#!/usr/bin/env python # -*- coding: utf-8 -*- import codecs import io import os import random import sys from .configuration import parse_options from .utils import ( compat_getpass, compat_print, DateRange, DEFAULT_OUTTMPL, decodeOption, DownloadError, MaxDownloadsReached, preferredencoding, read_batch_urls, SameFileError, setproctitle, std_headers, write_string, ) from .update import update_self from .FileDownloader import ( FileDownloader, ) from .extractor import gen_extractors from .YoutubeDL import YoutubeDL from .postprocessor import ( AtomicParsleyPP, FFmpegAudioFixPP, FFmpegMetadataPP, FFmpegVideoConvertor, FFmpegExtractAudioPP, FFmpegEmbedSubtitlePP, XAttrMetadataPP, ) def _real_main(argv): # Compatibility fixes for Windows if sys.platform == 'win32': # https://github.com/rg3/youtube-dl/issues/820 codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None) setproctitle(u'youtube-dl') parser, opts, args = parse_options(argv) if opts.user_agent is not None: std_headers['User-Agent'] = opts.user_agent if opts.referer is not None: std_headers['Referer'] = opts.referer if opts.headers is not None: for h in opts.headers: if ':' not in h[1:]: parser.error(u'wrong header formatting, it should be key:value, not "%s"' % h) key, value = h.split(':', 2) if opts.verbose: write_string(u'[debug] Adding header from command line option %s:%s\n' % (key, value)) std_headers[key] = value if opts.dump_user_agent: compat_print(std_headers['User-Agent']) return batch_urls = [] if opts.batchfile is not None: try: if opts.batchfile == '-': batchfd = sys.stdin else: batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore') batch_urls = read_batch_urls(batchfd) if opts.verbose: write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n') except IOError: sys.exit(u'ERROR: batch file could not be read') all_urls = [url.strip() for url in batch_urls + args] _enc = preferredencoding() all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] extractors = gen_extractors() if opts.list_extractors: for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): status = ' (CURRENTLY BROKEN)' if not ie.working() else '' compat_print(ie.IE_NAME + status) for url in all_urls: if ie.suitable(url): compat_print(u' ' + url) return if opts.list_extractor_descriptions: for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): if not ie.working(): continue desc = getattr(ie, 'IE_DESC', ie.IE_NAME) if not desc: continue if hasattr(ie, 'SEARCH_KEY'): searches = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise') counts = (u'', u'5', u'10', u'all') desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(counts), random.choice(searches)) compat_print(desc) return # Conflicting, missing and erroneous options if opts.usenetrc and (opts.username or opts.password): parser.error(u'using .netrc conflicts with giving username/password') if opts.password and not opts.username: parser.error(u'account username missing') if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): parser.error(u'using output template conflicts with using title, video ID or auto number') if opts.usetitle and opts.useid: parser.error(u'using title conflicts with using video ID') if opts.username and not opts.password: opts.password = compat_getpass(u'Type account password and press [Return]: ') if opts.ratelimit is not None: numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) if numeric_limit is None: parser.error(u'invalid rate limit specified') opts.ratelimit = numeric_limit if opts.min_filesize is not None: numeric_limit = FileDownloader.parse_bytes(opts.min_filesize) if numeric_limit is None: parser.error(u'invalid min_filesize specified') opts.min_filesize = numeric_limit if opts.max_filesize is not None: numeric_limit = FileDownloader.parse_bytes(opts.max_filesize) if numeric_limit is None: parser.error(u'invalid max_filesize specified') opts.max_filesize = numeric_limit if opts.retries is not None: try: opts.retries = int(opts.retries) except (TypeError, ValueError): parser.error(u'invalid retry count specified') if opts.buffersize is not None: numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) if numeric_buffersize is None: parser.error(u'invalid buffer size specified') opts.buffersize = numeric_buffersize if opts.playliststart <= 0: parser.error(u'Playlist start must be positive') if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart: parser.error(u'Playlist end must be greater than playlist start') if opts.extractaudio: if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']: parser.error(u'invalid audio format specified') if opts.audioquality: opts.audioquality = opts.audioquality.strip('kK') if not opts.audioquality.isdigit(): parser.error(u'invalid audio quality specified') if opts.recodevideo: if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: parser.error(u'invalid video recode format specified') if opts.date is not None: date = DateRange.day(opts.date) else: date = DateRange(opts.dateafter, opts.datebefore) if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search: parser.error(u'--default-search invalid; did you forget a colon (:) at the end?') # Do not download videos when there are audio-only formats if opts.extractaudio and not opts.keepvideo and opts.format is None: opts.format = 'bestaudio/best' # --all-sub automatically sets --write-sub if --write-auto-sub is not given # this was the old behaviour if only --all-sub was given. if opts.allsubtitles and not opts.writeautomaticsub: opts.writesubtitles = True if sys.version_info < (3,): # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) if opts.outtmpl is not None: opts.outtmpl = opts.outtmpl.decode(preferredencoding()) outtmpl =((opts.outtmpl is not None and opts.outtmpl) or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s') or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s') or (opts.useid and u'%(id)s.%(ext)s') or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') or DEFAULT_OUTTMPL) if not os.path.splitext(outtmpl)[1] and opts.extractaudio: parser.error(u'Cannot download a video and extract audio into the same' u' file! Use "{0}.%(ext)s" instead of "{0}" as the output' u' template'.format(outtmpl)) 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 download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive ydl_opts = { 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, 'videopassword': opts.videopassword, 'quiet': (opts.quiet or any_printing), 'no_warnings': opts.no_warnings, 'forceurl': opts.geturl, 'forcetitle': opts.gettitle, 'forceid': opts.getid, 'forcethumbnail': opts.getthumbnail, 'forcedescription': opts.getdescription, 'forceduration': opts.getduration, 'forcefilename': opts.getfilename, 'forceformat': opts.getformat, 'forcejson': opts.dumpjson, 'simulate': opts.simulate, 'skip_download': (opts.skip_download or opts.simulate or any_printing), 'format': opts.format, 'format_limit': opts.format_limit, 'listformats': opts.listformats, 'outtmpl': outtmpl, 'autonumber_size': opts.autonumber_size, 'restrictfilenames': opts.restrictfilenames, 'ignoreerrors': opts.ignoreerrors, 'ratelimit': opts.ratelimit, 'nooverwrites': opts.nooverwrites, 'retries': opts.retries, 'buffersize': opts.buffersize, 'noresizebuffer': opts.noresizebuffer, 'continuedl': opts.continue_dl, 'noprogress': opts.noprogress, 'progress_with_newline': opts.progress_with_newline, 'playliststart': opts.playliststart, 'playlistend': opts.playlistend, 'noplaylist': opts.noplaylist, 'logtostderr': opts.outtmpl == '-', 'consoletitle': opts.consoletitle, 'nopart': opts.nopart, 'updatetime': opts.updatetime, 'writedescription': opts.writedescription, 'writeannotations': opts.writeannotations, 'writeinfojson': opts.writeinfojson, 'writethumbnail': opts.writethumbnail, 'writesubtitles': opts.writesubtitles, 'writeautomaticsub': opts.writeautomaticsub, 'allsubtitles': opts.allsubtitles, 'listsubtitles': opts.listsubtitles, 'subtitlesformat': opts.subtitlesformat, 'subtitleslangs': opts.subtitleslangs, 'matchtitle': decodeOption(opts.matchtitle), 'rejecttitle': decodeOption(opts.rejecttitle), 'max_downloads': opts.max_downloads, 'prefer_free_formats': opts.prefer_free_formats, 'verbose': opts.verbose, 'dump_intermediate_pages': opts.dump_intermediate_pages, 'write_pages': opts.write_pages, 'test': opts.test, 'keepvideo': opts.keepvideo, 'min_filesize': opts.min_filesize, 'max_filesize': opts.max_filesize, 'min_views': opts.min_views, 'max_views': opts.max_views, 'daterange': date, 'cachedir': opts.cachedir, 'youtube_print_sig_code': opts.youtube_print_sig_code, 'age_limit': opts.age_limit, 'download_archive': download_archive_fn, 'cookiefile': opts.cookiefile, 'nocheckcertificate': opts.no_check_certificate, 'prefer_insecure': opts.prefer_insecure, 'proxy': opts.proxy, 'socket_timeout': opts.socket_timeout, 'bidi_workaround': opts.bidi_workaround, 'debug_printtraffic': opts.debug_printtraffic, 'prefer_ffmpeg': opts.prefer_ffmpeg, 'include_ads': opts.include_ads, 'default_search': opts.default_search, 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 'encoding': opts.encoding, } with YoutubeDL(ydl_opts) as ydl: ydl.print_debug_header() ydl.add_default_info_extractors() # PostProcessors # Add the metadata pp first, the other pps will copy it if opts.addmetadata: ydl.add_post_processor(FFmpegMetadataPP()) if opts.extractaudio: ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites)) if opts.recodevideo: ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo)) if opts.embedsubtitles: ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat)) if opts.xattrs: ydl.add_post_processor(XAttrMetadataPP()) if opts.embedthumbnail: if not opts.addmetadata: ydl.add_post_processor(FFmpegAudioFixPP()) ydl.add_post_processor(AtomicParsleyPP()) # Update version if opts.update_self: update_self(ydl.to_screen, opts.verbose) return # Maybe do nothing if not (all_urls or opts.load_info_filename): parser.error(u'you must provide at least one URL') try: if opts.load_info_filename: retcode = ydl.download_with_info_file(opts.load_info_filename) else: retcode = ydl.download(all_urls) except MaxDownloadsReached: ydl.to_screen(u'--max-download limit reached, aborting.') retcode = 101 sys.exit(retcode) def main(argv=None): try: _real_main(argv) except DownloadError: sys.exit(1) except SameFileError: sys.exit(u'ERROR: fixed output name but more than one file to download') except KeyboardInterrupt: sys.exit(u'\nERROR: Interrupted by user')