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 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-dlc')
  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.remuxvideo is not None:
 213         if opts.remuxvideo not in ['mp4', 'mkv']:
 214             parser.error('invalid video container format specified')
 215     if opts.recodevideo is not None:
 216         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
 217             parser.error('invalid video recode format specified')
 218     if opts.convertsubtitles is not None:
 219         if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
 220             parser.error('invalid subtitle format specified')
 221
 222     if opts.date is not None:
 223         date = DateRange.day(opts.date)
 224     else:
 225         date = DateRange(opts.dateafter, opts.datebefore)
 226
 227     # Do not download videos when there are audio-only formats
 228     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 229         opts.format = 'bestaudio/best'
 230
 231     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 232     # this was the old behaviour if only --all-sub was given.
 233     if opts.allsubtitles and not opts.writeautomaticsub:
 234         opts.writesubtitles = True
 235
 236     outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
 237                or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
 238                or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
 239                or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 240                or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
 241                or (opts.useid and '%(id)s.%(ext)s')
 242                or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
 243                or DEFAULT_OUTTMPL)
 244     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 245         parser.error('Cannot download a video and extract audio into the same'
 246                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 247                      ' template'.format(outtmpl))
 248
 249     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
 250     any_printing = opts.print_json
 251     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 252
 253     # PostProcessors
 254     postprocessors = []
 255     if opts.metafromtitle:
 256         postprocessors.append({
 257             'key': 'MetadataFromTitle',
 258             'titleformat': opts.metafromtitle
 259         })
 260     if opts.extractaudio:
 261         postprocessors.append({
 262             'key': 'FFmpegExtractAudio',
 263             'preferredcodec': opts.audioformat,
 264             'preferredquality': opts.audioquality,
 265             'nopostoverwrites': opts.nopostoverwrites,
 266         })
 267     if opts.remuxvideo:
 268         postprocessors.append({
 269             'key': 'FFmpegVideoRemuxer',
 270             'preferedformat': opts.remuxvideo,
 271         })
 272     if opts.recodevideo:
 273         postprocessors.append({
 274             'key': 'FFmpegVideoConvertor',
 275             'preferedformat': opts.recodevideo,
 276         })
 277     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 278     # FFmpegExtractAudioPP as containers before conversion may not support
 279     # metadata (3gp, webm, etc.)
 280     # And this post-processor should be placed before other metadata
 281     # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
 282     # extra metadata. By default ffmpeg preserves metadata applicable for both
 283     # source and target containers. From this point the container won't change,
 284     # so metadata can be added here.
 285     if opts.addmetadata:
 286         postprocessors.append({'key': 'FFmpegMetadata'})
 287     if opts.convertsubtitles:
 288         postprocessors.append({
 289             'key': 'FFmpegSubtitlesConvertor',
 290             'format': opts.convertsubtitles,
 291         })
 292     if opts.embedsubtitles:
 293         postprocessors.append({
 294             'key': 'FFmpegEmbedSubtitle',
 295         })
 296     if opts.embedthumbnail:
 297         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
 298         postprocessors.append({
 299             'key': 'EmbedThumbnail',
 300             'already_have_thumbnail': already_have_thumbnail
 301         })
 302         if not already_have_thumbnail:
 303             opts.writethumbnail = True
 304     # XAttrMetadataPP should be run after post-processors that may change file
 305     # contents
 306     if opts.xattrs:
 307         postprocessors.append({'key': 'XAttrMetadata'})
 308     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 309     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 310     if opts.exec_cmd:
 311         postprocessors.append({
 312             'key': 'ExecAfterDownload',
 313             'exec_cmd': opts.exec_cmd,
 314         })
 315     external_downloader_args = None
 316     if opts.external_downloader_args:
 317         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
 318     postprocessor_args = None
 319     if opts.postprocessor_args:
 320         postprocessor_args = compat_shlex_split(opts.postprocessor_args)
 321     match_filter = (
 322         None if opts.match_filter is None
 323         else match_filter_func(opts.match_filter))
 324
 325     ydl_opts = {
 326         'convertsubtitles': opts.convertsubtitles,
 327         'usenetrc': opts.usenetrc,
 328         'username': opts.username,
 329         'password': opts.password,
 330         'twofactor': opts.twofactor,
 331         'videopassword': opts.videopassword,
 332         'ap_mso': opts.ap_mso,
 333         'ap_username': opts.ap_username,
 334         'ap_password': opts.ap_password,
 335         'quiet': (opts.quiet or any_getting or any_printing),
 336         'no_warnings': opts.no_warnings,
 337         'forceurl': opts.geturl,
 338         'forcetitle': opts.gettitle,
 339         'forceid': opts.getid,
 340         'forcethumbnail': opts.getthumbnail,
 341         'forcedescription': opts.getdescription,
 342         'forceduration': opts.getduration,
 343         'forcefilename': opts.getfilename,
 344         'forceformat': opts.getformat,
 345         'forcejson': opts.dumpjson or opts.print_json,
 346         'dump_single_json': opts.dump_single_json,
 347         'simulate': opts.simulate or any_getting,
 348         'skip_download': opts.skip_download,
 349         'format': opts.format,
 350         'listformats': opts.listformats,
 351         'outtmpl': outtmpl,
 352         'autonumber_size': opts.autonumber_size,
 353         'autonumber_start': opts.autonumber_start,
 354         'restrictfilenames': opts.restrictfilenames,
 355         'ignoreerrors': opts.ignoreerrors,
 356         'force_generic_extractor': opts.force_generic_extractor,
 357         'ratelimit': opts.ratelimit,
 358         'nooverwrites': opts.nooverwrites,
 359         'retries': opts.retries,
 360         'fragment_retries': opts.fragment_retries,
 361         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 362         'keep_fragments': opts.keep_fragments,
 363         'buffersize': opts.buffersize,
 364         'noresizebuffer': opts.noresizebuffer,
 365         'http_chunk_size': opts.http_chunk_size,
 366         'continuedl': opts.continue_dl,
 367         'noprogress': opts.noprogress,
 368         'progress_with_newline': opts.progress_with_newline,
 369         'playliststart': opts.playliststart,
 370         'playlistend': opts.playlistend,
 371         'playlistreverse': opts.playlist_reverse,
 372         'playlistrandom': opts.playlist_random,
 373         'noplaylist': opts.noplaylist,
 374         'logtostderr': opts.outtmpl == '-',
 375         'consoletitle': opts.consoletitle,
 376         'nopart': opts.nopart,
 377         'updatetime': opts.updatetime,
 378         'writedescription': opts.writedescription,
 379         'writeannotations': opts.writeannotations,
 380         'writeinfojson': opts.writeinfojson,
 381         'writethumbnail': opts.writethumbnail,
 382         'write_all_thumbnails': opts.write_all_thumbnails,
 383         'writesubtitles': opts.writesubtitles,
 384         'writeautomaticsub': opts.writeautomaticsub,
 385         'allsubtitles': opts.allsubtitles,
 386         'listsubtitles': opts.listsubtitles,
 387         'subtitlesformat': opts.subtitlesformat,
 388         'subtitleslangs': opts.subtitleslangs,
 389         'matchtitle': decodeOption(opts.matchtitle),
 390         'rejecttitle': decodeOption(opts.rejecttitle),
 391         'max_downloads': opts.max_downloads,
 392         'prefer_free_formats': opts.prefer_free_formats,
 393         'verbose': opts.verbose,
 394         'dump_intermediate_pages': opts.dump_intermediate_pages,
 395         'write_pages': opts.write_pages,
 396         'test': opts.test,
 397         'keepvideo': opts.keepvideo,
 398         'min_filesize': opts.min_filesize,
 399         'max_filesize': opts.max_filesize,
 400         'min_views': opts.min_views,
 401         'max_views': opts.max_views,
 402         'daterange': date,
 403         'cachedir': opts.cachedir,
 404         'youtube_print_sig_code': opts.youtube_print_sig_code,
 405         'age_limit': opts.age_limit,
 406         'download_archive': download_archive_fn,
 407         'cookiefile': opts.cookiefile,
 408         'nocheckcertificate': opts.no_check_certificate,
 409         'prefer_insecure': opts.prefer_insecure,
 410         'proxy': opts.proxy,
 411         'socket_timeout': opts.socket_timeout,
 412         'bidi_workaround': opts.bidi_workaround,
 413         'debug_printtraffic': opts.debug_printtraffic,
 414         'prefer_ffmpeg': opts.prefer_ffmpeg,
 415         'include_ads': opts.include_ads,
 416         'default_search': opts.default_search,
 417         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 418         'encoding': opts.encoding,
 419         'extract_flat': opts.extract_flat,
 420         'mark_watched': opts.mark_watched,
 421         'merge_output_format': opts.merge_output_format,
 422         'postprocessors': postprocessors,
 423         'fixup': opts.fixup,
 424         'source_address': opts.source_address,
 425         'call_home': opts.call_home,
 426         'sleep_interval': opts.sleep_interval,
 427         'max_sleep_interval': opts.max_sleep_interval,
 428         'external_downloader': opts.external_downloader,
 429         'list_thumbnails': opts.list_thumbnails,
 430         'playlist_items': opts.playlist_items,
 431         'xattr_set_filesize': opts.xattr_set_filesize,
 432         'match_filter': match_filter,
 433         'no_color': opts.no_color,
 434         'ffmpeg_location': opts.ffmpeg_location,
 435         'hls_prefer_native': opts.hls_prefer_native,
 436         'hls_use_mpegts': opts.hls_use_mpegts,
 437         'external_downloader_args': external_downloader_args,
 438         'postprocessor_args': postprocessor_args,
 439         'cn_verification_proxy': opts.cn_verification_proxy,
 440         'geo_verification_proxy': opts.geo_verification_proxy,
 441         'config_location': opts.config_location,
 442         'geo_bypass': opts.geo_bypass,
 443         'geo_bypass_country': opts.geo_bypass_country,
 444         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 445         # just for deprecation check
 446         'autonumber': opts.autonumber if opts.autonumber is True else None,
 447         'usetitle': opts.usetitle if opts.usetitle is True else None,
 448     }
 449
 450     with YoutubeDL(ydl_opts) as ydl:
 451         # Update version
 452         if opts.update_self:
 453             update_self(ydl.to_screen, opts.verbose, ydl._opener)
 454
 455         # Remove cache dir
 456         if opts.rm_cachedir:
 457             ydl.cache.remove()
 458
 459         # Maybe do nothing
 460         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 461             if opts.update_self or opts.rm_cachedir:
 462                 sys.exit()
 463
 464             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 465             parser.error(
 466                 'You must provide at least one URL.\n'
 467                 'Type youtube-dlc --help to see a list of all options.')
 468
 469         try:
 470             if opts.load_info_filename is not None:
 471                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
 472             else:
 473                 retcode = ydl.download(all_urls)
 474         except MaxDownloadsReached:
 475             ydl.to_screen('--max-download limit reached, aborting.')
 476             retcode = 101
 477
 478     sys.exit(retcode)
 479
 480
 481 def main(argv=None):
 482     try:
 483         _real_main(argv)
 484     except DownloadError:
 485         sys.exit(1)
 486     except SameFileError:
 487         sys.exit('ERROR: fixed output name but more than one file to download')
 488     except KeyboardInterrupt:
 489         sys.exit('\nERROR: Interrupted by user')
 490
 491
 492 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']