Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/__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_expanduser,
  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     match_filter_func,
  30     MaxDownloadsReached,
  31     preferredencoding,
  32     read_batch_urls,
  33     SameFileError,
  34     setproctitle,
  35     std_headers,
  36     write_string,
  37 )
  38 from .update import update_self
  39 from .downloader import (
  40     FileDownloader,
  41 )
  42 from .extractor import gen_extractors, list_extractors
  43 from .YoutubeDL import YoutubeDL
  44
  45
  46 def _real_main(argv=None):
  47     # Compatibility fixes for Windows
  48     if sys.platform == 'win32':
  49         # https://github.com/rg3/youtube-dl/issues/820
  50         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  51
  52     workaround_optparse_bug9161()
  53
  54     setproctitle('youtube-dl')
  55
  56     parser, opts, args = parseOpts(argv)
  57
  58     # Set user agent
  59     if opts.user_agent is not None:
  60         std_headers['User-Agent'] = opts.user_agent
  61
  62     # Set referer
  63     if opts.referer is not None:
  64         std_headers['Referer'] = opts.referer
  65
  66     # Custom HTTP headers
  67     if opts.headers is not None:
  68         for h in opts.headers:
  69             if ':' not in h:
  70                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
  71             key, value = h.split(':', 1)
  72             if opts.verbose:
  73                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
  74             std_headers[key] = value
  75
  76     # Dump user agent
  77     if opts.dump_user_agent:
  78         write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
  79         sys.exit(0)
  80
  81     # Batch file verification
  82     batch_urls = []
  83     if opts.batchfile is not None:
  84         try:
  85             if opts.batchfile == '-':
  86                 batchfd = sys.stdin
  87             else:
  88                 batchfd = io.open(
  89                     compat_expanduser(opts.batchfile),
  90                     'r', encoding='utf-8', errors='ignore')
  91             batch_urls = read_batch_urls(batchfd)
  92             if opts.verbose:
  93                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  94         except IOError:
  95             sys.exit('ERROR: batch file could not be read')
  96     all_urls = batch_urls + args
  97     all_urls = [url.strip() for url in all_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
 122     # Conflicting, missing and erroneous options
 123     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 124         parser.error('using .netrc conflicts with giving username/password')
 125     if opts.password is not None and opts.username is None:
 126         parser.error('account username missing\n')
 127     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
 128         parser.error('using output template conflicts with using title, video ID or auto number')
 129     if opts.usetitle and opts.useid:
 130         parser.error('using title conflicts with using video ID')
 131     if opts.username is not None and opts.password is None:
 132         opts.password = compat_getpass('Type account password and press [Return]: ')
 133     if opts.ratelimit is not None:
 134         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 135         if numeric_limit is None:
 136             parser.error('invalid rate limit specified')
 137         opts.ratelimit = numeric_limit
 138     if opts.min_filesize is not None:
 139         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 140         if numeric_limit is None:
 141             parser.error('invalid min_filesize specified')
 142         opts.min_filesize = numeric_limit
 143     if opts.max_filesize is not None:
 144         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 145         if numeric_limit is None:
 146             parser.error('invalid max_filesize specified')
 147         opts.max_filesize = numeric_limit
 148     if opts.sleep_interval is not None:
 149         if opts.sleep_interval < 0:
 150             parser.error('sleep interval must be positive or 0')
 151     if opts.max_sleep_interval is not None:
 152         if opts.max_sleep_interval < 0:
 153             parser.error('max sleep interval must be positive or 0')
 154         if opts.max_sleep_interval < opts.sleep_interval:
 155             parser.error('max sleep interval must be greater than or equal to min sleep interval')
 156     else:
 157         opts.max_sleep_interval = opts.sleep_interval
 158
 159     def parse_retries(retries):
 160         if retries in ('inf', 'infinite'):
 161             parsed_retries = float('inf')
 162         else:
 163             try:
 164                 parsed_retries = int(retries)
 165             except (TypeError, ValueError):
 166                 parser.error('invalid retry count specified')
 167         return parsed_retries
 168     if opts.retries is not None:
 169         opts.retries = parse_retries(opts.retries)
 170     if opts.fragment_retries is not None:
 171         opts.fragment_retries = parse_retries(opts.fragment_retries)
 172     if opts.buffersize is not None:
 173         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 174         if numeric_buffersize is None:
 175             parser.error('invalid buffer size specified')
 176         opts.buffersize = numeric_buffersize
 177     if opts.playliststart <= 0:
 178         raise ValueError('Playlist start must be positive')
 179     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 180         raise ValueError('Playlist end must be greater than playlist start')
 181     if opts.extractaudio:
 182         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
 183             parser.error('invalid audio format specified')
 184     if opts.audioquality:
 185         opts.audioquality = opts.audioquality.strip('k').strip('K')
 186         if not opts.audioquality.isdigit():
 187             parser.error('invalid audio quality specified')
 188     if opts.recodevideo is not None:
 189         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
 190             parser.error('invalid video recode format specified')
 191     if opts.convertsubtitles is not None:
 192         if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
 193             parser.error('invalid subtitle format specified')
 194
 195     if opts.date is not None:
 196         date = DateRange.day(opts.date)
 197     else:
 198         date = DateRange(opts.dateafter, opts.datebefore)
 199
 200     # Do not download videos when there are audio-only formats
 201     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 202         opts.format = 'bestaudio/best'
 203
 204     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 205     # this was the old behaviour if only --all-sub was given.
 206     if opts.allsubtitles and not opts.writeautomaticsub:
 207         opts.writesubtitles = True
 208
 209     outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
 210                (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
 211                (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
 212                (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
 213                (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
 214                (opts.useid and '%(id)s.%(ext)s') or
 215                (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
 216                DEFAULT_OUTTMPL)
 217     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 218         parser.error('Cannot download a video and extract audio into the same'
 219                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 220                      ' template'.format(outtmpl))
 221
 222     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
 223     any_printing = opts.print_json
 224     download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 225
 226     # PostProcessors
 227     postprocessors = []
 228     # Add the metadata pp first, the other pps will copy it
 229     if opts.metafromtitle:
 230         postprocessors.append({
 231             'key': 'MetadataFromTitle',
 232             'titleformat': opts.metafromtitle
 233         })
 234     if opts.addmetadata:
 235         postprocessors.append({'key': 'FFmpegMetadata'})
 236     if opts.extractaudio:
 237         postprocessors.append({
 238             'key': 'FFmpegExtractAudio',
 239             'preferredcodec': opts.audioformat,
 240             'preferredquality': opts.audioquality,
 241             'nopostoverwrites': opts.nopostoverwrites,
 242         })
 243     if opts.recodevideo:
 244         postprocessors.append({
 245             'key': 'FFmpegVideoConvertor',
 246             'preferedformat': opts.recodevideo,
 247         })
 248     if opts.convertsubtitles:
 249         postprocessors.append({
 250             'key': 'FFmpegSubtitlesConvertor',
 251             'format': opts.convertsubtitles,
 252         })
 253     if opts.embedsubtitles:
 254         postprocessors.append({
 255             'key': 'FFmpegEmbedSubtitle',
 256         })
 257     if opts.xattrs:
 258         postprocessors.append({'key': 'XAttrMetadata'})
 259     if opts.embedthumbnail:
 260         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
 261         postprocessors.append({
 262             'key': 'EmbedThumbnail',
 263             'already_have_thumbnail': already_have_thumbnail
 264         })
 265         if not already_have_thumbnail:
 266             opts.writethumbnail = True
 267     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 268     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 269     if opts.exec_cmd:
 270         postprocessors.append({
 271             'key': 'ExecAfterDownload',
 272             'exec_cmd': opts.exec_cmd,
 273         })
 274     if opts.xattr_set_filesize:
 275         try:
 276             import xattr
 277             xattr  # Confuse flake8
 278         except ImportError:
 279             parser.error('setting filesize xattr requested but python-xattr is not available')
 280     external_downloader_args = None
 281     if opts.external_downloader_args:
 282         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
 283     postprocessor_args = None
 284     if opts.postprocessor_args:
 285         postprocessor_args = compat_shlex_split(opts.postprocessor_args)
 286     match_filter = (
 287         None if opts.match_filter is None
 288         else match_filter_func(opts.match_filter))
 289
 290     ydl_opts = {
 291         'usenetrc': opts.usenetrc,
 292         'username': opts.username,
 293         'password': opts.password,
 294         'twofactor': opts.twofactor,
 295         'videopassword': opts.videopassword,
 296         'quiet': (opts.quiet or any_getting or any_printing),
 297         'no_warnings': opts.no_warnings,
 298         'forceurl': opts.geturl,
 299         'forcetitle': opts.gettitle,
 300         'forceid': opts.getid,
 301         'forcethumbnail': opts.getthumbnail,
 302         'forcedescription': opts.getdescription,
 303         'forceduration': opts.getduration,
 304         'forcefilename': opts.getfilename,
 305         'forceformat': opts.getformat,
 306         'forcejson': opts.dumpjson or opts.print_json,
 307         'dump_single_json': opts.dump_single_json,
 308         'simulate': opts.simulate or any_getting,
 309         'skip_download': opts.skip_download,
 310         'format': opts.format,
 311         'listformats': opts.listformats,
 312         'outtmpl': outtmpl,
 313         'autonumber_size': opts.autonumber_size,
 314         'restrictfilenames': opts.restrictfilenames,
 315         'ignoreerrors': opts.ignoreerrors,
 316         'force_generic_extractor': opts.force_generic_extractor,
 317         'ratelimit': opts.ratelimit,
 318         'nooverwrites': opts.nooverwrites,
 319         'retries': opts.retries,
 320         'fragment_retries': opts.fragment_retries,
 321         'buffersize': opts.buffersize,
 322         'noresizebuffer': opts.noresizebuffer,
 323         'continuedl': opts.continue_dl,
 324         'noprogress': opts.noprogress,
 325         'progress_with_newline': opts.progress_with_newline,
 326         'playliststart': opts.playliststart,
 327         'playlistend': opts.playlistend,
 328         'playlistreverse': opts.playlist_reverse,
 329         'noplaylist': opts.noplaylist,
 330         'logtostderr': opts.outtmpl == '-',
 331         'consoletitle': opts.consoletitle,
 332         'nopart': opts.nopart,
 333         'updatetime': opts.updatetime,
 334         'writedescription': opts.writedescription,
 335         'writeannotations': opts.writeannotations,
 336         'writeinfojson': opts.writeinfojson,
 337         'writethumbnail': opts.writethumbnail,
 338         'write_all_thumbnails': opts.write_all_thumbnails,
 339         'writesubtitles': opts.writesubtitles,
 340         'writeautomaticsub': opts.writeautomaticsub,
 341         'allsubtitles': opts.allsubtitles,
 342         'listsubtitles': opts.listsubtitles,
 343         'subtitlesformat': opts.subtitlesformat,
 344         'subtitleslangs': opts.subtitleslangs,
 345         'matchtitle': decodeOption(opts.matchtitle),
 346         'rejecttitle': decodeOption(opts.rejecttitle),
 347         'max_downloads': opts.max_downloads,
 348         'prefer_free_formats': opts.prefer_free_formats,
 349         'verbose': opts.verbose,
 350         'dump_intermediate_pages': opts.dump_intermediate_pages,
 351         'write_pages': opts.write_pages,
 352         'test': opts.test,
 353         'keepvideo': opts.keepvideo,
 354         'min_filesize': opts.min_filesize,
 355         'max_filesize': opts.max_filesize,
 356         'min_views': opts.min_views,
 357         'max_views': opts.max_views,
 358         'daterange': date,
 359         'cachedir': opts.cachedir,
 360         'youtube_print_sig_code': opts.youtube_print_sig_code,
 361         'age_limit': opts.age_limit,
 362         'download_archive': download_archive_fn,
 363         'cookiefile': opts.cookiefile,
 364         'nocheckcertificate': opts.no_check_certificate,
 365         'prefer_insecure': opts.prefer_insecure,
 366         'proxy': opts.proxy,
 367         'socket_timeout': opts.socket_timeout,
 368         'bidi_workaround': opts.bidi_workaround,
 369         'debug_printtraffic': opts.debug_printtraffic,
 370         'prefer_ffmpeg': opts.prefer_ffmpeg,
 371         'include_ads': opts.include_ads,
 372         'default_search': opts.default_search,
 373         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 374         'encoding': opts.encoding,
 375         'extract_flat': opts.extract_flat,
 376         'mark_watched': opts.mark_watched,
 377         'merge_output_format': opts.merge_output_format,
 378         'postprocessors': postprocessors,
 379         'fixup': opts.fixup,
 380         'source_address': opts.source_address,
 381         'call_home': opts.call_home,
 382         'sleep_interval': opts.sleep_interval,
 383         'max_sleep_interval': opts.max_sleep_interval,
 384         'external_downloader': opts.external_downloader,
 385         'list_thumbnails': opts.list_thumbnails,
 386         'playlist_items': opts.playlist_items,
 387         'xattr_set_filesize': opts.xattr_set_filesize,
 388         'match_filter': match_filter,
 389         'no_color': opts.no_color,
 390         'ffmpeg_location': opts.ffmpeg_location,
 391         'hls_prefer_native': opts.hls_prefer_native,
 392         'hls_use_mpegts': opts.hls_use_mpegts,
 393         'external_downloader_args': external_downloader_args,
 394         'postprocessor_args': postprocessor_args,
 395         'cn_verification_proxy': opts.cn_verification_proxy,
 396         'geo_verification_proxy': opts.geo_verification_proxy,
 397
 398     }
 399
 400     with YoutubeDL(ydl_opts) as ydl:
 401         # Update version
 402         if opts.update_self:
 403             update_self(ydl.to_screen, opts.verbose, ydl._opener)
 404
 405         # Remove cache dir
 406         if opts.rm_cachedir:
 407             ydl.cache.remove()
 408
 409         # Maybe do nothing
 410         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 411             if opts.update_self or opts.rm_cachedir:
 412                 sys.exit()
 413
 414             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 415             parser.error(
 416                 'You must provide at least one URL.\n'
 417                 'Type youtube-dl --help to see a list of all options.')
 418
 419         try:
 420             if opts.load_info_filename is not None:
 421                 retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))
 422             else:
 423                 retcode = ydl.download(all_urls)
 424         except MaxDownloadsReached:
 425             ydl.to_screen('--max-download limit reached, aborting.')
 426             retcode = 101
 427
 428     sys.exit(retcode)
 429
 430
 431 def main(argv=None):
 432     try:
 433         _real_main(argv)
 434     except DownloadError:
 435         sys.exit(1)
 436     except SameFileError:
 437         sys.exit('ERROR: fixed output name but more than one file to download')
 438     except KeyboardInterrupt:
 439         sys.exit('\nERROR: Interrupted by user')
 440
 441 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']