Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/__init__.py

   1 #!/usr/bin/env python
   2 # -*- coding: utf-8 -*-
   3
   4 __license__ = 'Public Domain'
   5
   6 import codecs
   7 import io
   8 import os
   9 import random
  10 import sys
  11
  12
  13 from .options import (
  14     parseOpts,
  15 )
  16 from .utils import (
  17     compat_expanduser,
  18     compat_getpass,
  19     compat_print,
  20     DateRange,
  21     DEFAULT_OUTTMPL,
  22     decodeOption,
  23     DownloadError,
  24     MaxDownloadsReached,
  25     preferredencoding,
  26     read_batch_urls,
  27     SameFileError,
  28     setproctitle,
  29     std_headers,
  30     write_string,
  31 )
  32 from .update import update_self
  33 from .downloader import (
  34     FileDownloader,
  35 )
  36 from .extractor import gen_extractors
  37 from .YoutubeDL import YoutubeDL
  38 from .postprocessor import (
  39     AtomicParsleyPP,
  40     FFmpegAudioFixPP,
  41     FFmpegMetadataPP,
  42     FFmpegVideoConvertor,
  43     FFmpegExtractAudioPP,
  44     FFmpegEmbedSubtitlePP,
  45     XAttrMetadataPP,
  46     ExecAfterDownloadPP,
  47 )
  48
  49
  50 def _real_main(argv=None):
  51     # Compatibility fixes for Windows
  52     if sys.platform == 'win32':
  53         # https://github.com/rg3/youtube-dl/issues/820
  54         codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
  55
  56     setproctitle(u'youtube-dl')
  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 h.find(':', 1) < 0:
  72                 parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h)
  73             key, value = h.split(':', 2)
  74             if opts.verbose:
  75                 write_string(u'[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         compat_print(std_headers['User-Agent'])
  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(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
  91             batch_urls = read_batch_urls(batchfd)
  92             if opts.verbose:
  93                 write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
  94         except IOError:
  95             sys.exit(u'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     extractors = gen_extractors()
 102
 103     if opts.list_extractors:
 104         for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
 105             compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
 106             matchedUrls = [url for url in all_urls if ie.suitable(url)]
 107             for mu in matchedUrls:
 108                 compat_print(u'  ' + mu)
 109         sys.exit(0)
 110     if opts.list_extractor_descriptions:
 111         for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
 112             if not ie._WORKING:
 113                 continue
 114             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
 115             if desc is False:
 116                 continue
 117             if hasattr(ie, 'SEARCH_KEY'):
 118                 _SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny')
 119                 _COUNTS = (u'', u'5', u'10', u'all')
 120                 desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
 121             compat_print(desc)
 122         sys.exit(0)
 123
 124
 125     # Conflicting, missing and erroneous options
 126     if opts.usenetrc and (opts.username is not None or opts.password is not None):
 127         parser.error(u'using .netrc conflicts with giving username/password')
 128     if opts.password is not None and opts.username is None:
 129         parser.error(u'account username missing\n')
 130     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
 131         parser.error(u'using output template conflicts with using title, video ID or auto number')
 132     if opts.usetitle and opts.useid:
 133         parser.error(u'using title conflicts with using video ID')
 134     if opts.username is not None and opts.password is None:
 135         opts.password = compat_getpass(u'Type account password and press [Return]: ')
 136     if opts.ratelimit is not None:
 137         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 138         if numeric_limit is None:
 139             parser.error(u'invalid rate limit specified')
 140         opts.ratelimit = numeric_limit
 141     if opts.min_filesize is not None:
 142         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
 143         if numeric_limit is None:
 144             parser.error(u'invalid min_filesize specified')
 145         opts.min_filesize = numeric_limit
 146     if opts.max_filesize is not None:
 147         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
 148         if numeric_limit is None:
 149             parser.error(u'invalid max_filesize specified')
 150         opts.max_filesize = numeric_limit
 151     if opts.retries is not None:
 152         try:
 153             opts.retries = int(opts.retries)
 154         except (TypeError, ValueError):
 155             parser.error(u'invalid retry count specified')
 156     if opts.buffersize is not None:
 157         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
 158         if numeric_buffersize is None:
 159             parser.error(u'invalid buffer size specified')
 160         opts.buffersize = numeric_buffersize
 161     if opts.playliststart <= 0:
 162         raise ValueError(u'Playlist start must be positive')
 163     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
 164         raise ValueError(u'Playlist end must be greater than playlist start')
 165     if opts.extractaudio:
 166         if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
 167             parser.error(u'invalid audio format specified')
 168     if opts.audioquality:
 169         opts.audioquality = opts.audioquality.strip('k').strip('K')
 170         if not opts.audioquality.isdigit():
 171             parser.error(u'invalid audio quality specified')
 172     if opts.recodevideo is not None:
 173         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
 174             parser.error(u'invalid video recode format specified')
 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 (opts.writeautomaticsub == False):
 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 u'%(title)s-%(id)s-%(format)s.%(ext)s')
 195             or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
 196             or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 197             or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
 198             or (opts.useid and u'%(id)s.%(ext)s')
 199             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
 200             or DEFAULT_OUTTMPL)
 201     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
 202         parser.error(u'Cannot download a video and extract audio into the same'
 203                      u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
 204                      u' template'.format(outtmpl))
 205
 206     any_printing = 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     download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 208
 209     ydl_opts = {
 210         'usenetrc': opts.usenetrc,
 211         'username': opts.username,
 212         'password': opts.password,
 213         'twofactor': opts.twofactor,
 214         'videopassword': opts.videopassword,
 215         'quiet': (opts.quiet or any_printing),
 216         'no_warnings': opts.no_warnings,
 217         'forceurl': opts.geturl,
 218         'forcetitle': opts.gettitle,
 219         'forceid': opts.getid,
 220         'forcethumbnail': opts.getthumbnail,
 221         'forcedescription': opts.getdescription,
 222         'forceduration': opts.getduration,
 223         'forcefilename': opts.getfilename,
 224         'forceformat': opts.getformat,
 225         'forcejson': opts.dumpjson,
 226         'dump_single_json': opts.dump_single_json,
 227         'simulate': opts.simulate or any_printing,
 228         'skip_download': opts.skip_download,
 229         'format': opts.format,
 230         'format_limit': opts.format_limit,
 231         'listformats': opts.listformats,
 232         'outtmpl': outtmpl,
 233         'autonumber_size': opts.autonumber_size,
 234         'restrictfilenames': opts.restrictfilenames,
 235         'ignoreerrors': opts.ignoreerrors,
 236         'ratelimit': opts.ratelimit,
 237         'nooverwrites': opts.nooverwrites,
 238         'retries': opts.retries,
 239         'buffersize': opts.buffersize,
 240         'noresizebuffer': opts.noresizebuffer,
 241         'continuedl': opts.continue_dl,
 242         'noprogress': opts.noprogress,
 243         'progress_with_newline': opts.progress_with_newline,
 244         'playliststart': opts.playliststart,
 245         'playlistend': opts.playlistend,
 246         'noplaylist': opts.noplaylist,
 247         'logtostderr': opts.outtmpl == '-',
 248         'consoletitle': opts.consoletitle,
 249         'nopart': opts.nopart,
 250         'updatetime': opts.updatetime,
 251         'writedescription': opts.writedescription,
 252         'writeannotations': opts.writeannotations,
 253         'writeinfojson': opts.writeinfojson,
 254         'writethumbnail': opts.writethumbnail,
 255         'writesubtitles': opts.writesubtitles,
 256         'writeautomaticsub': opts.writeautomaticsub,
 257         'allsubtitles': opts.allsubtitles,
 258         'listsubtitles': opts.listsubtitles,
 259         'subtitlesformat': opts.subtitlesformat,
 260         'subtitleslangs': opts.subtitleslangs,
 261         'matchtitle': decodeOption(opts.matchtitle),
 262         'rejecttitle': decodeOption(opts.rejecttitle),
 263         'max_downloads': opts.max_downloads,
 264         'prefer_free_formats': opts.prefer_free_formats,
 265         'verbose': opts.verbose,
 266         'dump_intermediate_pages': opts.dump_intermediate_pages,
 267         'write_pages': opts.write_pages,
 268         'test': opts.test,
 269         'keepvideo': opts.keepvideo,
 270         'min_filesize': opts.min_filesize,
 271         'max_filesize': opts.max_filesize,
 272         'min_views': opts.min_views,
 273         'max_views': opts.max_views,
 274         'daterange': date,
 275         'cachedir': opts.cachedir,
 276         'youtube_print_sig_code': opts.youtube_print_sig_code,
 277         'age_limit': opts.age_limit,
 278         'download_archive': download_archive_fn,
 279         'cookiefile': opts.cookiefile,
 280         'nocheckcertificate': opts.no_check_certificate,
 281         'prefer_insecure': opts.prefer_insecure,
 282         'proxy': opts.proxy,
 283         'socket_timeout': opts.socket_timeout,
 284         'bidi_workaround': opts.bidi_workaround,
 285         'debug_printtraffic': opts.debug_printtraffic,
 286         'prefer_ffmpeg': opts.prefer_ffmpeg,
 287         'include_ads': opts.include_ads,
 288         'default_search': opts.default_search,
 289         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
 290         'encoding': opts.encoding,
 291         'exec_cmd': opts.exec_cmd,
 292         'extract_flat': opts.extract_flat,
 293     }
 294
 295     with YoutubeDL(ydl_opts) as ydl:
 296         # PostProcessors
 297         # Add the metadata pp first, the other pps will copy it
 298         if opts.addmetadata:
 299             ydl.add_post_processor(FFmpegMetadataPP())
 300         if opts.extractaudio:
 301             ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
 302         if opts.recodevideo:
 303             ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
 304         if opts.embedsubtitles:
 305             ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
 306         if opts.xattrs:
 307             ydl.add_post_processor(XAttrMetadataPP())
 308         if opts.embedthumbnail:
 309             if not opts.addmetadata:
 310                 ydl.add_post_processor(FFmpegAudioFixPP())
 311             ydl.add_post_processor(AtomicParsleyPP())
 312
 313
 314         # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
 315         # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
 316         if opts.exec_cmd:
 317             ydl.add_post_processor(ExecAfterDownloadPP(
 318                 verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
 319
 320         # Update version
 321         if opts.update_self:
 322             update_self(ydl.to_screen, opts.verbose)
 323
 324         # Remove cache dir
 325         if opts.rm_cachedir:
 326             ydl.cache.remove()
 327
 328         # Maybe do nothing
 329         if (len(all_urls) < 1) and (opts.load_info_filename is None):
 330             if not (opts.update_self or opts.rm_cachedir):
 331                 parser.error(u'you must provide at least one URL')
 332             else:
 333                 sys.exit()
 334
 335         try:
 336             if opts.load_info_filename is not None:
 337                 retcode = ydl.download_with_info_file(opts.load_info_filename)
 338             else:
 339                 retcode = ydl.download(all_urls)
 340         except MaxDownloadsReached:
 341             ydl.to_screen(u'--max-download limit reached, aborting.')
 342             retcode = 101
 343
 344     sys.exit(retcode)
 345
 346
 347 def main(argv=None):
 348     try:
 349         _real_main(argv)
 350     except DownloadError:
 351         sys.exit(1)
 352     except SameFileError:
 353         sys.exit(u'ERROR: fixed output name but more than one file to download')
 354     except KeyboardInterrupt:
 355         sys.exit(u'\nERROR: Interrupted by user')