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