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 re
  13 import sys
  14
  15
  16 from .options import (
  17     parseOpts,
  18 )
  19 from .compat import (
  20     compat_getpass,
  21     workaround_optparse_bug9161,
  22 )
  23 from .utils import (
  24     DateRange,
  25     decodeOption,
  26     DEFAULT_OUTTMPL,
  27     DownloadError,
  28     ExistingVideoReached,
  29     expand_path,
  30     match_filter_func,
  31     MaxDownloadsReached,
  32     preferredencoding,
  33     read_batch_urls,
  34     RejectedVideoReached,
  35     SameFileError,
  36     setproctitle,
  37     std_headers,
  38     write_string,
  39     render_table,
  40 )
  41 from .update import update_self
  42 from .downloader import (
  43     FileDownloader,
  44 )
  45 from .extractor import gen_extractors, list_extractors
  46 from .extractor.common import InfoExtractor
  47 from .extractor.adobepass import MSO_INFO
  48 from .YoutubeDL import YoutubeDL
  49
  50
  51 def _real_main(argv=None):
  52     # Compatibility fixes for Windows
  53     if sys.platform == 'win32':
  54         # https://github.com/ytdl-org/youtube-dl/issues/820
  55         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  56
  57     workaround_optparse_bug9161()
  58
  59     setproctitle('youtube-dlc')
  60
  61     parser, opts, args = parseOpts(argv)
  62
  63     # Set user agent
  64     if opts.user_agent is not None:
  65         std_headers['User-Agent'] = opts.user_agent
  66
  67     # Set referer
  68     if opts.referer is not None:
  69         std_headers['Referer'] = opts.referer
  70
  71     # Custom HTTP headers
  72     std_headers.update(opts.headers)
  73
  74     # Dump user agent
  75     if opts.dump_user_agent:
  76         write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
  77         sys.exit(0)
  78
  79     # Batch file verification
  80     batch_urls = []
  81     if opts.batchfile is not None:
  82         try:
  83             if opts.batchfile == '-':
  84                 batchfd = sys.stdin
  85             else:
  86                 batchfd = io.open(
  87                     expand_path(opts.batchfile),
  88                     'r', encoding='utf-8', errors='ignore')
  89             batch_urls = read_batch_urls(batchfd)
  90             if opts.verbose:
  91                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  92         except IOError:
  93             sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
  94     all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
  95     _enc = preferredencoding()
  96     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
  97
  98     if opts.list_extractors:
  99         for ie in list_extractors(opts.age_limit):
 100             write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
 101             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 102             for mu in matchedUrls:
 103                 write_string('  ' + mu + '\n', out=sys.stdout)
 104         sys.exit(0)
 105     if opts.list_extractor_descriptions:
 106         for ie in list_extractors(opts.age_limit):
 107             if not ie._WORKING:
 108                 continue
 109             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
 110             if desc is False:
 111                 continue
 112             if hasattr(ie, 'SEARCH_KEY'):
 113                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 114                 _COUNTS = ('', '5', '10', 'all')
 115                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
 116             write_string(desc + '\n', out=sys.stdout)
 117         sys.exit(0)
 118     if opts.ap_list_mso:
 119         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
 120         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
 121         sys.exit(0)
 122
 123     # Conflicting, missing and erroneous options
 124     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 125         parser.error('using .netrc conflicts with giving username/password')
 126     if opts.password is not None and opts.username is None:
 127         parser.error('account username missing\n')
 128     if opts.ap_password is not None and opts.ap_username is None:
 129         parser.error('TV Provider account username missing\n')
 130     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
 131         parser.error('using output template conflicts with using title, video ID or auto number')
 132     if opts.autonumber_size is not None:
 133         if opts.autonumber_size <= 0:
 134             parser.error('auto number size must be positive')
 135     if opts.autonumber_start is not None:
 136         if opts.autonumber_start < 0:
 137             parser.error('auto number start must be positive or 0')
 138     if opts.usetitle and opts.useid:
 139         parser.error('using title conflicts with using video ID')
 140     if opts.username is not None and opts.password is None:
 141         opts.password = compat_getpass('Type account password and press [Return]: ')
 142     if opts.ap_username is not None and opts.ap_password is None:
 143         opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
 144     if opts.ratelimit is not None:
 145         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 146         if numeric_limit is None:
 147             parser.error('invalid rate limit specified')
 148         opts.ratelimit = numeric_limit
 149     if opts.min_filesize is not None:
 150         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 151         if numeric_limit is None:
 152             parser.error('invalid min_filesize specified')
 153         opts.min_filesize = numeric_limit
 154     if opts.max_filesize is not None:
 155         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 156         if numeric_limit is None:
 157             parser.error('invalid max_filesize specified')
 158         opts.max_filesize = numeric_limit
 159     if opts.sleep_interval is not None:
 160         if opts.sleep_interval < 0:
 161             parser.error('sleep interval must be positive or 0')
 162     if opts.max_sleep_interval is not None:
 163         if opts.max_sleep_interval < 0:
 164             parser.error('max sleep interval must be positive or 0')
 165         if opts.sleep_interval is None:
 166             parser.error('min sleep interval must be specified, use --min-sleep-interval')
 167         if opts.max_sleep_interval < opts.sleep_interval:
 168             parser.error('max sleep interval must be greater than or equal to min sleep interval')
 169     else:
 170         opts.max_sleep_interval = opts.sleep_interval
 171     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
 172         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 173     if opts.overwrites:
 174         # --yes-overwrites implies --no-continue
 175         opts.continue_dl = False
 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.remuxvideo is not None:
 212         if opts.remuxvideo not in ['mp4', 'mkv']:
 213             parser.error('invalid video container format specified')
 214     if opts.recodevideo is not None:
 215         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
 216             parser.error('invalid video recode format specified')
 217     if opts.convertsubtitles is not None:
 218         if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
 219             parser.error('invalid subtitle format specified')
 220
 221     if opts.date is not None:
 222         date = DateRange.day(opts.date)
 223     else:
 224         date = DateRange(opts.dateafter, opts.datebefore)
 225
 226     # Do not download videos when there are audio-only formats
 227     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 228         opts.format = 'bestaudio/best'
 229
 230     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 231     # this was the old behaviour if only --all-sub was given.
 232     if opts.allsubtitles and not opts.writeautomaticsub:
 233         opts.writesubtitles = True
 234
 235     outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
 236                or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
 237                or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
 238                or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 239                or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
 240                or (opts.useid and '%(id)s.%(ext)s')
 241                or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
 242                or DEFAULT_OUTTMPL)
 243     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 244         parser.error('Cannot download a video and extract audio into the same'
 245                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 246                      ' template'.format(outtmpl))
 247     for f in opts.format_sort:
 248         if re.match(InfoExtractor.FormatSort.regex, f) is None:
 249             parser.error('invalid format sort string "%s" specified' % f)
 250
 251     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
 252     any_printing = opts.print_json
 253     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 254
 255     # PostProcessors
 256     postprocessors = []
 257     if opts.metafromtitle:
 258         postprocessors.append({
 259             'key': 'MetadataFromTitle',
 260             'titleformat': opts.metafromtitle
 261         })
 262     if opts.extractaudio:
 263         postprocessors.append({
 264             'key': 'FFmpegExtractAudio',
 265             'preferredcodec': opts.audioformat,
 266             'preferredquality': opts.audioquality,
 267             'nopostoverwrites': opts.nopostoverwrites,
 268         })
 269     if opts.remuxvideo:
 270         postprocessors.append({
 271             'key': 'FFmpegVideoRemuxer',
 272             'preferedformat': opts.remuxvideo,
 273         })
 274     if opts.recodevideo:
 275         postprocessors.append({
 276             'key': 'FFmpegVideoConvertor',
 277             'preferedformat': opts.recodevideo,
 278         })
 279     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 280     # FFmpegExtractAudioPP as containers before conversion may not support
 281     # metadata (3gp, webm, etc.)
 282     # And this post-processor should be placed before other metadata
 283     # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
 284     # extra metadata. By default ffmpeg preserves metadata applicable for both
 285     # source and target containers. From this point the container won't change,
 286     # so metadata can be added here.
 287     if opts.addmetadata:
 288         postprocessors.append({'key': 'FFmpegMetadata'})
 289     if opts.convertsubtitles:
 290         postprocessors.append({
 291             'key': 'FFmpegSubtitlesConvertor',
 292             'format': opts.convertsubtitles,
 293         })
 294     if opts.embedsubtitles:
 295         postprocessors.append({
 296             'key': 'FFmpegEmbedSubtitle',
 297         })
 298     if opts.embedthumbnail:
 299         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
 300         postprocessors.append({
 301             'key': 'EmbedThumbnail',
 302             'already_have_thumbnail': already_have_thumbnail
 303         })
 304         if not already_have_thumbnail:
 305             opts.writethumbnail = True
 306     # XAttrMetadataPP should be run after post-processors that may change file
 307     # contents
 308     if opts.xattrs:
 309         postprocessors.append({'key': 'XAttrMetadata'})
 310     # This should be below all ffmpeg PP because it may cut parts out from the video
 311     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
 312     if opts.sponskrub is not False:
 313         postprocessors.append({
 314             'key': 'SponSkrub',
 315             'path': opts.sponskrub_path,
 316             'args': opts.sponskrub_args,
 317             'cut': opts.sponskrub_cut,
 318             'force': opts.sponskrub_force,
 319             'ignoreerror': opts.sponskrub is None,
 320         })
 321     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 322     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 323     if opts.exec_cmd:
 324         postprocessors.append({
 325             'key': 'ExecAfterDownload',
 326             'exec_cmd': opts.exec_cmd,
 327         })
 328
 329     if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
 330         opts.postprocessor_args.setdefault('sponskrub', [])
 331         opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
 332
 333     match_filter = (
 334         None if opts.match_filter is None
 335         else match_filter_func(opts.match_filter))
 336
 337     ydl_opts = {
 338         'convertsubtitles': opts.convertsubtitles,
 339         'usenetrc': opts.usenetrc,
 340         'username': opts.username,
 341         'password': opts.password,
 342         'twofactor': opts.twofactor,
 343         'videopassword': opts.videopassword,
 344         'ap_mso': opts.ap_mso,
 345         'ap_username': opts.ap_username,
 346         'ap_password': opts.ap_password,
 347         'quiet': (opts.quiet or any_getting or any_printing),
 348         'no_warnings': opts.no_warnings,
 349         'forceurl': opts.geturl,
 350         'forcetitle': opts.gettitle,
 351         'forceid': opts.getid,
 352         'forcethumbnail': opts.getthumbnail,
 353         'forcedescription': opts.getdescription,
 354         'forceduration': opts.getduration,
 355         'forcefilename': opts.getfilename,
 356         'forceformat': opts.getformat,
 357         'forcejson': opts.dumpjson or opts.print_json,
 358         'dump_single_json': opts.dump_single_json,
 359         'force_write_download_archive': opts.force_write_download_archive,
 360         'simulate': opts.simulate or any_getting,
 361         'skip_download': opts.skip_download,
 362         'format': opts.format,
 363         'format_sort': opts.format_sort,
 364         'format_sort_force': opts.format_sort_force,
 365         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 366         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 367         'listformats': opts.listformats,
 368         'listformats_table': opts.listformats_table,
 369         'outtmpl': outtmpl,
 370         'autonumber_size': opts.autonumber_size,
 371         'autonumber_start': opts.autonumber_start,
 372         'restrictfilenames': opts.restrictfilenames,
 373         'ignoreerrors': opts.ignoreerrors,
 374         'force_generic_extractor': opts.force_generic_extractor,
 375         'ratelimit': opts.ratelimit,
 376         'overwrites': opts.overwrites,
 377         'retries': opts.retries,
 378         'fragment_retries': opts.fragment_retries,
 379         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 380         'keep_fragments': opts.keep_fragments,
 381         'buffersize': opts.buffersize,
 382         'noresizebuffer': opts.noresizebuffer,
 383         'http_chunk_size': opts.http_chunk_size,
 384         'continuedl': opts.continue_dl,
 385         'noprogress': opts.noprogress,
 386         'progress_with_newline': opts.progress_with_newline,
 387         'playliststart': opts.playliststart,
 388         'playlistend': opts.playlistend,
 389         'playlistreverse': opts.playlist_reverse,
 390         'playlistrandom': opts.playlist_random,
 391         'noplaylist': opts.noplaylist,
 392         'logtostderr': opts.outtmpl == '-',
 393         'consoletitle': opts.consoletitle,
 394         'nopart': opts.nopart,
 395         'updatetime': opts.updatetime,
 396         'writedescription': opts.writedescription,
 397         'writeannotations': opts.writeannotations,
 398         'writeinfojson': opts.writeinfojson,
 399         'writethumbnail': opts.writethumbnail,
 400         'write_all_thumbnails': opts.write_all_thumbnails,
 401         'writelink': opts.writelink,
 402         'writeurllink': opts.writeurllink,
 403         'writewebloclink': opts.writewebloclink,
 404         'writedesktoplink': opts.writedesktoplink,
 405         'writesubtitles': opts.writesubtitles,
 406         'writeautomaticsub': opts.writeautomaticsub,
 407         'allsubtitles': opts.allsubtitles,
 408         'listsubtitles': opts.listsubtitles,
 409         'subtitlesformat': opts.subtitlesformat,
 410         'subtitleslangs': opts.subtitleslangs,
 411         'matchtitle': decodeOption(opts.matchtitle),
 412         'rejecttitle': decodeOption(opts.rejecttitle),
 413         'max_downloads': opts.max_downloads,
 414         'prefer_free_formats': opts.prefer_free_formats,
 415         'trim_file_name': opts.trim_file_name,
 416         'verbose': opts.verbose,
 417         'dump_intermediate_pages': opts.dump_intermediate_pages,
 418         'write_pages': opts.write_pages,
 419         'test': opts.test,
 420         'keepvideo': opts.keepvideo,
 421         'min_filesize': opts.min_filesize,
 422         'max_filesize': opts.max_filesize,
 423         'min_views': opts.min_views,
 424         'max_views': opts.max_views,
 425         'daterange': date,
 426         'cachedir': opts.cachedir,
 427         'youtube_print_sig_code': opts.youtube_print_sig_code,
 428         'age_limit': opts.age_limit,
 429         'download_archive': download_archive_fn,
 430         'break_on_existing': opts.break_on_existing,
 431         'break_on_reject': opts.break_on_reject,
 432         'cookiefile': opts.cookiefile,
 433         'nocheckcertificate': opts.no_check_certificate,
 434         'prefer_insecure': opts.prefer_insecure,
 435         'proxy': opts.proxy,
 436         'socket_timeout': opts.socket_timeout,
 437         'bidi_workaround': opts.bidi_workaround,
 438         'debug_printtraffic': opts.debug_printtraffic,
 439         'prefer_ffmpeg': opts.prefer_ffmpeg,
 440         'include_ads': opts.include_ads,
 441         'default_search': opts.default_search,
 442         'dynamic_mpd': opts.dynamic_mpd,
 443         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 444         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 445         'encoding': opts.encoding,
 446         'extract_flat': opts.extract_flat,
 447         'mark_watched': opts.mark_watched,
 448         'merge_output_format': opts.merge_output_format,
 449         'postprocessors': postprocessors,
 450         'fixup': opts.fixup,
 451         'source_address': opts.source_address,
 452         'call_home': opts.call_home,
 453         'sleep_interval': opts.sleep_interval,
 454         'max_sleep_interval': opts.max_sleep_interval,
 455         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 456         'external_downloader': opts.external_downloader,
 457         'list_thumbnails': opts.list_thumbnails,
 458         'playlist_items': opts.playlist_items,
 459         'xattr_set_filesize': opts.xattr_set_filesize,
 460         'match_filter': match_filter,
 461         'no_color': opts.no_color,
 462         'ffmpeg_location': opts.ffmpeg_location,
 463         'hls_prefer_native': opts.hls_prefer_native,
 464         'hls_use_mpegts': opts.hls_use_mpegts,
 465         'external_downloader_args': opts.external_downloader_args,
 466         'postprocessor_args': opts.postprocessor_args,
 467         'cn_verification_proxy': opts.cn_verification_proxy,
 468         'geo_verification_proxy': opts.geo_verification_proxy,
 469         'config_location': opts.config_location,
 470         'geo_bypass': opts.geo_bypass,
 471         'geo_bypass_country': opts.geo_bypass_country,
 472         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 473         # just for deprecation check
 474         'autonumber': opts.autonumber if opts.autonumber is True else None,
 475         'usetitle': opts.usetitle if opts.usetitle is True else None,
 476     }
 477
 478     with YoutubeDL(ydl_opts) as ydl:
 479         # Update version
 480         if opts.update_self:
 481             update_self(ydl.to_screen, opts.verbose, ydl._opener)
 482
 483         # Remove cache dir
 484         if opts.rm_cachedir:
 485             ydl.cache.remove()
 486
 487         # Maybe do nothing
 488         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 489             if opts.update_self or opts.rm_cachedir:
 490                 sys.exit()
 491
 492             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 493             parser.error(
 494                 'You must provide at least one URL.\n'
 495                 'Type youtube-dlc --help to see a list of all options.')
 496
 497         try:
 498             if opts.load_info_filename is not None:
 499                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
 500             else:
 501                 retcode = ydl.download(all_urls)
 502         except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
 503             ydl.to_screen('Aborting remaining downloads')
 504             retcode = 101
 505
 506     sys.exit(retcode)
 507
 508
 509 def main(argv=None):
 510     try:
 511         _real_main(argv)
 512     except DownloadError:
 513         sys.exit(1)
 514     except SameFileError:
 515         sys.exit('ERROR: fixed output name but more than one file to download')
 516     except KeyboardInterrupt:
 517         sys.exit('\nERROR: Interrupted by user')
 518
 519
 520 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']