'socket_timeout': opts.socket_timeout, 404 'bidi_workaround': opts.bidi_workaround, 405 'debug_printtraffic': opts.debug_printtraffic, 406 'prefer_ffmpeg': opts.prefer_ffmpeg, 407 'include_ads': opts.include_ads, 408 'default_search': opts.default_search, 409 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 410 'encoding': opts.encoding, 411 'extract_flat': opts.extract_flat, 412 'mark_watched': opts.mark_watched, 413 'merge_output_format': opts.merge_output_format, 414 'postprocessors': postprocessors, 415 'fixup': opts.fixup, 416 'source_address': opts.source_address, 417 'call_home': opts.call_home, 418 'sleep_interval': opts.sleep_interval, 419 'max_sleep_interval': opts.max_sleep_interval, 420 'external_downloader': opts.external_downloader, 421 'list_thumbnails': opts.list_thumbnails, 422 'playlist_items': opts.playlist_items, 423 'xattr_set_filesize': opts.xattr_set_filesize, 424 'match_filter': match_filter, 425 'no_color': opts.no_color, 426 'ffmpeg_location': opts.ffmpeg_location, 427 'hls_prefer_native': opts.hls_prefer_native, 428 'hls_use_mpegts': opts.hls_use_mpegts, 429 'external_downloader_args': external_downloader_args, 430 'postprocessor_args': postprocessor_args, 431 'cn_verification_proxy': opts.cn_verification_proxy, 432 'geo_verification_proxy': opts.geo_verification_proxy, 433 'config_location': opts.config_location, 434 'geo_bypass': opts.geo_bypass, 435 'geo_bypass_country': opts.geo_bypass_country, 436 'geo_bypass_ip_block': opts.geo_bypass_ip_block, 437 # just for deprecation check 438 'autonumber': opts.autonumber if opts.autonumber is True else None, 439 'usetitle': opts.usetitle if opts.usetitle is True else None, 440 } 441 442 with YoutubeDL(ydl_opts) as ydl: 443 # Update version 444 if opts.update_self: 445 update_self(ydl.to_screen, opts.verbose, ydl._opener) 446 447 # Remove cache dir 448 if opts.rm_cachedir: 449 ydl.cache.remove() 450 451 # Maybe do nothing 452 if (len(all_urls) < 1) and (opts.load_info_filename is None): 453 if opts.update_self or opts.rm_cachedir: 454 sys.exit() 455 456 ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv) 457 parser.error( 458 'You must provide at least one URL.\n' 459 'Type youtube-dl --help to see a list of all options.') 460 461 try: 462 if opts.load_info_filename is not None: 463 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename)) 464 else: 465 retcode = ydl.download(all_urls) 466 except MaxDownloadsReached: 467 ydl.to_screen('--max-download limit reached, aborting.') 468 retcode = 101 469 470 sys.exit(retcode) 471 472 473 def main(argv=None): 474 try: 475 _real_main(argv) 476 except DownloadError: 477 sys.exit(1) 478 except SameFileError: 479 sys.exit('ERROR: fixed output name but more than one file to download') 480 except KeyboardInterrupt: 481 sys.exit('\nERROR: Interrupted by user') 482 483 484 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']