mirror of
https://github.com/yt-dlp/yt-dlp
synced 2024-06-29 05:54:33 +00:00
Compare commits
6 Commits
5aad7ea9db
...
72dd264987
Author | SHA1 | Date | |
---|---|---|---|
|
72dd264987 | ||
|
f3411af12e | ||
|
34bf80c62d | ||
|
0ed18251d2 | ||
|
773b554bf5 | ||
|
5982686f86 |
|
@ -158,6 +158,11 @@ def test_sanitize_filename(self):
|
|||
self.assertEqual('yes no', sanitize_filename('yes? no', is_id=False))
|
||||
self.assertEqual('this - that', sanitize_filename('this: that', is_id=False))
|
||||
|
||||
self.assertEqual('abc_<>\\*|de', sanitize_filename('abc/<>\\*|de', keep_bad_win_chars=True, is_id=False))
|
||||
self.assertEqual('xxx_<>\\*|', sanitize_filename('xxx/<>\\*|', keep_bad_win_chars=True, is_id=False))
|
||||
self.assertEqual('yes? no', sanitize_filename('yes? no', keep_bad_win_chars=True, is_id=False))
|
||||
self.assertEqual('this: that', sanitize_filename('this: that', keep_bad_win_chars=True, is_id=False))
|
||||
|
||||
self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
|
||||
aumlaut = 'ä'
|
||||
self.assertEqual(sanitize_filename(aumlaut), aumlaut)
|
||||
|
@ -168,6 +173,10 @@ def test_sanitize_filename(self):
|
|||
sanitize_filename('New World record at 0:12:34'),
|
||||
'New World record at 0_12_34')
|
||||
|
||||
self.assertEqual(
|
||||
sanitize_filename('New World record at 0:12:34', keep_bad_win_chars=True),
|
||||
'New World record at 0:12:34')
|
||||
|
||||
self.assertEqual(sanitize_filename('--gasdgf'), '--gasdgf')
|
||||
self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
|
||||
self.assertEqual(sanitize_filename('--gasdgf', is_id=False), '_-gasdgf')
|
||||
|
@ -219,6 +228,10 @@ def test_sanitize_ids(self):
|
|||
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
|
||||
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
|
||||
|
||||
self.assertEqual(sanitize_filename('_n_cd26wFpw', keep_bad_win_chars=True, is_id=True), '_n_cd26wFpw')
|
||||
self.assertEqual(sanitize_filename('_BD_eEpuzXw', keep_bad_win_chars=True, is_id=True), '_BD_eEpuzXw')
|
||||
self.assertEqual(sanitize_filename('N0Y__7-UOdI', keep_bad_win_chars=True, is_id=True), 'N0Y__7-UOdI')
|
||||
|
||||
def test_sanitize_path(self):
|
||||
if sys.platform != 'win32':
|
||||
return
|
||||
|
|
|
@ -1292,10 +1292,12 @@ def get_value(mdict):
|
|||
na = self.params.get('outtmpl_na_placeholder', 'NA')
|
||||
|
||||
def filename_sanitizer(key, value, restricted=self.params.get('restrictfilenames')):
|
||||
return sanitize_filename(str(value), restricted=restricted, is_id=(
|
||||
bool(re.search(r'(^|[_.])id(\.|$)', key))
|
||||
if 'filename-sanitization' in self.params['compat_opts']
|
||||
else NO_DEFAULT))
|
||||
return sanitize_filename(
|
||||
str(value), self.params.get('keep_bad_win_chars', False), restricted=restricted,
|
||||
is_id=(
|
||||
bool(re.search(r'(^|[_.])id(\.|$)', key))
|
||||
if 'filename-sanitization' in self.params['compat_opts']
|
||||
else NO_DEFAULT))
|
||||
|
||||
sanitizer = sanitize if callable(sanitize) else filename_sanitizer
|
||||
sanitize = bool(sanitize)
|
||||
|
|
|
@ -816,6 +816,7 @@ def parse_options(argv=None):
|
|||
'autonumber_start': opts.autonumber_start,
|
||||
'restrictfilenames': opts.restrictfilenames,
|
||||
'windowsfilenames': opts.windowsfilenames,
|
||||
'keep_bad_win_chars': opts.keep_bad_win_chars,
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
'force_generic_extractor': opts.force_generic_extractor,
|
||||
'allowed_extractors': opts.allowed_extractors or ['default'],
|
||||
|
|
|
@ -1020,7 +1020,7 @@ def _request_dump_filename(self, url, video_id, data=None):
|
|||
if len(basen) > trim_length:
|
||||
h = '___' + hashlib.md5(basen.encode()).hexdigest()
|
||||
basen = basen[:trim_length - len(h)] + h
|
||||
filename = sanitize_filename(f'{basen}.dump', restricted=True)
|
||||
filename = sanitize_filename(f'{basen}.dump', self.get_param('keep_bad_win_chars', False), restricted=True)
|
||||
# Working around MAX_PATH limitation on Windows (see
|
||||
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
|
||||
if compat_os_name == 'nt':
|
||||
|
|
|
@ -1,51 +1,35 @@
|
|||
import random
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import xpath_text
|
||||
|
||||
|
||||
class MatchTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
|
||||
_VALID_URL = [
|
||||
r'https?://matchtv\.ru/on-air/?(?:$|[?#])',
|
||||
r'https?://video\.matchtv\.ru/iframe/channel/106/?(?:$|[?#])',
|
||||
]
|
||||
_TESTS = [{
|
||||
'url': 'http://matchtv.ru/#live-player',
|
||||
'url': 'http://matchtv.ru/on-air/',
|
||||
'info_dict': {
|
||||
'id': 'matchtv-live',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
||||
'is_live': True,
|
||||
'live_status': 'is_live',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://matchtv.ru/on-air/',
|
||||
'url': 'https://video.matchtv.ru/iframe/channel/106',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = 'matchtv-live'
|
||||
video_url = self._download_json(
|
||||
'http://player.matchtv.ntvplus.tv/player/smil', video_id,
|
||||
query={
|
||||
'ts': '',
|
||||
'quality': 'SD',
|
||||
'contentId': '561d2c0df7159b37178b4567',
|
||||
'sign': '',
|
||||
'includeHighlights': '0',
|
||||
'userId': '',
|
||||
'sessionId': random.randint(1, 1000000000),
|
||||
'contentType': 'channel',
|
||||
'timeShift': '0',
|
||||
'platform': 'portal',
|
||||
},
|
||||
headers={
|
||||
'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
|
||||
})['data']['videoUrl']
|
||||
f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
|
||||
formats = self._extract_f4m_formats(f4m_url, video_id)
|
||||
webpage = self._download_webpage('https://video.matchtv.ru/iframe/channel/106', video_id)
|
||||
video_url = self._html_search_regex(
|
||||
r'data-config="config=(https?://[^?"]+)[?"]', webpage, 'video URL').replace('/feed/', '/media/') + '.m3u8'
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': 'Матч ТВ - Прямой эфир',
|
||||
'is_live': True,
|
||||
'formats': formats,
|
||||
'formats': self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True),
|
||||
}
|
||||
|
|
|
@ -267,6 +267,10 @@ def _dict_from_options_callback(
|
|||
out_dict[key] = [*out_dict.get(key, []), val] if append else val
|
||||
setattr(parser.values, option.dest, out_dict)
|
||||
|
||||
def _store_multiple_callback(option, opt_str, value, parser, values):
|
||||
for key, value in values.items():
|
||||
setattr(parser.values, key, value)
|
||||
|
||||
def when_prefix(default):
|
||||
return {
|
||||
'default': {},
|
||||
|
@ -1361,7 +1365,13 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
|
|||
help='Force filenames to be Windows-compatible')
|
||||
filesystem.add_option(
|
||||
'--no-windows-filenames',
|
||||
action='store_false', dest='windowsfilenames',
|
||||
action='callback', dest='keep_bad_win_chars', default=False, callback=_store_multiple_callback,
|
||||
callback_kwargs={
|
||||
'values': {
|
||||
'windowsfilenames': False,
|
||||
'keep_bad_win_chars': True
|
||||
}
|
||||
},
|
||||
help='Make filenames Windows-compatible only if using Windows (default)')
|
||||
filesystem.add_option(
|
||||
'--trim-filenames', '--trim-file-names', metavar='LENGTH',
|
||||
|
|
|
@ -609,11 +609,12 @@ def timeconvert(timestr):
|
|||
return timestamp
|
||||
|
||||
|
||||
def sanitize_filename(s, restricted=False, is_id=NO_DEFAULT):
|
||||
def sanitize_filename(s, keep_bad_win_chars=False, restricted=False, is_id=NO_DEFAULT):
|
||||
"""Sanitizes a string so it could be used as part of a filename.
|
||||
@param restricted Use a stricter subset of allowed characters
|
||||
@param is_id Whether this is an ID that should be kept unchanged if possible.
|
||||
If unset, yt-dlp's new sanitization rules are in effect
|
||||
@param keep_bad_win_chars Whether to keep characters invalid on Windows
|
||||
@param restricted Use a stricter subset of allowed characters
|
||||
@param is_id Whether this is an ID that should be kept unchanged if possible.
|
||||
If unset, yt-dlp's new sanitization rules are in effect
|
||||
"""
|
||||
if s == '':
|
||||
return ''
|
||||
|
@ -623,16 +624,16 @@ def replace_insane(char):
|
|||
return ACCENT_CHARS[char]
|
||||
elif not restricted and char == '\n':
|
||||
return '\0 '
|
||||
elif is_id is NO_DEFAULT and not restricted and char in '"*:<>?|/\\':
|
||||
elif is_id is NO_DEFAULT and not restricted and char in '"*:<>?|/\\' and not keep_bad_win_chars:
|
||||
# Replace with their full-width unicode counterparts
|
||||
return {'/': '\u29F8', '\\': '\u29f9'}.get(char, chr(ord(char) + 0xfee0))
|
||||
elif char == '?' or ord(char) < 32 or ord(char) == 127:
|
||||
elif (not keep_bad_win_chars and char == '?') or ord(char) < 32 or ord(char) == 127:
|
||||
return ''
|
||||
elif char == '"':
|
||||
elif not keep_bad_win_chars and char == '"':
|
||||
return '' if restricted else '\''
|
||||
elif char == ':':
|
||||
elif not keep_bad_win_chars and char == ':':
|
||||
return '\0_\0-' if restricted else '\0 \0-'
|
||||
elif char in '\\/|*<>':
|
||||
elif (not keep_bad_win_chars and char in '\\|*<>') or char == '/':
|
||||
return '\0_'
|
||||
if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace() or ord(char) > 127):
|
||||
return '' if unicodedata.category(char)[0] in 'CM' else '\0_'
|
||||
|
@ -641,7 +642,8 @@ def replace_insane(char):
|
|||
# Replace look-alike Unicode glyphs
|
||||
if restricted and (is_id is NO_DEFAULT or not is_id):
|
||||
s = unicodedata.normalize('NFKC', s)
|
||||
s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s) # Handle timestamps
|
||||
s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0) if keep_bad_win_chars
|
||||
else m.group(0).replace(':', '_'), s) # Handle timestamps
|
||||
result = ''.join(map(replace_insane, s))
|
||||
if is_id is NO_DEFAULT:
|
||||
result = re.sub(r'(\0.)(?:(?=\1)..)+', r'\1', result) # Remove repeated substitute chars
|
||||
|
|
Loading…
Reference in New Issue
Block a user