from .compat import compat_shlex_quote
from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
-from .downloader import FileDownloader
from .downloader.external import get_external_downloader
from .extractor import list_extractor_classes
from .extractor.adobepass import MSO_INFO
-from .extractor.common import InfoExtractor
from .options import parseOpts
from .postprocessor import (
FFmpegExtractAudioPP,
DateRange,
DownloadCancelled,
DownloadError,
+ FormatSorter,
GeoUtils,
PlaylistEntries,
SameFileError,
format_field,
int_or_none,
match_filter_func,
+ parse_bytes,
parse_duration,
preferredencoding,
read_batch_urls,
def print_extractor_information(opts, urls):
- # Importing GenericIE is currently slow since it imports other extractors
- # TODO: Move this back to module level after generalization of embed detection
- from .extractor.generic import GenericIE
-
out = ''
if opts.list_extractors:
+ # Importing GenericIE is currently slow since it imports YoutubeIE
+ from .extractor.generic import GenericIE
+
urls = dict.fromkeys(urls, False)
for ie in list_extractor_classes(opts.age_limit):
out += ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n'
else:
opts.embed_infojson = False
if 'format-sort' in opts.compat_opts:
- opts.format_sort.extend(InfoExtractor.FormatSort.ytdl_default)
+ opts.format_sort.extend(FormatSorter.ytdl_default)
_video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
_audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
if _video_multistreams_set is False and _audio_multistreams_set is False:
# Format sort
for f in opts.format_sort:
- validate_regex('format sorting', f, InfoExtractor.FormatSort.regex)
+ validate_regex('format sorting', f, FormatSorter.regex)
# Postprocessor formats
validate_regex('merge output format', opts.merge_output_format,
raise ValueError(f'invalid {key} retry sleep expression {expr!r}')
# Bytes
- def parse_bytes(name, value):
+ def validate_bytes(name, value):
if value is None:
return None
- numeric_limit = FileDownloader.parse_bytes(value)
+ numeric_limit = parse_bytes(value)
validate(numeric_limit is not None, 'rate limit', value)
return numeric_limit
- opts.ratelimit = parse_bytes('rate limit', opts.ratelimit)
- opts.throttledratelimit = parse_bytes('throttled rate limit', opts.throttledratelimit)
- opts.min_filesize = parse_bytes('min filesize', opts.min_filesize)
- opts.max_filesize = parse_bytes('max filesize', opts.max_filesize)
- opts.buffersize = parse_bytes('buffer size', opts.buffersize)
- opts.http_chunk_size = parse_bytes('http chunk size', opts.http_chunk_size)
+ opts.ratelimit = validate_bytes('rate limit', opts.ratelimit)
+ opts.throttledratelimit = validate_bytes('throttled rate limit', opts.throttledratelimit)
+ opts.min_filesize = validate_bytes('min filesize', opts.min_filesize)
+ opts.max_filesize = validate_bytes('max filesize', opts.max_filesize)
+ opts.buffersize = validate_bytes('buffer size', opts.buffersize)
+ opts.http_chunk_size = validate_bytes('http chunk size', opts.http_chunk_size)
# Output templates
def validate_outtmpl(tmpl, msg):
if outtmpl_default == '':
opts.skip_download = None
del opts.outtmpl['default']
- if outtmpl_default and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
- raise ValueError(
- 'Cannot download a video and extract audio into the same file! '
- f'Use "{outtmpl_default}.%(ext)s" instead of "{outtmpl_default}" as the output template')
def parse_chapters(name, value):
chapters, ranges = [], []
+ parse_timestamp = lambda x: float('inf') if x in ('inf', 'infinite') else parse_duration(x)
for regex in value or []:
if regex.startswith('*'):
- for range in regex[1:].split(','):
- dur = tuple(map(parse_duration, range.strip().split('-')))
- if len(dur) == 2 and all(t is not None for t in dur):
- ranges.append(dur)
- else:
- raise ValueError(f'invalid {name} time range "{regex}". Must be of the form *start-end')
+ for range_ in map(str.strip, regex[1:].split(',')):
+ mobj = range_ != '-' and re.fullmatch(r'([^-]+)?\s*-\s*([^-]+)?', range_)
+ dur = mobj and (parse_timestamp(mobj.group(1) or '0'), parse_timestamp(mobj.group(2) or 'inf'))
+ if None in (dur or [None]):
+ raise ValueError(f'invalid {name} time range "{regex}". Must be of the form "*start-end"')
+ ranges.append(dur)
continue
try:
chapters.append(re.compile(regex))
mobj = re.fullmatch(r'''(?x)
(?P<name>[^+:]+)
(?:\s*\+\s*(?P<keyring>[^:]+))?
- (?:\s*:\s*(?P<profile>.+?))?
+ (?:\s*:\s*(?
!:)(?P<profile>.+?))?
(?:\s*::\s*(?P<container>.+))?
''', opts.cookiesfrombrowser)
if mobj is None:
raise ValueError(f'{cmd} is invalid; {err}')
yield action
- parse_metadata = opts.parse_metadata or []
if opts.metafromtitle is not None:
- parse_metadata.append('title:%s' % opts.metafromtitle)
- opts.parse_metadata = list(itertools.chain(*map(metadataparser_actions, parse_metadata)))
+ opts.parse_metadata.setdefault('pre_process', []).append('title:%s' % opts.metafromtitle)
+ opts.parse_metadata = {
+ k: list(itertools.chain(*map(metadataparser_actions, v)))
+ for k, v in opts.parse_metadata.items()
+ }
# Other options
if opts.playlist_items is not None:
except Exception:
raise ValueError('unsupported geo-bypass country or ip-block')
- opts.match_filter = match_filter_func(opts.match_filter)
+ opts.match_filter = match_filter_func(opts.match_filter, opts.breaking_match_filter)
if opts.download_archive is not None:
opts.download_archive = expand_path(opts.download_archive)
+ if opts.ffmpeg_location is not None:
+ opts.ffmpeg_location = expand_path(opts.ffmpeg_location)
+
if opts.user_agent is not None:
opts.headers.setdefault('User-Agent', opts.user_agent)
if opts.referer is not None:
val1=opts.sponskrub and opts.sponskrub_cut)
# Conflicts with --allow-unplayable-formats
- report_conflict('--add-metadata', 'addmetadata')
+ report_conflict('--embed-metadata', 'addmetadata')
report_conflict('--embed-chapters', 'addchapters')
report_conflict('--embed-info-json', 'embed_infojson')
report_conflict('--embed-subs', 'embedsubtitles')
def get_postprocessors(opts):
yield from opts.add_postprocessors
- if opts.parse_metadata:
+ for when, actions in opts.parse_metadata.items():
yield {
'key': 'MetadataParser',
- 'actions': opts.parse_metadata,
- 'when': 'pre_process'
+ 'actions': actions,
+ 'when': when
}
sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
if sponsorblock_query:
postprocessors = list(get_postprocessors(opts))
- print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[2:])
+ print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[3:])
any_getting = any(getattr(opts, k) for k in (
'dumpjson', 'dump_single_json', 'getdescription', 'getduration', 'getfilename',
'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
))
+ if opts.quiet is None:
+ opts.quiet = any_getting or opts.print_json or bool(opts.forceprint)
playlist_pps = [pp for pp in postprocessors if pp.get('when') == 'playlist']
write_playlist_infojson = (opts.writeinfojson and not opts.clean_infojson
'client_certificate': opts.client_certificate,
'client_certificate_key': opts.client_certificate_key,
'client_certificate_password': opts.client_certificate_password,
- 'quiet': opts.quiet or any_getting or opts.print_json or bool(opts.forceprint),
+ 'quiet': opts.quiet,
'no_warnings': opts.no_warnings,
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'legacyserverconnect': opts.legacy_server_connect,
'nocheckcertificate': opts.no_check_certificate,
'prefer_insecure': opts.prefer_insecure,
+ 'enable_file_urls': opts.enable_file_urls,
'http_headers': opts.headers,
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
if opts.rm_cachedir:
ydl.cache.remove()
- updater = Updater(ydl)
+ updater = Updater(ydl, opts.update_self if isinstance(opts.update_self, str) else None)
if opts.update_self and updater.update() and actual_use:
if updater.cmd:
return updater.restart()
parser.destroy()
try:
if opts.load_info_filename is not None:
+ if all_urls:
+ ydl.report_warning('URLs are ignored due to --load-info-json')
return ydl.download_with_info_file(expand_path(opts.load_info_filename))
else:
return ydl.download(all_urls)
def main(argv=None):
+ global _IN_CLI
+ _IN_CLI = True
try:
_exit(*variadic(_real_main(argv)))
except DownloadError:
projects / yt-dlp.git / blobdiff