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_print,
  22     workaround_optparse_bug9161,
  23 )
  24 from .utils import (
  25     DateRange,
  26     DEFAULT_OUTTMPL,
  27     decodeOption,
  28     DownloadError,
  29     MaxDownloadsReached,
  30     preferredencoding,
  31     read_batch_urls,
  32     SameFileError,
  33     setproctitle,
  34     std_headers,
  35     write_string,
  36 )
  37 from .update import update_self
  38 from .downloader import (
  39     FileDownloader,
  40 )
  41 from .extractor import gen_extractors, list_extractors
  42 from .YoutubeDL import YoutubeDL
  43
  44
  45 def _real_main(argv=None):
  46     # Compatibility fixes for Windows
  47     if sys.platform == 'win32':
  48         # https://github.com/rg3/youtube-dl/issues/820
  49         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  50
  51     workaround_optparse_bug9161()
  52
  53     setproctitle('youtube-dl')
  54
  55     parser, opts, args = parseOpts(argv)
  56
  57     # Set user agent
  58     if opts.user_agent is not None:
  59         std_headers['User-Agent'] = opts.user_agent
  60
  61     # Set referer
  62     if opts.referer is not None:
  63         std_headers['Referer'] = opts.referer
  64
  65     # Custom HTTP headers
  66     if opts.headers is not None:
  67         for h in opts.headers:
  68             if h.find(':', 1) < 0:
  69                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
  70             key, value = h.split(':', 2)
  71             if opts.verbose:
  72                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
  73             std_headers[key] = value
  74
  75     # Dump user agent
  76     if opts.dump_user_agent:
  77         compat_print(std_headers['User-Agent'])
  78         sys.exit(0)
  79
  80     # Batch file verification
  81     batch_urls = []
  82     if opts.batchfile is not None:
  83         try:
  84             if opts.batchfile == '-':
  85                 batchfd = sys.stdin
  86             else:
  87                 batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
  88             batch_urls = read_batch_urls(batchfd)
  89             if opts.verbose:
  90                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
  91         except IOError:
  92             sys.exit('ERROR: batch file could not be read')
  93     all_urls = batch_urls + args
  94     all_urls = [url.strip() for url in all_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             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
 101             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 102             for mu in matchedUrls:
 103                 compat_print('  ' + mu)
 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             compat_print(desc)
 117         sys.exit(0)
 118
 119     # Conflicting, missing and erroneous options
 120     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 121         parser.error('using .netrc conflicts with giving username/password')
 122     if opts.password is not None and opts.username is None:
 123         parser.error('account username missing\n')
 124     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
 125         parser.error('using output template conflicts with using title, video ID or auto number')
 126     if opts.usetitle and opts.useid:
 127         parser.error('using title conflicts with using video ID')
 128     if opts.username is not None and opts.password is None:
 129         opts.password = compat_getpass('Type account password and press [Return]: ')
 130     if opts.ratelimit is not None:
 131         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 132         if numeric_limit is None:
 133             parser.error('invalid rate limit specified')
 134         opts.ratelimit = numeric_limit
 135     if opts.sleepinterval is not None:
 136         try:
 137             opts.sleepinterval = abs(int(opts.sleepinterval))
 138         except ValueError:
 139             parser.error(u'invalid sleep interval specified')
 140     if opts.min_filesize is not None:
 141         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 142         if numeric_limit is None:
 143             parser.error('invalid min_filesize specified')
 144         opts.min_filesize = numeric_limit
 145     if opts.max_filesize is not None:
 146         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 147         if numeric_limit is None:
 148             parser.error('invalid max_filesize specified')
 149         opts.max_filesize = numeric_limit
 150     if opts.retries is not None:
 151         try:
 152             opts.retries = int(opts.retries)
 153         except (TypeError, ValueError):
 154             parser.error('invalid retry count specified')
 155     if opts.buffersize is not None:
 156         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 157         if numeric_buffersize is None:
 158             parser.error('invalid buffer size specified')
 159         opts.buffersize = numeric_buffersize
 160     if opts.playliststart <= 0:
 161         raise ValueError('Playlist start must be positive')
 162     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 163         raise ValueError('Playlist end must be greater than playlist start')
 164     if opts.extractaudio:
 165         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
 166             parser.error('invalid audio format specified')
 167     if opts.audioquality:
 168         opts.audioquality = opts.audioquality.strip('k').strip('K')
 169         if not opts.audioquality.isdigit():
 170             parser.error('invalid audio quality specified')
 171     if opts.recodevideo is not None:
 172         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
 173             parser.error('invalid video recode format specified')
 174
 175     if opts.date is not None:
 176         date = DateRange.day(opts.date)
 177     else:
 178         date = DateRange(opts.dateafter, opts.datebefore)
 179
 180     # Do not download videos when there are audio-only formats
 181     if opts.extractaudio and not opts.keepvideo and opts.format is None:
 182         opts.format = 'bestaudio/best'
 183
 184     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
 185     # this was the old behaviour if only --all-sub was given.
 186     if opts.allsubtitles and not opts.writeautomaticsub:
 187         opts.writesubtitles = True
 188
 189     if sys.version_info < (3,):
 190         # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
 191         if opts.outtmpl is not None:
 192             opts.outtmpl = opts.outtmpl.decode(preferredencoding())
 193     outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
 194                or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
 195                or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
 196                or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 197                or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
 198                or (opts.useid and '%(id)s.%(ext)s')
 199                or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
 200                or DEFAULT_OUTTMPL)
 201     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 202         parser.error('Cannot download a video and extract audio into the same'
 203                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 204                      ' template'.format(outtmpl))
 205
 206     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
 207     any_printing = opts.print_json
 208     download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 209
 210     # PostProcessors
 211     postprocessors = []
 212     # Add the metadata pp first, the other pps will copy it
 213     if opts.addmetadata:
 214         postprocessors.append({'key': 'FFmpegMetadata'})
 215     if opts.extractaudio:
 216         postprocessors.append({
 217             'key': 'FFmpegExtractAudio',
 218             'preferredcodec': opts.audioformat,
 219             'preferredquality': opts.audioquality,
 220             'nopostoverwrites': opts.nopostoverwrites,
 221         })
 222     if opts.recodevideo:
 223         postprocessors.append({
 224             'key': 'FFmpegVideoConvertor',
 225             'preferedformat': opts.recodevideo,
 226         })
 227     if opts.embedsubtitles:
 228         postprocessors.append({
 229             'key': 'FFmpegEmbedSubtitle',
 230             'subtitlesformat': opts.subtitlesformat,
 231         })
 232     if opts.xattrs:
 233         postprocessors.append({'key': 'XAttrMetadata'})
 234     if opts.embedthumbnail:
 235         if not opts.addmetadata:
 236             postprocessors.append({'key': 'FFmpegAudioFix'})
 237         postprocessors.append({'key': 'AtomicParsley'})
 238     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 239     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 240     if opts.exec_cmd:
 241         postprocessors.append({
 242             'key': 'ExecAfterDownload',
 243             'verboseOutput': opts.verbose,
 244             'exec_cmd': opts.exec_cmd,
 245         })
 246
 247     ydl_opts = {
 248         'usenetrc': opts.usenetrc,
 249         'username': opts.username,
 250         'password': opts.password,
 251         'twofactor': opts.twofactor,
 252         'videopassword': opts.videopassword,
 253         'quiet': (opts.quiet or any_getting or any_printing),
 254         'no_warnings': opts.no_warnings,
 255         'forceurl': opts.geturl,
 256         'forcetitle': opts.gettitle,
 257         'forceid': opts.getid,
 258         'forcethumbnail': opts.getthumbnail,
 259         'forcedescription': opts.getdescription,
 260         'forceduration': opts.getduration,
 261         'forcefilename': opts.getfilename,
 262         'forceformat': opts.getformat,
 263         'forcejson': opts.dumpjson or opts.print_json,
 264         'dump_single_json': opts.dump_single_json,
 265         'simulate': opts.simulate or any_getting,
 266         'skip_download': opts.skip_download,
 267         'format': opts.format,
 268         'format_limit': opts.format_limit,
 269         'listformats': opts.listformats,
 270         'outtmpl': outtmpl,
 271         'autonumber_size': opts.autonumber_size,
 272         'restrictfilenames': opts.restrictfilenames,
 273         'ignoreerrors': opts.ignoreerrors,
 274         'ratelimit': opts.ratelimit,
 275         'sleepinterval': opts.sleepinterval,
 276         'nooverwrites': opts.nooverwrites,
 277         'retries': opts.retries,
 278         'buffersize': opts.buffersize,
 279         'noresizebuffer': opts.noresizebuffer,
 280         'continuedl': opts.continue_dl,
 281         'noprogress': opts.noprogress,
 282         'progress_with_newline': opts.progress_with_newline,
 283         'playliststart': opts.playliststart,
 284         'playlistend': opts.playlistend,
 285         'playlistreverse': opts.playlist_reverse,
 286         'noplaylist': opts.noplaylist,
 287         'logtostderr': opts.outtmpl == '-',
 288         'consoletitle': opts.consoletitle,
 289         'nopart': opts.nopart,
 290         'updatetime': opts.updatetime,
 291         'writedescription': opts.writedescription,
 292         'writeannotations': opts.writeannotations,
 293         'writeinfojson': opts.writeinfojson,
 294         'writethumbnail': opts.writethumbnail,
 295         'writesubtitles': opts.writesubtitles,
 296         'writeautomaticsub': opts.writeautomaticsub,
 297         'allsubtitles': opts.allsubtitles,
 298         'listsubtitles': opts.listsubtitles,
 299         'subtitlesformat': opts.subtitlesformat,
 300         'subtitleslangs': opts.subtitleslangs,
 301         'matchtitle': decodeOption(opts.matchtitle),
 302         'rejecttitle': decodeOption(opts.rejecttitle),
 303         'max_downloads': opts.max_downloads,
 304         'prefer_free_formats': opts.prefer_free_formats,
 305         'verbose': opts.verbose,
 306         'dump_intermediate_pages': opts.dump_intermediate_pages,
 307         'write_pages': opts.write_pages,
 308         'test': opts.test,
 309         'keepvideo': opts.keepvideo,
 310         'min_filesize': opts.min_filesize,
 311         'max_filesize': opts.max_filesize,
 312         'min_views': opts.min_views,
 313         'max_views': opts.max_views,
 314         'daterange': date,
 315         'cachedir': opts.cachedir,
 316         'youtube_print_sig_code': opts.youtube_print_sig_code,
 317         'age_limit': opts.age_limit,
 318         'download_archive': download_archive_fn,
 319         'cookiefile': opts.cookiefile,
 320         'nocheckcertificate': opts.no_check_certificate,
 321         'prefer_insecure': opts.prefer_insecure,
 322         'proxy': opts.proxy,
 323         'socket_timeout': opts.socket_timeout,
 324         'bidi_workaround': opts.bidi_workaround,
 325         'debug_printtraffic': opts.debug_printtraffic,
 326         'prefer_ffmpeg': opts.prefer_ffmpeg,
 327         'include_ads': opts.include_ads,
 328         'default_search': opts.default_search,
 329         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 330         'encoding': opts.encoding,
 331         'exec_cmd': opts.exec_cmd,
 332         'extract_flat': opts.extract_flat,
 333         'merge_output_format': opts.merge_output_format,
 334         'postprocessors': postprocessors,
 335         'fixup': opts.fixup,
 336         'source_address': opts.source_address,
 337         'call_home': opts.call_home,
 338         'sleep_interval': opts.sleep_interval,
 339     }
 340
 341     with YoutubeDL(ydl_opts) as ydl:
 342         # Update version
 343         if opts.update_self:
 344             update_self(ydl.to_screen, opts.verbose)
 345
 346         # Remove cache dir
 347         if opts.rm_cachedir:
 348             ydl.cache.remove()
 349
 350         # Maybe do nothing
 351         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 352             if opts.update_self or opts.rm_cachedir:
 353                 sys.exit()
 354
 355             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
 356             parser.error('you must provide at least one URL')
 357
 358         try:
 359             if opts.load_info_filename is not None:
 360                 retcode = ydl.download_with_info_file(opts.load_info_filename)
 361             else:
 362                 retcode = ydl.download(all_urls)
 363         except MaxDownloadsReached:
 364             ydl.to_screen('--max-download limit reached, aborting.')
 365             retcode = 101
 366
 367     sys.exit(retcode)
 368
 369
 370 def main(argv=None):
 371     try:
 372         _real_main(argv)
 373     except DownloadError:
 374         sys.exit(1)
 375     except SameFileError:
 376         sys.exit('ERROR: fixed output name but more than one file to download')
 377     except KeyboardInterrupt:
 378         sys.exit('\nERROR: Interrupted by user')
 379
 380 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']