logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

__init__.py (20438B)

    

  1. #!/usr/bin/env python
  2. # coding: utf-8
  4. from __future__ import unicode_literals
  6. __license__ = 'Public Domain'
  8. import io
  9. import os
  10. import random
  11. import sys
  14. from .options import (
  15.     parseOpts,
  16. )
  17. from .compat import (
  18.     compat_getpass,
  19.     compat_register_utf8,
  20.     compat_shlex_split,
  21.     workaround_optparse_bug9161,
  22. )
  23. from .utils import (
  24.     DateRange,
  25.     decodeOption,
  26.     DEFAULT_OUTTMPL,
  27.     DownloadError,
  28.     expand_path,
  29.     match_filter_func,
  30.     MaxDownloadsReached,
  31.     preferredencoding,
  32.     read_batch_urls,
  33.     SameFileError,
  34.     setproctitle,
  35.     std_headers,
  36.     write_string,
  37.     render_table,
  38. )
  39. from .update import update_self
  40. from .downloader import (
  41.     FileDownloader,
  42. )
  43. from .extractor import gen_extractors, list_extractors
  44. from .extractor.adobepass import MSO_INFO
  45. from .YoutubeDL import YoutubeDL
  48. def _real_main(argv=None):
  49.     # Compatibility fix for Windows
  50.     compat_register_utf8()
  52.     workaround_optparse_bug9161()
  54.     setproctitle('youtube-dl')
  56.     parser, opts, args = parseOpts(argv)
  58.     # Set user agent
  59.     if opts.user_agent is not None:
  60.         std_headers['User-Agent'] = opts.user_agent
  62.     # Set referer
  63.     if opts.referer is not None:
  64.         std_headers['Referer'] = opts.referer
  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
  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)
  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.                     expand_path(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 %s could not be read' % opts.batchfile)
  96.     all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls
  97.     _enc = preferredencoding()
  98.     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
  100.     if opts.list_extractors:
  101.         for ie in list_extractors(opts.age_limit):
  102.             write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
  103.             matchedUrls = [url for url in all_urls if ie.suitable(url)]
  104.             for mu in matchedUrls:
  105.                 write_string('  ' + mu + '\n', out=sys.stdout)
  106.         sys.exit(0)
  107.     if opts.list_extractor_descriptions:
  108.         for ie in list_extractors(opts.age_limit):
  109.             if not ie._WORKING:
  110.                 continue
  111.             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
  112.             if desc is False:
  113.                 continue
  114.             if hasattr(ie, 'SEARCH_KEY'):
  115.                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
  116.                 _COUNTS = ('', '5', '10', 'all')
  117.                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
  118.             write_string(desc + '\n', out=sys.stdout)
  119.         sys.exit(0)
  120.     if opts.ap_list_mso:
  121.         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
  122.         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
  123.         sys.exit(0)
  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('using .netrc conflicts with giving username/password')
  128.     if opts.password is not None and opts.username is None:
  129.         parser.error('account username missing\n')
  130.     if opts.ap_password is not None and opts.ap_username is None:
  131.         parser.error('TV Provider account username missing\n')
  132.     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
  133.         parser.error('using output template conflicts with using title, video ID or auto number')
  134.     if opts.autonumber_size is not None:
  135.         if opts.autonumber_size <= 0:
  136.             parser.error('auto number size must be positive')
  137.     if opts.autonumber_start is not None:
  138.         if opts.autonumber_start < 0:
  139.             parser.error('auto number start must be positive or 0')
  140.     if opts.usetitle and opts.useid:
  141.         parser.error('using title conflicts with using video ID')
  142.     if opts.username is not None and opts.password is None:
  143.         opts.password = compat_getpass('Type account password and press [Return]: ')
  144.     if opts.ap_username is not None and opts.ap_password is None:
  145.         opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
  146.     if opts.ratelimit is not None:
  147.         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
  148.         if numeric_limit is None:
  149.             parser.error('invalid rate limit specified')
  150.         opts.ratelimit = numeric_limit
  151.     if opts.min_filesize is not None:
  152.         numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
  153.         if numeric_limit is None:
  154.             parser.error('invalid min_filesize specified')
  155.         opts.min_filesize = numeric_limit
  156.     if opts.max_filesize is not None:
  157.         numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
  158.         if numeric_limit is None:
  159.             parser.error('invalid max_filesize specified')
  160.         opts.max_filesize = numeric_limit
  161.     if opts.sleep_interval is not None:
  162.         if opts.sleep_interval < 0:
  163.             parser.error('sleep interval must be positive or 0')
  164.     if opts.max_sleep_interval is not None:
  165.         if opts.max_sleep_interval < 0:
  166.             parser.error('max sleep interval must be positive or 0')
  167.         if opts.sleep_interval is None:
  168.             parser.error('min sleep interval must be specified, use --min-sleep-interval')
  169.         if opts.max_sleep_interval < opts.sleep_interval:
  170.             parser.error('max sleep interval must be greater than or equal to min sleep interval')
  171.     else:
  172.         opts.max_sleep_interval = opts.sleep_interval
  173.     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
  174.         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
  176.     def parse_retries(retries):
  177.         if retries in ('inf', 'infinite'):
  178.             parsed_retries = float('inf')
  179.         else:
  180.             try:
  181.                 parsed_retries = int(retries)
  182.             except (TypeError, ValueError):
  183.                 parser.error('invalid retry count specified')
  184.         return parsed_retries
  185.     if opts.retries is not None:
  186.         opts.retries = parse_retries(opts.retries)
  187.     if opts.fragment_retries is not None:
  188.         opts.fragment_retries = parse_retries(opts.fragment_retries)
  189.     if opts.buffersize is not None:
  190.         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
  191.         if numeric_buffersize is None:
  192.             parser.error('invalid buffer size specified')
  193.         opts.buffersize = numeric_buffersize
  194.     if opts.http_chunk_size is not None:
  195.         numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
  196.         if not numeric_chunksize:
  197.             parser.error('invalid http chunk size specified')
  198.         opts.http_chunk_size = numeric_chunksize
  199.     if opts.playliststart <= 0:
  200.         raise ValueError('Playlist start must be positive')
  201.     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
  202.         raise ValueError('Playlist end must be greater than playlist start')
  203.     if opts.extractaudio:
  204.         if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
  205.             parser.error('invalid audio format specified')
  206.     if opts.audioquality:
  207.         opts.audioquality = opts.audioquality.strip('k').strip('K')
  208.         if not opts.audioquality.isdigit():
  209.             parser.error('invalid audio quality specified')
  210.     if opts.recodevideo is not None:
  211.         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
  212.             parser.error('invalid video recode format specified')
  213.     if opts.convertsubtitles is not None:
  214.         if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
  215.             parser.error('invalid subtitle format specified')
  217.     if opts.date is not None:
  218.         date = DateRange.day(opts.date)
  219.     else:
  220.         date = DateRange(opts.dateafter, opts.datebefore)
  222.     # Do not download videos when there are audio-only formats
  223.     if opts.extractaudio and not opts.keepvideo and opts.format is None:
  224.         opts.format = 'bestaudio/best'
  226.     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
  227.     # this was the old behaviour if only --all-sub was given.
  228.     if opts.allsubtitles and not opts.writeautomaticsub:
  229.         opts.writesubtitles = True
  231.     outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
  232.                or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
  233.                or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
  234.                or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
  235.                or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
  236.                or (opts.useid and '%(id)s.%(ext)s')
  237.                or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
  238.                or DEFAULT_OUTTMPL)
  239.     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
  240.         parser.error('Cannot download a video and extract audio into the same'
  241.                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
  242.                      ' template'.format(outtmpl))
  244.     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
  245.     any_printing = opts.print_json
  246.     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
  248.     # PostProcessors
  249.     postprocessors = []
  250.     if opts.metafromtitle:
  251.         postprocessors.append({
  252.             'key': 'MetadataFromTitle',
  253.             'titleformat': opts.metafromtitle
  254.         })
  255.     if opts.extractaudio:
  256.         postprocessors.append({
  257.             'key': 'FFmpegExtractAudio',
  258.             'preferredcodec': opts.audioformat,
  259.             'preferredquality': opts.audioquality,
  260.             'nopostoverwrites': opts.nopostoverwrites,
  261.         })
  262.     if opts.recodevideo:
  263.         postprocessors.append({
  264.             'key': 'FFmpegVideoConvertor',
  265.             'preferedformat': opts.recodevideo,
  266.         })
  267.     # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
  268.     # FFmpegExtractAudioPP as containers before conversion may not support
  269.     # metadata (3gp, webm, etc.)
  270.     # And this post-processor should be placed before other metadata
  271.     # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
  272.     # extra metadata. By default ffmpeg preserves metadata applicable for both
  273.     # source and target containers. From this point the container won't change,
  274.     # so metadata can be added here.
  275.     if opts.addmetadata:
  276.         postprocessors.append({'key': 'FFmpegMetadata'})
  277.     if opts.convertsubtitles:
  278.         postprocessors.append({
  279.             'key': 'FFmpegSubtitlesConvertor',
  280.             'format': opts.convertsubtitles,
  281.         })
  282.     if opts.embedsubtitles:
  283.         postprocessors.append({
  284.             'key': 'FFmpegEmbedSubtitle',
  285.         })
  286.     if opts.embedthumbnail:
  287.         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
  288.         postprocessors.append({
  289.             'key': 'EmbedThumbnail',
  290.             'already_have_thumbnail': already_have_thumbnail
  291.         })
  292.         if not already_have_thumbnail:
  293.             opts.writethumbnail = True
  294.     # XAttrMetadataPP should be run after post-processors that may change file
  295.     # contents
  296.     if opts.xattrs:
  297.         postprocessors.append({'key': 'XAttrMetadata'})
  298.     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
  299.     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
  300.     if opts.exec_cmd:
  301.         postprocessors.append({
  302.             'key': 'ExecAfterDownload',
  303.             'exec_cmd': opts.exec_cmd,
  304.         })
  305.     external_downloader_args = None
  306.     if opts.external_downloader_args:
  307.         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
  308.     postprocessor_args = None
  309.     if opts.postprocessor_args:
  310.         postprocessor_args = compat_shlex_split(opts.postprocessor_args)
  311.     match_filter = (
  312.         None if opts.match_filter is None
  313.         else match_filter_func(opts.match_filter))
  315.     ydl_opts = {
  316.         'usenetrc': opts.usenetrc,
  317.         'username': opts.username,
  318.         'password': opts.password,
  319.         'twofactor': opts.twofactor,
  320.         'videopassword': opts.videopassword,
  321.         'ap_mso': opts.ap_mso,
  322.         'ap_username': opts.ap_username,
  323.         'ap_password': opts.ap_password,
  324.         'quiet': (opts.quiet or any_getting or any_printing),
  325.         'no_warnings': opts.no_warnings,
  326.         'forceurl': opts.geturl,
  327.         'forcetitle': opts.gettitle,
  328.         'forceid': opts.getid,
  329.         'forcethumbnail': opts.getthumbnail,
  330.         'forcedescription': opts.getdescription,
  331.         'forceduration': opts.getduration,
  332.         'forcefilename': opts.getfilename,
  333.         'forceformat': opts.getformat,
  334.         'forcejson': opts.dumpjson or opts.print_json,
  335.         'dump_single_json': opts.dump_single_json,
  336.         'simulate': opts.simulate or any_getting,
  337.         'skip_download': opts.skip_download,
  338.         'format': opts.format,
  339.         'listformats': opts.listformats,
  340.         'outtmpl': outtmpl,
  341.         'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
  342.         'autonumber_size': opts.autonumber_size,
  343.         'autonumber_start': opts.autonumber_start,
  344.         'restrictfilenames': opts.restrictfilenames,
  345.         'ignoreerrors': opts.ignoreerrors,
  346.         'force_generic_extractor': opts.force_generic_extractor,
  347.         'ratelimit': opts.ratelimit,
  348.         'nooverwrites': opts.nooverwrites,
  349.         'retries': opts.retries,
  350.         'fragment_retries': opts.fragment_retries,
  351.         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
  352.         'keep_fragments': opts.keep_fragments,
  353.         'buffersize': opts.buffersize,
  354.         'noresizebuffer': opts.noresizebuffer,
  355.         'http_chunk_size': opts.http_chunk_size,
  356.         'continuedl': opts.continue_dl,
  357.         'noprogress': opts.noprogress,
  358.         'progress_with_newline': opts.progress_with_newline,
  359.         'playliststart': opts.playliststart,
  360.         'playlistend': opts.playlistend,
  361.         'playlistreverse': opts.playlist_reverse,
  362.         'playlistrandom': opts.playlist_random,
  363.         'noplaylist': opts.noplaylist,
  364.         'logtostderr': opts.outtmpl == '-',
  365.         'consoletitle': opts.consoletitle,
  366.         'nopart': opts.nopart,
  367.         'updatetime': opts.updatetime,
  368.         'writedescription': opts.writedescription,
  369.         'writeannotations': opts.writeannotations,
  370.         'writeinfojson': opts.writeinfojson,
  371.         'writethumbnail': opts.writethumbnail,
  372.         'write_all_thumbnails': opts.write_all_thumbnails,
  373.         'writesubtitles': opts.writesubtitles,
  374.         'writeautomaticsub': opts.writeautomaticsub,
  375.         'allsubtitles': opts.allsubtitles,
  376.         'listsubtitles': opts.listsubtitles,
  377.         'subtitlesformat': opts.subtitlesformat,
  378.         'subtitleslangs': opts.subtitleslangs,
  379.         'matchtitle': decodeOption(opts.matchtitle),
  380.         'rejecttitle': decodeOption(opts.rejecttitle),
  381.         'max_downloads': opts.max_downloads,
  382.         'prefer_free_formats': opts.prefer_free_formats,
  383.         'verbose': opts.verbose,
  384.         'dump_intermediate_pages': opts.dump_intermediate_pages,
  385.         'write_pages': opts.write_pages,
  386.         'test': opts.test,
  387.         'keepvideo': opts.keepvideo,
  388.         'min_filesize': opts.min_filesize,
  389.         'max_filesize': opts.max_filesize,
  390.         'min_views': opts.min_views,
  391.         'max_views': opts.max_views,
  392.         'daterange': date,
  393.         'cachedir': opts.cachedir,
  394.         'youtube_print_sig_code': opts.youtube_print_sig_code,
  395.         'age_limit': opts.age_limit,
  396.         'download_archive': download_archive_fn,
  397.         'cookiefile': opts.cookiefile,
  398.         'nocheckcertificate': opts.no_check_certificate,
  399.         'prefer_insecure': opts.prefer_insecure,
  400.         'proxy': opts.proxy,
  401.         'socket_timeout': opts.socket_timeout,
  402.         'bidi_workaround': opts.bidi_workaround,
  403.         'debug_printtraffic': opts.debug_printtraffic,
  404.         'prefer_ffmpeg': opts.prefer_ffmpeg,
  405.         'include_ads': opts.include_ads,
  406.         'default_search': opts.default_search,
  407.         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
  408.         'encoding': opts.encoding,
  409.         'extract_flat': opts.extract_flat,
  410.         'mark_watched': opts.mark_watched,
  411.         'merge_output_format': opts.merge_output_format,
  412.         'postprocessors': postprocessors,
  413.         'fixup': opts.fixup,
  414.         'source_address': opts.source_address,
  415.         'call_home': opts.call_home,
  416.         'sleep_interval': opts.sleep_interval,
  417.         'max_sleep_interval': opts.max_sleep_interval,
  418.         'external_downloader': opts.external_downloader,
  419.         'list_thumbnails': opts.list_thumbnails,
  420.         'playlist_items': opts.playlist_items,
  421.         'xattr_set_filesize': opts.xattr_set_filesize,
  422.         'match_filter': match_filter,
  423.         'no_color': opts.no_color,
  424.         'ffmpeg_location': opts.ffmpeg_location,
  425.         'hls_prefer_native': opts.hls_prefer_native,
  426.         'hls_use_mpegts': opts.hls_use_mpegts,
  427.         'external_downloader_args': external_downloader_args,
  428.         'postprocessor_args': postprocessor_args,
  429.         'cn_verification_proxy': opts.cn_verification_proxy,
  430.         'geo_verification_proxy': opts.geo_verification_proxy,
  431.         'config_location': opts.config_location,
  432.         'geo_bypass': opts.geo_bypass,
  433.         'geo_bypass_country': opts.geo_bypass_country,
  434.         'geo_bypass_ip_block': opts.geo_bypass_ip_block,
  435.         # just for deprecation check
  436.         'autonumber': opts.autonumber if opts.autonumber is True else None,
  437.         'usetitle': opts.usetitle if opts.usetitle is True else None,
  438.     }
  440.     with YoutubeDL(ydl_opts) as ydl:
  441.         # Update version
  442.         if opts.update_self:
  443.             update_self(ydl.to_screen, opts.verbose, ydl._opener)
  445.         # Remove cache dir
  446.         if opts.rm_cachedir:
  447.             ydl.cache.remove()
  449.         # Maybe do nothing
  450.         if (len(all_urls) < 1) and (opts.load_info_filename is None):
  451.             if opts.update_self or opts.rm_cachedir:
  452.                 sys.exit()
  454.             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
  455.             parser.error(
  456.                 'You must provide at least one URL.\n'
  457.                 'Type youtube-dl --help to see a list of all options.')
  459.         try:
  460.             if opts.load_info_filename is not None:
  461.                 retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
  462.             else:
  463.                 retcode = ydl.download(all_urls)
  464.         except MaxDownloadsReached:
  465.             ydl.to_screen('--max-download limit reached, aborting.')
  466.             retcode = 101
  468.     sys.exit(retcode)
  471. def main(argv=None):
  472.     try:
  473.         _real_main(argv)
  474.     except DownloadError:
  475.         sys.exit(1)
  476.     except SameFileError:
  477.         sys.exit('ERROR: fixed output name but more than one file to download')
  478.     except KeyboardInterrupt:
  479.         sys.exit('\nERROR: Interrupted by user')
  482. __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']