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 re
  12 import random
  13 import sys
  14
  15
  16 from .options import (
  17     parseOpts,
  18 )
  19 from .compat import (
  20     compat_getpass,
  21     compat_shlex_split,
  22     workaround_optparse_bug9161,
  23 )
  24 from .utils import (
  25     DateRange,
  26     decodeOption,
  27     DEFAULT_OUTTMPL,
  28     DownloadError,
  29     expand_path,
  30     match_filter_func,
  31     MaxDownloadsReached,
  32     preferredencoding,
  33     read_batch_urls,
  34     SameFileError,
  35     setproctitle,
  36     std_headers,
  37     write_string,
  38     render_table,
  39 )
  40 from .update import update_self
  41 from .downloader import (
  42     FileDownloader,
  43 )
  44 from .extractor import gen_extractors, list_extractors
  45 from .extractor.common import InfoExtractor
  46 from .extractor.adobepass import MSO_INFO
  47 from .YoutubeDL import YoutubeDL
  48
  49
  50 def _real_main(argv=None):
  51     # Compatibility fixes for Windows
  52     if sys.platform == 'win32':
  53         # https://github.com/ytdl-org/youtube-dl/issues/820
  54         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  55
  56     workaround_optparse_bug9161()
  57
  58     setproctitle('youtube-dlc')
  59
  60     parser, opts, args = parseOpts(argv)
  61
  62     # Set user agent
  63     if opts.user_agent is not None:
  64         std_headers['User-Agent'] = opts.user_agent
  65
  66     # Set referer
  67     if opts.referer is not None:
  68         std_headers['Referer'] = opts.referer
  69
  70     # Custom HTTP headers
  71     if opts.headers is not None:
  72         for h in opts.headers:
  73             if ':' not in h:
  74                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
  75             key, value = h.split(':', 1)
  76             if opts.verbose:
  77                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
  78             std_headers[key] = value
  79
  80     # Dump user agent
  81     if opts.dump_user_agent:
  82         write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
  83         sys.exit(0)
  84
  85     # Batch file verification
  86     batch_urls = []
  87     if opts.batchfile is not None:
  88         try:
  89             if opts.batchfile == '-':
  90                 batchfd = sys.stdin
  91             else:
  92                 batchfd = io.open(
  93                     expand_path(opts.batchfile),
  94                     'r', encoding='utf-8', errors='ignore')
  95             batch_urls = read_batch_urls(batchfd)
  96             if opts.verbose:
  97                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  98         except IOError:
  99             sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
 100     all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
 101     _enc = preferredencoding()
 102     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 103
 104     if opts.list_extractors:
 105         for ie in list_extractors(opts.age_limit):
 106             write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
 107             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 108             for mu in matchedUrls:
 109                 write_string('  ' + mu + '\n', out=sys.stdout)
 110         sys.exit(0)
 111     if opts.list_extractor_descriptions:
 112         for ie in list_extractors(opts.age_limit):
 113             if not ie._WORKING:
 114                 continue
 115             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
 116             if desc is False:
 117                 continue
 118             if hasattr(ie, 'SEARCH_KEY'):
 119                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
 120                 _COUNTS = ('', '5', '10', 'all')
 121                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
 122             write_string(desc + '\n', out=sys.stdout)
 123         sys.exit(0)
 124     if opts.ap_list_mso:
 125         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
 126         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
 127         sys.exit(0)
 128
 129     # Conflicting, missing and erroneous options
 130     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 131         parser.error('using .netrc conflicts with giving username/password')
 132     if opts.password is not None and opts.username is None:
 133         parser.error('account username missing\n')
 134     if opts.ap_password is not None and opts.ap_username is None:
 135         parser.error('TV Provider account username missing\n')
 136     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
 137         parser.error('using output template conflicts with using title, video ID or auto number')
 138     if opts.autonumber_size is not None:
 139         if opts.autonumber_size <= 0:
 140             parser.error('auto number size must be positive')
 141     if opts.autonumber_start is not None:
 142         if opts.autonumber_start < 0:
 143             parser.error('auto number start must be positive or 0')
 144     if opts.usetitle and opts.useid:
 145         parser.error('using title conflicts with using video ID')
 146     if opts.username is not None and opts.password is None:
 147         opts.password = compat_getpass('Type account password and press [Return]: ')
 148     if opts.ap_username is not None and opts.ap_password is None:
 149         opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
 150     if opts.ratelimit is not None:
 151         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 152         if numeric_limit is None:
 153             parser.error('invalid rate limit specified')
 154         opts.ratelimit = numeric_limit
 155     if opts.min_filesize is not None:
 156         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 157         if numeric_limit is None:
 158             parser.error('invalid min_filesize specified')
 159         opts.min_filesize = numeric_limit
 160     if opts.max_filesize is not None:
 161         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 162         if numeric_limit is None:
 163             parser.error('invalid max_filesize specified')
 164         opts.max_filesize = numeric_limit
 165     if opts.sleep_interval is not None:
 166         if opts.sleep_interval < 0:
 167             parser.error('sleep interval must be positive or 0')
 168     if opts.max_sleep_interval is not None:
 169         if opts.max_sleep_interval < 0:
 170             parser.error('max sleep interval must be positive or 0')
 171         if opts.sleep_interval is None:
 172             parser.error('min sleep interval must be specified, use --min-sleep-interval')
 173         if opts.max_sleep_interval < opts.sleep_interval:
 174             parser.error('max sleep interval must be greater than or equal to min sleep interval')
 175     else:
 176         opts.max_sleep_interval = opts.sleep_interval
 177     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
 178         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 179
 180     def parse_retries(retries):
 181         if retries in ('inf', 'infinite'):
 182             parsed_retries = float('inf')
 183         else:
 184             try:
 185                 parsed_retries = int(retries)
 186             except (TypeError, ValueError):
 187                 parser.error('invalid retry count specified')
 188         return parsed_retries
 189     if opts.retries is not None:
 190         opts.retries = parse_retries(opts.retries)
 191     if opts.fragment_retries is not None:
 192         opts.fragment_retries = parse_retries(opts.fragment_retries)
 193     if opts.buffersize is not None:
 194         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 195         if numeric_buffersize is None:
 196             parser.error('invalid buffer size specified')
 197         opts.buffersize = numeric_buffersize
 198     if opts.http_chunk_size is not None:
 199         numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
 200         if not numeric_chunksize:
 201             parser.error('invalid http chunk size specified')
 202         opts.http_chunk_size = numeric_chunksize
 203     if opts.playliststart <= 0:
 204         raise ValueError('Playlist start must be positive')
 205     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 206         raise ValueError('Playlist end must be greater than playlist start')
 207     if opts.extractaudio:
 208         if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
 209             parser.error('invalid audio format specified')
 210     if opts.audioquality:
 211         opts.audioquality = opts.audioquality.strip('k').strip('K')
 212         if not opts.audioquality.isdigit():
 213             parser.error('invalid audio quality specified')
 214     if opts.remuxvideo is not None:
 215         if opts.remuxvideo not in ['mp4', 'mkv']:
 216             parser.error('invalid video container format specified')
 217     if opts.recodevideo is not None:
 218         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
 219             parser.error('invalid video recode format specified')
 220     if opts.convertsubtitles is not None:
 221         if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
 222             parser.error('invalid subtitle format specified')
 223
 224     if opts.date is not None:
 225         date = DateRange.day(opts.date)
 226     else:
 227         date = DateRange(opts.dateafter, opts.datebefore)
 228
 229     # Do not download videos when there are audio-only formats
 230     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 231         opts.format = 'bestaudio/best'
 232
 233     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 234     # this was the old behaviour if only --all-sub was given.
 235     if opts.allsubtitles and not opts.writeautomaticsub:
 236         opts.writesubtitles = True
 237
 238     outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
 239                or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
 240                or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
 241                or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 242                or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
 243                or (opts.useid and '%(id)s.%(ext)s')
 244                or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
 245                or DEFAULT_OUTTMPL)
 246     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 247         parser.error('Cannot download a video and extract audio into the same'
 248                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 249                      ' template'.format(outtmpl))
 250     for f in opts.format_sort:
 251         if re.match(InfoExtractor.FormatSort.regex, f) is None:
 252             parser.error('invalid format sort string "%s" specified' % f)
 253
 254     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
 255     any_printing = opts.print_json
 256     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 257
 258     # PostProcessors
 259     postprocessors = []
 260     if opts.metafromtitle:
 261         postprocessors.append({
 262             'key': 'MetadataFromTitle',
 263             'titleformat': opts.metafromtitle
 264         })
 265     if opts.extractaudio:
 266         postprocessors.append({
 267             'key': 'FFmpegExtractAudio',
 268             'preferredcodec': opts.audioformat,
 269             'preferredquality': opts.audioquality,
 270             'nopostoverwrites': opts.nopostoverwrites,
 271         })
 272     if opts.remuxvideo:
 273         postprocessors.append({
 274             'key': 'FFmpegVideoRemuxer',
 275             'preferedformat': opts.remuxvideo,
 276         })
 277     if opts.recodevideo:
 278         postprocessors.append({
 279             'key': 'FFmpegVideoConvertor',
 280             'preferedformat': opts.recodevideo,
 281         })
 282     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
 283     # FFmpegExtractAudioPP as containers before conversion may not support
 284     # metadata (3gp, webm, etc.)
 285     # And this post-processor should be placed before other metadata
 286     # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
 287     # extra metadata. By default ffmpeg preserves metadata applicable for both
 288     # source and target containers. From this point the container won't change,
 289     # so metadata can be added here.
 290     if opts.addmetadata:
 291         postprocessors.append({'key': 'FFmpegMetadata'})
 292     if opts.convertsubtitles:
 293         postprocessors.append({
 294             'key': 'FFmpegSubtitlesConvertor',
 295             'format': opts.convertsubtitles,
 296         })
 297     if opts.embedsubtitles:
 298         postprocessors.append({
 299             'key': 'FFmpegEmbedSubtitle',
 300         })
 301     if opts.embedthumbnail:
 302         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
 303         postprocessors.append({
 304             'key': 'EmbedThumbnail',
 305             'already_have_thumbnail': already_have_thumbnail
 306         })
 307         if not already_have_thumbnail:
 308             opts.writethumbnail = True
 309     # XAttrMetadataPP should be run after post-processors that may change file
 310     # contents
 311     if opts.xattrs:
 312         postprocessors.append({'key': 'XAttrMetadata'})
 313     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 314     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 315     if opts.exec_cmd:
 316         postprocessors.append({
 317             'key': 'ExecAfterDownload',
 318             'exec_cmd': opts.exec_cmd,
 319         })
 320     external_downloader_args = None
 321     if opts.external_downloader_args:
 322         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
 323     postprocessor_args = None
 324     if opts.postprocessor_args:
 325         postprocessor_args = compat_shlex_split(opts.postprocessor_args)
 326     match_filter = (
 327         None if opts.match_filter is None
 328         else match_filter_func(opts.match_filter))
 329
 330     ydl_opts = {
 331         'convertsubtitles': opts.convertsubtitles,
 332         'usenetrc': opts.usenetrc,
 333         'username': opts.username,
 334         'password': opts.password,
 335         'twofactor': opts.twofactor,
 336         'videopassword': opts.videopassword,
 337         'ap_mso': opts.ap_mso,
 338         'ap_username': opts.ap_username,
 339         'ap_password': opts.ap_password,
 340         'quiet': (opts.quiet or any_getting or any_printing),
 341         'no_warnings': opts.no_warnings,
 342         'forceurl': opts.geturl,
 343         'forcetitle': opts.gettitle,
 344         'forceid': opts.getid,
 345         'forcethumbnail': opts.getthumbnail,
 346         'forcedescription': opts.getdescription,
 347         'forceduration': opts.getduration,
 348         'forcefilename': opts.getfilename,
 349         'forceformat': opts.getformat,
 350         'forcejson': opts.dumpjson or opts.print_json,
 351         'dump_single_json': opts.dump_single_json,
 352         'simulate': opts.simulate or any_getting,
 353         'skip_download': opts.skip_download,
 354         'format': opts.format,
 355         'format_sort': opts.format_sort,
 356         'format_sort_force': opts.format_sort_force,
 357         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
 358         'allow_multiple_audio_streams': opts.allow_multiple_audio_streams,
 359         'listformats': opts.listformats,
 360         'outtmpl': outtmpl,
 361         'autonumber_size': opts.autonumber_size,
 362         'autonumber_start': opts.autonumber_start,
 363         'restrictfilenames': opts.restrictfilenames,
 364         'ignoreerrors': opts.ignoreerrors,
 365         'force_generic_extractor': opts.force_generic_extractor,
 366         'ratelimit': opts.ratelimit,
 367         'nooverwrites': opts.nooverwrites,
 368         'retries': opts.retries,
 369         'fragment_retries': opts.fragment_retries,
 370         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
 371         'keep_fragments': opts.keep_fragments,
 372         'buffersize': opts.buffersize,
 373         'noresizebuffer': opts.noresizebuffer,
 374         'http_chunk_size': opts.http_chunk_size,
 375         'continuedl': opts.continue_dl,
 376         'noprogress': opts.noprogress,
 377         'progress_with_newline': opts.progress_with_newline,
 378         'playliststart': opts.playliststart,
 379         'playlistend': opts.playlistend,
 380         'playlistreverse': opts.playlist_reverse,
 381         'playlistrandom': opts.playlist_random,
 382         'noplaylist': opts.noplaylist,
 383         'logtostderr': opts.outtmpl == '-',
 384         'consoletitle': opts.consoletitle,
 385         'nopart': opts.nopart,
 386         'updatetime': opts.updatetime,
 387         'writedescription': opts.writedescription,
 388         'writeannotations': opts.writeannotations,
 389         'writeinfojson': opts.writeinfojson,
 390         'writethumbnail': opts.writethumbnail,
 391         'write_all_thumbnails': opts.write_all_thumbnails,
 392         'writesubtitles': opts.writesubtitles,
 393         'writeautomaticsub': opts.writeautomaticsub,
 394         'allsubtitles': opts.allsubtitles,
 395         'listsubtitles': opts.listsubtitles,
 396         'subtitlesformat': opts.subtitlesformat,
 397         'subtitleslangs': opts.subtitleslangs,
 398         'matchtitle': decodeOption(opts.matchtitle),
 399         'rejecttitle': decodeOption(opts.rejecttitle),
 400         'max_downloads': opts.max_downloads,
 401         'prefer_free_formats': opts.prefer_free_formats,
 402         'trim_file_name': opts.trim_file_name,
 403         'verbose': opts.verbose,
 404         'dump_intermediate_pages': opts.dump_intermediate_pages,
 405         'write_pages': opts.write_pages,
 406         'test': opts.test,
 407         'keepvideo': opts.keepvideo,
 408         'min_filesize': opts.min_filesize,
 409         'max_filesize': opts.max_filesize,
 410         'min_views': opts.min_views,
 411         'max_views': opts.max_views,
 412         'daterange': date,
 413         'cachedir': opts.cachedir,
 414         'youtube_print_sig_code': opts.youtube_print_sig_code,
 415         'age_limit': opts.age_limit,
 416         'download_archive': download_archive_fn,
 417         'break_on_existing': opts.break_on_existing,
 418         'cookiefile': opts.cookiefile,
 419         'nocheckcertificate': opts.no_check_certificate,
 420         'prefer_insecure': opts.prefer_insecure,
 421         'proxy': opts.proxy,
 422         'socket_timeout': opts.socket_timeout,
 423         'bidi_workaround': opts.bidi_workaround,
 424         'debug_printtraffic': opts.debug_printtraffic,
 425         'prefer_ffmpeg': opts.prefer_ffmpeg,
 426         'include_ads': opts.include_ads,
 427         'default_search': opts.default_search,
 428         'dynamic_mpd': opts.dynamic_mpd,
 429         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 430         'youtube_include_hls_manifest': opts.youtube_include_hls_manifest,
 431         'encoding': opts.encoding,
 432         'extract_flat': opts.extract_flat,
 433         'mark_watched': opts.mark_watched,
 434         'merge_output_format': opts.merge_output_format,
 435         'postprocessors': postprocessors,
 436         'fixup': opts.fixup,
 437         'source_address': opts.source_address,
 438         'call_home': opts.call_home,
 439         'sleep_interval': opts.sleep_interval,
 440         'max_sleep_interval': opts.max_sleep_interval,
 441         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
 442         'external_downloader': opts.external_downloader,
 443         'list_thumbnails': opts.list_thumbnails,
 444         'playlist_items': opts.playlist_items,
 445         'xattr_set_filesize': opts.xattr_set_filesize,
 446         'match_filter': match_filter,
 447         'no_color': opts.no_color,
 448         'ffmpeg_location': opts.ffmpeg_location,
 449         'hls_prefer_native': opts.hls_prefer_native,
 450         'hls_use_mpegts': opts.hls_use_mpegts,
 451         'external_downloader_args': external_downloader_args,
 452         'postprocessor_args': postprocessor_args,
 453         'cn_verification_proxy': opts.cn_verification_proxy,
 454         'geo_verification_proxy': opts.geo_verification_proxy,
 455         'config_location': opts.config_location,
 456         'geo_bypass': opts.geo_bypass,
 457         'geo_bypass_country': opts.geo_bypass_country,
 458         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
 459         # just for deprecation check
 460         'autonumber': opts.autonumber if opts.autonumber is True else None,
 461         'usetitle': opts.usetitle if opts.usetitle is True else None,
 462     }
 463
 464     with YoutubeDL(ydl_opts) as ydl:
 465         # Update version
 466         if opts.update_self:
 467             update_self(ydl.to_screen, opts.verbose, ydl._opener)
 468
 469         # Remove cache dir
 470         if opts.rm_cachedir:
 471             ydl.cache.remove()
 472
 473         # Maybe do nothing
 474         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 475             if opts.update_self or opts.rm_cachedir:
 476                 sys.exit()
 477
 478             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 479             parser.error(
 480                 'You must provide at least one URL.\n'
 481                 'Type youtube-dlc --help to see a list of all options.')
 482
 483         try:
 484             if opts.load_info_filename is not None:
 485                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
 486             else:
 487                 retcode = ydl.download(all_urls)
 488         except MaxDownloadsReached:
 489             ydl.to_screen('--max-download limit reached, aborting.')
 490             retcode = 101
 491
 492     sys.exit(retcode)
 493
 494
 495 def main(argv=None):
 496     try:
 497         _real_main(argv)
 498     except DownloadError:
 499         sys.exit(1)
 500     except SameFileError:
 501         sys.exit('ERROR: fixed output name but more than one file to download')
 502     except KeyboardInterrupt:
 503         sys.exit('\nERROR: Interrupted by user')
 504
 505
 506 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']