+import asyncio
import atexit
import base64
import binascii
import xml.etree.ElementTree
import zlib
-from .compat import asyncio, functools # isort: split
+from .compat import functools # isort: split
from .compat import (
compat_etree_fromstring,
compat_expanduser,
'juillet', 'août', 'septembre', 'octobre', 'novembre', 'décembre'],
}
-KNOWN_EXTENSIONS = (
- 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
- 'flv', 'f4v', 'f4a', 'f4b',
- 'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
- 'mkv', 'mka', 'mk3d',
- 'avi', 'divx',
- 'mov',
- 'asf', 'wmv', 'wma',
- '3gp', '3g2',
- 'mp3',
- 'flac',
- 'ape',
- 'wav',
- 'f4f', 'f4m', 'm3u8', 'smil')
-
# needed for sanitizing filenames in restricted mode
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
'%d/%m/%Y',
'%d/%m/%y',
'%d/%m/%Y %H:%M:%S',
+ '%d-%m-%Y %H:%M',
])
DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
if filename == '-':
if sys.platform == 'win32':
import msvcrt
- msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
+ # stdout may be any IO stream. Eg, when using contextlib.redirect_stdout
+ with contextlib.suppress(io.UnsupportedOperation):
+ msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
for attempt in range(2):
return os.path.join(*sanitized_path)
-def sanitize_url(url):
+def sanitize_url(url, *, scheme='http'):
# Prepend protocol-less URLs with `http:` scheme in order to mitigate
# the number of unwanted failures due to missing protocol
if url is None:
return
elif url.startswith('//'):
- return 'http:%s' % url
+ return f'{scheme}:{url}'
# Fix some common typos seen so far
COMMON_TYPOS = (
# https://github.com/ytdl-org/youtube-dl/issues/15649
self.countries = countries
+class UserNotLive(ExtractorError):
+ """Error when a channel/user is not live"""
+
+ def __init__(self, msg=None, **kwargs):
+ kwargs['expected'] = True
+ super().__init__(msg or 'The channel is not currently live', **kwargs)
+
+
class DownloadError(YoutubeDLError):
"""Download Error exception.
return age_limit < content_limit
+# List of known byte-order-marks (BOM)
+BOMS = [
+ (b'\xef\xbb\xbf', 'utf-8'),
+ (b'\x00\x00\xfe\xff', 'utf-32-be'),
+ (b'\xff\xfe\x00\x00', 'utf-32-le'),
+ (b'\xff\xfe', 'utf-16-le'),
+ (b'\xfe\xff', 'utf-16-be'),
+]
+
+
def is_html(first_bytes):
""" Detect whether a file contains HTML by examining its first bytes. """
- BOMS = [
- (b'\xef\xbb\xbf', 'utf-8'),
- (b'\x00\x00\xfe\xff', 'utf-32-be'),
- (b'\xff\xfe\x00\x00', 'utf-32-le'),
- (b'\xff\xfe', 'utf-16-le'),
- (b'\xfe\xff', 'utf-16-be'),
- ]
-
encoding = 'utf-8'
for bom, enc in BOMS:
while first_bytes.startswith(bom):
if not filters or any(match_str(f, info_dict, incomplete) for f in filters):
return NO_DEFAULT if interactive and not incomplete else None
else:
- video_title = info_dict.get('title') or info_dict.get('id') or 'video'
+ video_title = info_dict.get('title') or info_dict.get('id') or 'entry'
filter_str = ') | ('.join(map(str.strip, filters))
return f'{video_title} does not pass filter ({filter_str}), skipping ..'
return _match_func
return sys.stdin
+def determine_file_encoding(data):
+ """
+ Detect the text encoding used
+ @returns (encoding, bytes to skip)
+ """
+
+ # BOM marks are given priority over declarations
+ for bom, enc in BOMS:
+ if data.startswith(bom):
+ return enc, len(bom)
+
+ # Strip off all null bytes to match even when UTF-16 or UTF-32 is used.
+ # We ignore the endianness to get a good enough match
+ data = data.replace(b'\0', b'')
+ mobj = re.match(rb'(?m)^#\s*coding\s*:\s*(\S+)\s*$', data)
+ return mobj.group(1).decode() if mobj else None, 0
+
+
class Config:
own_args = None
parsed_args = None
@staticmethod
def read_file(filename, default=[]):
try:
- optionf = open(filename)
+ optionf = open(filename, 'rb')
except OSError:
return default # silently skip if file is not present
+ try:
+ enc, skip = determine_file_encoding(optionf.read(512))
+ optionf.seek(skip, io.SEEK_SET)
+ except OSError:
+ enc = None # silently skip read errors
try:
# FIXME: https://github.com/ytdl-org/youtube-dl/commit/dfe5fa49aed02cf36ba9f743b11b0903554b5e56
- contents = optionf.read()
+ contents = optionf.read().decode(enc or preferredencoding())
res = shlex.split(contents, comments=True)
except Exception as err:
raise ValueError(f'Unable to parse "{filename}": {err}')
return self.__dict__.items()
+MEDIA_EXTENSIONS = Namespace(
+ common_video=('avi', 'flv', 'mkv', 'mov', 'mp4', 'webm'),
+ video=('3g2', '3gp', 'f4v', 'mk3d', 'divx', 'mpg', 'ogv', 'm4v', 'wmv'),
+ common_audio=('aiff', 'alac', 'flac', 'm4a', 'mka', 'mp3', 'ogg', 'opus', 'wav'),
+ audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4p', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma'),
+ thumbnails=('jpg', 'png', 'webp'),
+ storyboards=('mhtml', ),
+ subtitles=('srt', 'vtt', 'ass', 'lrc'),
+ manifests=('f4f', 'f4m', 'm3u8', 'smil', 'mpd'),
+)
+MEDIA_EXTENSIONS.video += MEDIA_EXTENSIONS.common_video
+MEDIA_EXTENSIONS.audio += MEDIA_EXTENSIONS.common_audio
+
+KNOWN_EXTENSIONS = (*MEDIA_EXTENSIONS.video, *MEDIA_EXTENSIONS.audio, *MEDIA_EXTENSIONS.manifests)
+
+
# Deprecated
has_certifi = bool(certifi)
has_websockets = bool(websockets)
projects / yt-dlp.git / blobdiff