mirror of
https://github.com/ytdl-org/youtube-dl
synced 2025-06-21 12:22:41 +09:00
Compare commits
11 Commits
6789a6b1ab
...
53a5e99a2e
Author | SHA1 | Date | |
---|---|---|---|
![]() |
53a5e99a2e | ||
![]() |
2b4fbfce25 | ||
![]() |
1bc45b8b6c | ||
![]() |
b982d77d0b | ||
![]() |
c55dbf4838 | ||
![]() |
087d865230 | ||
![]() |
a4fc1151f1 | ||
![]() |
a464c159e6 | ||
![]() |
7dca08eff0 | ||
![]() |
2239ee7965 | ||
![]() |
dc179db221 |
@ -84,6 +84,21 @@ _SIG_TESTS = [
|
|||||||
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
|
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
_NSIG_TESTS = [
|
_NSIG_TESTS = [
|
||||||
@ -153,7 +168,7 @@ _NSIG_TESTS = [
|
|||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
|
||||||
'-Txvy6bT5R6LqgnQNx', 'dcklJCnRUHbgSg',
|
'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
|
||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
|
||||||
@ -173,7 +188,7 @@ _NSIG_TESTS = [
|
|||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
|
||||||
'qO0NiMtYQ7TeJnfFG2', 'k9cuJDHNS5O7kQ',
|
'aCi3iElgd2kq0bxVbQ', 'QX1y8jGb2IbZ0w',
|
||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
|
||||||
@ -231,10 +246,6 @@ _NSIG_TESTS = [
|
|||||||
'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
|
||||||
'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
|
'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
|
||||||
),
|
),
|
||||||
(
|
|
||||||
'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
|
|
||||||
'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
|
|
||||||
),
|
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
|
||||||
'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
|
'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
|
||||||
@ -259,6 +270,22 @@ _NSIG_TESTS = [
|
|||||||
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
|
'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
|
||||||
|
'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
|
||||||
|
'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
|
||||||
|
'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
|
'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
@ -271,6 +298,8 @@ class TestPlayerInfo(unittest.TestCase):
|
|||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
|
||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
|
||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
|
||||||
|
('https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js', 'e7567ecf'),
|
||||||
|
('https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js', '643afba4'),
|
||||||
# obsolete
|
# obsolete
|
||||||
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
|
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
|
||||||
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
|
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
|
||||||
@ -280,8 +309,9 @@ class TestPlayerInfo(unittest.TestCase):
|
|||||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
|
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
|
||||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
|
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
|
||||||
)
|
)
|
||||||
|
ie = YoutubeIE(FakeYDL({'cachedir': False}))
|
||||||
for player_url, expected_player_id in PLAYER_URLS:
|
for player_url, expected_player_id in PLAYER_URLS:
|
||||||
player_id = YoutubeIE._extract_player_info(player_url)
|
player_id = ie._extract_player_info(player_url)
|
||||||
self.assertEqual(player_id, expected_player_id)
|
self.assertEqual(player_id, expected_player_id)
|
||||||
|
|
||||||
|
|
||||||
@ -301,8 +331,8 @@ class TestSignature(unittest.TestCase):
|
|||||||
def t_factory(name, sig_func, url_pattern):
|
def t_factory(name, sig_func, url_pattern):
|
||||||
def make_tfunc(url, sig_input, expected_sig):
|
def make_tfunc(url, sig_input, expected_sig):
|
||||||
m = url_pattern.match(url)
|
m = url_pattern.match(url)
|
||||||
assert m, '%r should follow URL format' % url
|
assert m, '{0!r} should follow URL format'.format(url)
|
||||||
test_id = m.group('id')
|
test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
|
||||||
|
|
||||||
def test_func(self):
|
def test_func(self):
|
||||||
basename = 'player-{0}-{1}.js'.format(name, test_id)
|
basename = 'player-{0}-{1}.js'.format(name, test_id)
|
||||||
@ -335,12 +365,16 @@ def n_sig(jscode, sig_input):
|
|||||||
|
|
||||||
|
|
||||||
make_sig_test = t_factory(
|
make_sig_test = t_factory(
|
||||||
'signature', signature, re.compile(r'.*(?:-|/player/)(?P<id>[a-zA-Z0-9_-]+)(?:/.+\.js|(?:/watch_as3|/html5player)?\.[a-z]+)$'))
|
'signature', signature,
|
||||||
|
re.compile(r'''(?x)
|
||||||
|
.+/(?P<h5>html5)?player(?(h5)(?:-en_US)?-|/)(?P<id>[a-zA-Z0-9/._-]+)
|
||||||
|
(?(h5)/(?:watch_as3|html5player))?\.js$
|
||||||
|
'''))
|
||||||
for test_spec in _SIG_TESTS:
|
for test_spec in _SIG_TESTS:
|
||||||
make_sig_test(*test_spec)
|
make_sig_test(*test_spec)
|
||||||
|
|
||||||
make_nsig_test = t_factory(
|
make_nsig_test = t_factory(
|
||||||
'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_-]+)/.+.js$'))
|
'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_/.-]+)\.js$'))
|
||||||
for test_spec in _NSIG_TESTS:
|
for test_spec in _NSIG_TESTS:
|
||||||
make_nsig_test(*test_spec)
|
make_nsig_test(*test_spec)
|
||||||
|
|
||||||
|
@ -122,6 +122,7 @@ from .postprocessor import (
|
|||||||
FFmpegFixupM4aPP,
|
FFmpegFixupM4aPP,
|
||||||
FFmpegFixupStretchedPP,
|
FFmpegFixupStretchedPP,
|
||||||
FFmpegMergerPP,
|
FFmpegMergerPP,
|
||||||
|
FFmpegConcatPP,
|
||||||
FFmpegPostProcessor,
|
FFmpegPostProcessor,
|
||||||
get_postprocessor,
|
get_postprocessor,
|
||||||
)
|
)
|
||||||
@ -1206,6 +1207,20 @@ class YoutubeDL(object):
|
|||||||
entry_result = self.__process_iterable_entry(entry, download, extra)
|
entry_result = self.__process_iterable_entry(entry, download, extra)
|
||||||
# TODO: skip failed (empty) entries?
|
# TODO: skip failed (empty) entries?
|
||||||
playlist_results.append(entry_result)
|
playlist_results.append(entry_result)
|
||||||
|
|
||||||
|
if self.params.get('concat_playlist', False):
|
||||||
|
concat_pp = FFmpegConcatPP(self)
|
||||||
|
ie_result['__postprocessors'] = [concat_pp]
|
||||||
|
ie_result['__files_to_concat'] = list(map(lambda e: e['_filename'], entries))
|
||||||
|
|
||||||
|
filename_wo_ext = self.prepare_filename(ie_result)
|
||||||
|
|
||||||
|
# Ensure filename always has a correct extension for successful merge
|
||||||
|
ie_result['ext'] = self.params.get('merge_output_format') or entries[0]['ext']
|
||||||
|
ie_result['_filename'] = filename = '%s.%s' % (filename_wo_ext, ie_result['ext'])
|
||||||
|
|
||||||
|
self.post_process(filename, ie_result)
|
||||||
|
|
||||||
ie_result['entries'] = playlist_results
|
ie_result['entries'] = playlist_results
|
||||||
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
|
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
|
||||||
return ie_result
|
return ie_result
|
||||||
@ -1858,6 +1873,7 @@ class YoutubeDL(object):
|
|||||||
new_info = dict(info_dict)
|
new_info = dict(info_dict)
|
||||||
new_info.update(format)
|
new_info.update(format)
|
||||||
self.process_info(new_info)
|
self.process_info(new_info)
|
||||||
|
format.update(new_info)
|
||||||
# We update the info dict with the best quality format (backwards compatibility)
|
# We update the info dict with the best quality format (backwards compatibility)
|
||||||
info_dict.update(formats_to_download[-1])
|
info_dict.update(formats_to_download[-1])
|
||||||
return info_dict
|
return info_dict
|
||||||
|
@ -411,6 +411,7 @@ def _real_main(argv=None):
|
|||||||
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
|
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
|
||||||
'encoding': opts.encoding,
|
'encoding': opts.encoding,
|
||||||
'extract_flat': opts.extract_flat,
|
'extract_flat': opts.extract_flat,
|
||||||
|
'concat_playlist': opts.concat_playlist,
|
||||||
'mark_watched': opts.mark_watched,
|
'mark_watched': opts.mark_watched,
|
||||||
'merge_output_format': opts.merge_output_format,
|
'merge_output_format': opts.merge_output_format,
|
||||||
'postprocessors': postprocessors,
|
'postprocessors': postprocessors,
|
||||||
|
@ -692,9 +692,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
'invidious': '|'.join(_INVIDIOUS_SITES),
|
'invidious': '|'.join(_INVIDIOUS_SITES),
|
||||||
}
|
}
|
||||||
_PLAYER_INFO_RE = (
|
_PLAYER_INFO_RE = (
|
||||||
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})//(?:tv-)?player',
|
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/(?:tv-)?player',
|
||||||
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
|
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias(?:_tce)?\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
|
||||||
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
|
r'\b(?P<id>vfl[a-zA-Z0-9_-]{6,})\b.*?\.js$',
|
||||||
)
|
)
|
||||||
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
||||||
|
|
||||||
@ -1626,15 +1626,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
""" Return a string representation of a signature """
|
""" Return a string representation of a signature """
|
||||||
return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
|
return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
|
||||||
|
|
||||||
@classmethod
|
def _extract_player_info(self, player_url):
|
||||||
def _extract_player_info(cls, player_url):
|
try:
|
||||||
for player_re in cls._PLAYER_INFO_RE:
|
return self._search_regex(
|
||||||
id_m = re.search(player_re, player_url)
|
self._PLAYER_INFO_RE, player_url, 'player info', group='id')
|
||||||
if id_m:
|
except ExtractorError as e:
|
||||||
break
|
raise ExtractorError(
|
||||||
else:
|
'Cannot identify player %r' % (player_url,), cause=e)
|
||||||
raise ExtractorError('Cannot identify player %r' % player_url)
|
|
||||||
return id_m.group('id')
|
|
||||||
|
|
||||||
def _load_player(self, video_id, player_url, fatal=True, player_id=None):
|
def _load_player(self, video_id, player_url, fatal=True, player_id=None):
|
||||||
if not player_id:
|
if not player_id:
|
||||||
@ -1711,6 +1709,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
' return %s\n') % (signature_id_tuple, expr_code)
|
' return %s\n') % (signature_id_tuple, expr_code)
|
||||||
self.to_screen('Extracted signature function:\n' + code)
|
self.to_screen('Extracted signature function:\n' + code)
|
||||||
|
|
||||||
|
def _extract_sig_fn(self, jsi, funcname):
|
||||||
|
var_ay = self._search_regex(
|
||||||
|
r'''(?x)
|
||||||
|
(?:\*/|\{|\n|^)\s*(?:'[^']+'\s*;\s*)
|
||||||
|
(var\s*[\w$]+\s*=\s*(?:
|
||||||
|
('|")(?:\\\2|(?!\2).)+\2\s*\.\s*split\(\s*('|")\W+\3\s*\)|
|
||||||
|
\[\s*(?:('|")(?:\\\4|(?!\4).)*\4\s*(?:(?=\])|,\s*))+\]
|
||||||
|
))(?=\s*[,;])
|
||||||
|
''', jsi.code, 'useful values', default='')
|
||||||
|
|
||||||
|
sig_fn = jsi.extract_function_code(funcname)
|
||||||
|
|
||||||
|
if var_ay:
|
||||||
|
sig_fn = (sig_fn[0], ';\n'.join((var_ay, sig_fn[1])))
|
||||||
|
|
||||||
|
return sig_fn
|
||||||
|
|
||||||
def _parse_sig_js(self, jscode):
|
def _parse_sig_js(self, jscode):
|
||||||
# Examples where `sig` is funcname:
|
# Examples where `sig` is funcname:
|
||||||
# sig=function(a){a=a.split(""); ... ;return a.join("")};
|
# sig=function(a){a=a.split(""); ... ;return a.join("")};
|
||||||
@ -1736,8 +1751,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
jscode, 'Initial JS player signature function name', group='sig')
|
jscode, 'Initial JS player signature function name', group='sig')
|
||||||
|
|
||||||
jsi = JSInterpreter(jscode)
|
jsi = JSInterpreter(jscode)
|
||||||
initial_function = jsi.extract_function(funcname)
|
|
||||||
return lambda s: initial_function([s])
|
initial_function = self._extract_sig_fn(jsi, funcname)
|
||||||
|
|
||||||
|
func = jsi.extract_function_from_code(*initial_function)
|
||||||
|
|
||||||
|
return lambda s: func([s])
|
||||||
|
|
||||||
def _cached(self, func, *cache_id):
|
def _cached(self, func, *cache_id):
|
||||||
def inner(*args, **kwargs):
|
def inner(*args, **kwargs):
|
||||||
@ -1856,15 +1875,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
|
|
||||||
def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
|
def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
|
||||||
|
|
||||||
var_ay = self._search_regex(
|
|
||||||
r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"(?:\\"|[^"])+"\s*\.\s*split\("\W+"\))(?=\s*[,;])',
|
|
||||||
jsi.code, 'useful values', default='')
|
|
||||||
|
|
||||||
func_name = self._extract_n_function_name(jsi.code)
|
func_name = self._extract_n_function_name(jsi.code)
|
||||||
|
|
||||||
func_code = jsi.extract_function_code(func_name)
|
func_code = self._extract_sig_fn(jsi, func_name)
|
||||||
if var_ay:
|
|
||||||
func_code = (func_code[0], ';\n'.join((var_ay, func_code[1])))
|
|
||||||
|
|
||||||
if player_id:
|
if player_id:
|
||||||
self.cache.store('youtube-nsig', player_id, func_code)
|
self.cache.store('youtube-nsig', player_id, func_code)
|
||||||
@ -2136,7 +2149,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
video_details = merge_dicts(*traverse_obj(
|
video_details = merge_dicts(*traverse_obj(
|
||||||
(player_response, api_player_response),
|
(player_response, api_player_response),
|
||||||
(Ellipsis, 'videoDetails', T(dict))))
|
(Ellipsis, 'videoDetails', T(dict))))
|
||||||
player_response.update(api_player_response or {})
|
player_response.update(filter_dict(
|
||||||
|
api_player_response or {}, cndn=lambda k, _: k != 'captions'))
|
||||||
player_response['videoDetails'] = video_details
|
player_response['videoDetails'] = video_details
|
||||||
|
|
||||||
def is_agegated(playability):
|
def is_agegated(playability):
|
||||||
@ -2566,8 +2580,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
}
|
}
|
||||||
|
|
||||||
pctr = traverse_obj(
|
pctr = traverse_obj(
|
||||||
player_response,
|
(player_response, api_player_response),
|
||||||
('captions', 'playerCaptionsTracklistRenderer', T(dict)))
|
(Ellipsis, 'captions', 'playerCaptionsTracklistRenderer', T(dict)))
|
||||||
if pctr:
|
if pctr:
|
||||||
def process_language(container, base_url, lang_code, query):
|
def process_language(container, base_url, lang_code, query):
|
||||||
lang_subs = []
|
lang_subs = []
|
||||||
@ -2584,20 +2598,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
def process_subtitles():
|
def process_subtitles():
|
||||||
subtitles = {}
|
subtitles = {}
|
||||||
for caption_track in traverse_obj(pctr, (
|
for caption_track in traverse_obj(pctr, (
|
||||||
'captionTracks', lambda _, v: v.get('baseUrl'))):
|
Ellipsis, 'captionTracks', lambda _, v: (
|
||||||
|
v.get('baseUrl') and v.get('languageCode')))):
|
||||||
base_url = self._yt_urljoin(caption_track['baseUrl'])
|
base_url = self._yt_urljoin(caption_track['baseUrl'])
|
||||||
if not base_url:
|
if not base_url:
|
||||||
continue
|
continue
|
||||||
|
lang_code = caption_track['languageCode']
|
||||||
if caption_track.get('kind') != 'asr':
|
if caption_track.get('kind') != 'asr':
|
||||||
lang_code = caption_track.get('languageCode')
|
|
||||||
if not lang_code:
|
|
||||||
continue
|
|
||||||
process_language(
|
process_language(
|
||||||
subtitles, base_url, lang_code, {})
|
subtitles, base_url, lang_code, {})
|
||||||
continue
|
continue
|
||||||
automatic_captions = {}
|
automatic_captions = {}
|
||||||
|
process_language(
|
||||||
|
automatic_captions, base_url, lang_code, {})
|
||||||
for translation_language in traverse_obj(pctr, (
|
for translation_language in traverse_obj(pctr, (
|
||||||
'translationLanguages', lambda _, v: v.get('languageCode'))):
|
Ellipsis, 'translationLanguages', lambda _, v: v.get('languageCode'))):
|
||||||
translation_language_code = translation_language['languageCode']
|
translation_language_code = translation_language['languageCode']
|
||||||
process_language(
|
process_language(
|
||||||
automatic_captions, base_url, translation_language_code,
|
automatic_captions, base_url, translation_language_code,
|
||||||
|
@ -678,7 +678,7 @@ class JSInterpreter(object):
|
|||||||
return len(obj)
|
return len(obj)
|
||||||
try:
|
try:
|
||||||
return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
|
return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
|
||||||
except (TypeError, KeyError, IndexError) as e:
|
except (TypeError, KeyError, IndexError, ValueError) as e:
|
||||||
# allow_undefined is None gives correct behaviour
|
# allow_undefined is None gives correct behaviour
|
||||||
if allow_undefined or (
|
if allow_undefined or (
|
||||||
allow_undefined is None and not isinstance(e, TypeError)):
|
allow_undefined is None and not isinstance(e, TypeError)):
|
||||||
@ -1038,6 +1038,10 @@ class JSInterpreter(object):
|
|||||||
left_val = self._index(left_val, idx)
|
left_val = self._index(left_val, idx)
|
||||||
if isinstance(idx, float):
|
if isinstance(idx, float):
|
||||||
idx = int(idx)
|
idx = int(idx)
|
||||||
|
if isinstance(left_val, list) and len(left_val) <= int_or_none(idx, default=-1):
|
||||||
|
# JS Array is a sparsely assignable list
|
||||||
|
# TODO: handle extreme sparsity without memory bloat, eg using auxiliary dict
|
||||||
|
left_val.extend((idx - len(left_val) + 1) * [JS_Undefined])
|
||||||
left_val[idx] = self._operator(
|
left_val[idx] = self._operator(
|
||||||
m.group('op'), self._index(left_val, idx) if m.group('op') else None,
|
m.group('op'), self._index(left_val, idx) if m.group('op') else None,
|
||||||
m.group('expr'), expr, local_vars, allow_recursion)
|
m.group('expr'), expr, local_vars, allow_recursion)
|
||||||
@ -1204,9 +1208,10 @@ class JSInterpreter(object):
|
|||||||
elif member == 'join':
|
elif member == 'join':
|
||||||
assertion(isinstance(obj, list), 'must be applied on a list')
|
assertion(isinstance(obj, list), 'must be applied on a list')
|
||||||
assertion(len(argvals) <= 1, 'takes at most one argument')
|
assertion(len(argvals) <= 1, 'takes at most one argument')
|
||||||
return (',' if len(argvals) == 0 else argvals[0]).join(
|
return (',' if len(argvals) == 0 or argvals[0] in (None, JS_Undefined)
|
||||||
('' if x in (None, JS_Undefined) else _js_toString(x))
|
else argvals[0]).join(
|
||||||
for x in obj)
|
('' if x in (None, JS_Undefined) else _js_toString(x))
|
||||||
|
for x in obj)
|
||||||
elif member == 'reverse':
|
elif member == 'reverse':
|
||||||
assertion(not argvals, 'does not take any arguments')
|
assertion(not argvals, 'does not take any arguments')
|
||||||
obj.reverse()
|
obj.reverse()
|
||||||
@ -1364,19 +1369,21 @@ class JSInterpreter(object):
|
|||||||
code, _ = self._separate_at_paren(func_m.group('code')) # refine the match
|
code, _ = self._separate_at_paren(func_m.group('code')) # refine the match
|
||||||
return self.build_arglist(func_m.group('args')), code
|
return self.build_arglist(func_m.group('args')), code
|
||||||
|
|
||||||
def extract_function(self, funcname):
|
def extract_function(self, funcname, *global_stack):
|
||||||
return function_with_repr(
|
return function_with_repr(
|
||||||
self.extract_function_from_code(*self.extract_function_code(funcname)),
|
self.extract_function_from_code(*itertools.chain(
|
||||||
|
self.extract_function_code(funcname), global_stack)),
|
||||||
'F<%s>' % (funcname,))
|
'F<%s>' % (funcname,))
|
||||||
|
|
||||||
def extract_function_from_code(self, argnames, code, *global_stack):
|
def extract_function_from_code(self, argnames, code, *global_stack):
|
||||||
local_vars = {}
|
local_vars = {}
|
||||||
|
|
||||||
|
start = None
|
||||||
while True:
|
while True:
|
||||||
mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code)
|
mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code[start:])
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
break
|
break
|
||||||
start, body_start = mobj.span()
|
start, body_start = ((start or 0) + x for x in mobj.span())
|
||||||
body, remaining = self._separate_at_paren(code[body_start - 1:])
|
body, remaining = self._separate_at_paren(code[body_start - 1:])
|
||||||
name = self._named_object(local_vars, self.extract_function_from_code(
|
name = self._named_object(local_vars, self.extract_function_from_code(
|
||||||
[x.strip() for x in mobj.group('args').split(',')],
|
[x.strip() for x in mobj.group('args').split(',')],
|
||||||
|
@ -183,6 +183,11 @@ def parseOpts(overrideArguments=None):
|
|||||||
action='store_const', dest='extract_flat', const='in_playlist',
|
action='store_const', dest='extract_flat', const='in_playlist',
|
||||||
default=False,
|
default=False,
|
||||||
help='Do not extract the videos of a playlist, only list them.')
|
help='Do not extract the videos of a playlist, only list them.')
|
||||||
|
general.add_option(
|
||||||
|
'--concat-playlist',
|
||||||
|
action='store_true', dest='concat_playlist', default=False,
|
||||||
|
help='Concatenate all videos in a playlist into a single video file. Useful for services which split up full '
|
||||||
|
'episodes into multiple segments.')
|
||||||
general.add_option(
|
general.add_option(
|
||||||
'--mark-watched',
|
'--mark-watched',
|
||||||
action='store_true', dest='mark_watched', default=False,
|
action='store_true', dest='mark_watched', default=False,
|
||||||
|
@ -9,6 +9,7 @@ from .ffmpeg import (
|
|||||||
FFmpegFixupM3u8PP,
|
FFmpegFixupM3u8PP,
|
||||||
FFmpegFixupM4aPP,
|
FFmpegFixupM4aPP,
|
||||||
FFmpegMergerPP,
|
FFmpegMergerPP,
|
||||||
|
FFmpegConcatPP,
|
||||||
FFmpegMetadataPP,
|
FFmpegMetadataPP,
|
||||||
FFmpegVideoConvertorPP,
|
FFmpegVideoConvertorPP,
|
||||||
FFmpegSubtitlesConvertorPP,
|
FFmpegSubtitlesConvertorPP,
|
||||||
@ -31,6 +32,7 @@ __all__ = [
|
|||||||
'FFmpegFixupM4aPP',
|
'FFmpegFixupM4aPP',
|
||||||
'FFmpegFixupStretchedPP',
|
'FFmpegFixupStretchedPP',
|
||||||
'FFmpegMergerPP',
|
'FFmpegMergerPP',
|
||||||
|
'FFmpegConcatPP',
|
||||||
'FFmpegMetadataPP',
|
'FFmpegMetadataPP',
|
||||||
'FFmpegPostProcessor',
|
'FFmpegPostProcessor',
|
||||||
'FFmpegSubtitlesConvertorPP',
|
'FFmpegSubtitlesConvertorPP',
|
||||||
|
@ -84,7 +84,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
|
|||||||
|
|
||||||
self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
|
self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
|
||||||
|
|
||||||
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
|
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options, [])
|
||||||
|
|
||||||
if not self._already_have_thumbnail:
|
if not self._already_have_thumbnail:
|
||||||
os.remove(encodeFilename(thumbnail_filename))
|
os.remove(encodeFilename(thumbnail_filename))
|
||||||
|
@ -5,7 +5,6 @@ import subprocess
|
|||||||
import time
|
import time
|
||||||
import re
|
import re
|
||||||
|
|
||||||
|
|
||||||
from .common import AudioConversionError, PostProcessor
|
from .common import AudioConversionError, PostProcessor
|
||||||
|
|
||||||
from ..compat import compat_open as open
|
from ..compat import compat_open as open
|
||||||
@ -24,7 +23,6 @@ from ..utils import (
|
|||||||
replace_extension,
|
replace_extension,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
EXT_TO_OUT_FORMATS = {
|
EXT_TO_OUT_FORMATS = {
|
||||||
'aac': 'adts',
|
'aac': 'adts',
|
||||||
'flac': 'flac',
|
'flac': 'flac',
|
||||||
@ -196,7 +194,7 @@ class FFmpegPostProcessor(PostProcessor):
|
|||||||
return mobj.group(1)
|
return mobj.group(1)
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
|
def run_ffmpeg_multiple_files(self, input_paths, out_path, opts, file_opts):
|
||||||
self.check_version()
|
self.check_version()
|
||||||
|
|
||||||
oldest_mtime = min(
|
oldest_mtime = min(
|
||||||
@ -207,6 +205,7 @@ class FFmpegPostProcessor(PostProcessor):
|
|||||||
files_cmd = []
|
files_cmd = []
|
||||||
for path in input_paths:
|
for path in input_paths:
|
||||||
files_cmd.extend([
|
files_cmd.extend([
|
||||||
|
*file_opts,
|
||||||
encodeArgument('-i'),
|
encodeArgument('-i'),
|
||||||
encodeFilename(self._ffmpeg_filename_argument(path), True)
|
encodeFilename(self._ffmpeg_filename_argument(path), True)
|
||||||
])
|
])
|
||||||
@ -231,8 +230,8 @@ class FFmpegPostProcessor(PostProcessor):
|
|||||||
raise FFmpegPostProcessorError(msg)
|
raise FFmpegPostProcessorError(msg)
|
||||||
self.try_utime(out_path, oldest_mtime, oldest_mtime)
|
self.try_utime(out_path, oldest_mtime, oldest_mtime)
|
||||||
|
|
||||||
def run_ffmpeg(self, path, out_path, opts):
|
def run_ffmpeg(self, path, out_path, opts, file_opts):
|
||||||
self.run_ffmpeg_multiple_files([path], out_path, opts)
|
self.run_ffmpeg_multiple_files([path], out_path, opts, file_opts)
|
||||||
|
|
||||||
def _ffmpeg_filename_argument(self, fn):
|
def _ffmpeg_filename_argument(self, fn):
|
||||||
# Always use 'file:' because the filename may contain ':' (ffmpeg
|
# Always use 'file:' because the filename may contain ':' (ffmpeg
|
||||||
@ -270,7 +269,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
|||||||
raise PostProcessingError('WARNING: unable to obtain file audio codec with ffprobe')
|
raise PostProcessingError('WARNING: unable to obtain file audio codec with ffprobe')
|
||||||
|
|
||||||
more_opts = []
|
more_opts = []
|
||||||
if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
|
if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (
|
||||||
|
self._preferredcodec == 'm4a' and filecodec == 'aac'):
|
||||||
if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
|
if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:
|
||||||
# Lossless, but in another container
|
# Lossless, but in another container
|
||||||
acodec = 'copy'
|
acodec = 'copy'
|
||||||
@ -315,7 +315,8 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
|||||||
extension = 'wav'
|
extension = 'wav'
|
||||||
more_opts += ['-f', 'wav']
|
more_opts += ['-f', 'wav']
|
||||||
|
|
||||||
prefix, sep, ext = path.rpartition('.') # not os.path.splitext, since the latter does not work on unicode in all setups
|
prefix, sep, ext = path.rpartition(
|
||||||
|
'.') # not os.path.splitext, since the latter does not work on unicode in all setups
|
||||||
new_path = prefix + sep + extension
|
new_path = prefix + sep + extension
|
||||||
|
|
||||||
information['filepath'] = new_path
|
information['filepath'] = new_path
|
||||||
@ -353,14 +354,16 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
|
|||||||
def run(self, information):
|
def run(self, information):
|
||||||
path = information['filepath']
|
path = information['filepath']
|
||||||
if information['ext'] == self._preferedformat:
|
if information['ext'] == self._preferedformat:
|
||||||
self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
|
self._downloader.to_screen(
|
||||||
|
'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
|
||||||
return [], information
|
return [], information
|
||||||
options = []
|
options = []
|
||||||
if self._preferedformat == 'avi':
|
if self._preferedformat == 'avi':
|
||||||
options.extend(['-c:v', 'libxvid', '-vtag', 'XVID'])
|
options.extend(['-c:v', 'libxvid', '-vtag', 'XVID'])
|
||||||
prefix, sep, ext = path.rpartition('.')
|
prefix, sep, ext = path.rpartition('.')
|
||||||
outpath = prefix + sep + self._preferedformat
|
outpath = prefix + sep + self._preferedformat
|
||||||
self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
|
self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (
|
||||||
|
information['ext'], self._preferedformat) + outpath)
|
||||||
self.run_ffmpeg(path, outpath, options)
|
self.run_ffmpeg(path, outpath, options)
|
||||||
information['filepath'] = outpath
|
information['filepath'] = outpath
|
||||||
information['format'] = self._preferedformat
|
information['format'] = self._preferedformat
|
||||||
@ -419,7 +422,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
|
|||||||
|
|
||||||
temp_filename = prepend_extension(filename, 'temp')
|
temp_filename = prepend_extension(filename, 'temp')
|
||||||
self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename)
|
self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename)
|
||||||
self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
|
self.run_ffmpeg_multiple_files(input_files, temp_filename, opts, [])
|
||||||
os.remove(encodeFilename(filename))
|
os.remove(encodeFilename(filename))
|
||||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||||
|
|
||||||
@ -502,7 +505,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
|
|||||||
options.extend(['-map_metadata', '1'])
|
options.extend(['-map_metadata', '1'])
|
||||||
|
|
||||||
self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
|
self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
|
||||||
self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
|
self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options, [])
|
||||||
if chapters:
|
if chapters:
|
||||||
os.remove(metadata_filename)
|
os.remove(metadata_filename)
|
||||||
os.remove(encodeFilename(filename))
|
os.remove(encodeFilename(filename))
|
||||||
@ -516,7 +519,7 @@ class FFmpegMergerPP(FFmpegPostProcessor):
|
|||||||
temp_filename = prepend_extension(filename, 'temp')
|
temp_filename = prepend_extension(filename, 'temp')
|
||||||
args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0']
|
args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0']
|
||||||
self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename)
|
self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename)
|
||||||
self.run_ffmpeg_multiple_files(info['__files_to_merge'], temp_filename, args)
|
self.run_ffmpeg_multiple_files(info['__files_to_merge'], temp_filename, args, [])
|
||||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||||
return info['__files_to_merge'], info
|
return info['__files_to_merge'], info
|
||||||
|
|
||||||
@ -538,6 +541,29 @@ class FFmpegMergerPP(FFmpegPostProcessor):
|
|||||||
return True
|
return True
|
||||||
|
|
||||||
|
|
||||||
|
class FFmpegConcatPP(FFmpegPostProcessor):
|
||||||
|
def run(self, info):
|
||||||
|
filename = info['filepath']
|
||||||
|
|
||||||
|
list_filename = prepend_extension(filename, 'list')
|
||||||
|
temp_filename = prepend_extension(filename, 'temp')
|
||||||
|
|
||||||
|
with open(list_filename, 'wt') as f:
|
||||||
|
f.write('ffconcat version 1.0\n')
|
||||||
|
for file in info['__files_to_concat']:
|
||||||
|
f.write("file '%s'\n" % self._ffmpeg_filename_argument(file))
|
||||||
|
|
||||||
|
file_opts = ['-f', 'concat', '-safe', '0']
|
||||||
|
opts = ['-c', 'copy']
|
||||||
|
self._downloader.to_screen('[ffmpeg] Concatenating files into "%s"' % filename)
|
||||||
|
self.run_ffmpeg(list_filename, temp_filename, opts, file_opts)
|
||||||
|
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||||
|
return info['__files_to_concat'], info
|
||||||
|
|
||||||
|
def can_merge(self):
|
||||||
|
return True
|
||||||
|
|
||||||
|
|
||||||
class FFmpegFixupStretchedPP(FFmpegPostProcessor):
|
class FFmpegFixupStretchedPP(FFmpegPostProcessor):
|
||||||
def run(self, info):
|
def run(self, info):
|
||||||
stretched_ratio = info.get('stretched_ratio')
|
stretched_ratio = info.get('stretched_ratio')
|
||||||
@ -583,7 +609,7 @@ class FFmpegFixupM3u8PP(FFmpegPostProcessor):
|
|||||||
|
|
||||||
options = ['-c', 'copy', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
|
options = ['-c', 'copy', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
|
||||||
self._downloader.to_screen('[ffmpeg] Fixing malformed AAC bitstream in "%s"' % filename)
|
self._downloader.to_screen('[ffmpeg] Fixing malformed AAC bitstream in "%s"' % filename)
|
||||||
self.run_ffmpeg(filename, temp_filename, options)
|
self.run_ffmpeg(filename, temp_filename, options, [])
|
||||||
|
|
||||||
os.remove(encodeFilename(filename))
|
os.remove(encodeFilename(filename))
|
||||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||||
|
Loading…
x
Reference in New Issue
Block a user