mirror of
https://github.com/ytdl-org/youtube-dl
synced 2025-01-27 13:50:11 +09:00
Compare commits
5 Commits
05629006f1
...
fde34402da
Author | SHA1 | Date | |
---|---|---|---|
|
fde34402da | ||
|
c5098961b0 | ||
|
dbc08fba83 | ||
|
71223bff39 | ||
|
4ba9065654 |
@ -425,6 +425,34 @@ class TestJSInterpreter(unittest.TestCase):
|
|||||||
self._test(jsi, [''], args=['', '-'])
|
self._test(jsi, [''], args=['', '-'])
|
||||||
self._test(jsi, [], args=['', ''])
|
self._test(jsi, [], args=['', ''])
|
||||||
|
|
||||||
|
def test_slice(self):
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
|
||||||
|
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
|
||||||
|
self._test('function f(){return "012345678".slice()}', '012345678')
|
||||||
|
self._test('function f(){return "012345678".slice(0)}', '012345678')
|
||||||
|
self._test('function f(){return "012345678".slice(5)}', '5678')
|
||||||
|
self._test('function f(){return "012345678".slice(99)}', '')
|
||||||
|
self._test('function f(){return "012345678".slice(-2)}', '78')
|
||||||
|
self._test('function f(){return "012345678".slice(-99)}', '012345678')
|
||||||
|
self._test('function f(){return "012345678".slice(0, 0)}', '')
|
||||||
|
self._test('function f(){return "012345678".slice(1, 0)}', '')
|
||||||
|
self._test('function f(){return "012345678".slice(0, 1)}', '0')
|
||||||
|
self._test('function f(){return "012345678".slice(3, 6)}', '345')
|
||||||
|
self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
|
||||||
|
self._test('function f(){return "012345678".slice(-1, 1)}', '')
|
||||||
|
self._test('function f(){return "012345678".slice(-3, -1)}', '67')
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
@ -174,6 +174,14 @@ _NSIG_TESTS = [
|
|||||||
'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
|
||||||
'7X-he4jjvMx7BCX', 'sViSydX8IHtdWA',
|
'7X-he4jjvMx7BCX', 'sViSydX8IHtdWA',
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
|
||||||
|
'-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
|
||||||
|
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
@ -20,10 +20,9 @@ class AlphaPornoIE(InfoExtractor):
|
|||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Sensual striptease porn with Samantha Alexandra',
|
'title': 'Sensual striptease porn with Samantha Alexandra',
|
||||||
'thumbnail': r're:https?://.*\.jpg$',
|
'thumbnail': r're:https?://.*\.jpg$',
|
||||||
'timestamp': 1418694611,
|
'timestamp': 1418701811,
|
||||||
'upload_date': '20141216',
|
'upload_date': '20141216',
|
||||||
'duration': 387,
|
'duration': 387,
|
||||||
'filesize_approx': 54120000,
|
|
||||||
'tbr': 1145,
|
'tbr': 1145,
|
||||||
'categories': list,
|
'categories': list,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
@ -36,42 +35,53 @@ class AlphaPornoIE(InfoExtractor):
|
|||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
video_id = self._search_regex(
|
video_id = self._search_regex(
|
||||||
r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
|
[r"video_id\s*:\s*'([^']+)'", r"\['video_id'\]\s*=\s*(.+?);"], webpage, 'video id')
|
||||||
|
|
||||||
|
entries = self._parse_html5_media_entries('https://alphaporno.com', webpage, video_id)
|
||||||
|
info = {}
|
||||||
|
if len(entries) > 0:
|
||||||
|
info = entries[0]
|
||||||
|
for fmt in info['formats']:
|
||||||
|
fmt['tbr'] = int_or_none(self._search_regex(r"br=(\d+)", fmt['url'], 'bitrate', default=None))
|
||||||
|
else:
|
||||||
video_url = self._search_regex(
|
video_url = self._search_regex(
|
||||||
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
|
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
|
||||||
ext = self._html_search_meta(
|
ext = self._html_search_meta(
|
||||||
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
|
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
|
||||||
|
bitrate = int_or_none(self._html_search_meta(
|
||||||
|
'bitrate', webpage, 'bitrate', default=None))
|
||||||
|
info = {
|
||||||
|
'url': video_url,
|
||||||
|
'ext': ext,
|
||||||
|
'tbr': bitrate,
|
||||||
|
}
|
||||||
|
|
||||||
title = self._search_regex(
|
title = self._search_regex(
|
||||||
[r'<meta content="([^"]+)" itemprop="description">',
|
[r'<meta content="([^"]+)" itemprop="description">',
|
||||||
r'class="title" itemprop="name">([^<]+)<'],
|
r'class="title" itemprop="name">([^<]+)<',
|
||||||
|
r'<h1>(.*?)</h1>'],
|
||||||
webpage, 'title')
|
webpage, 'title')
|
||||||
thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
|
thumbnail = self._html_search_meta(['og:image', 'thumbnail'], webpage, 'thumbnail')
|
||||||
timestamp = parse_iso8601(self._html_search_meta(
|
timestamp = parse_iso8601(self._og_search_property('video:release_date', webpage, 'upload date', fatal=False),
|
||||||
'uploadDate', webpage, 'upload date'))
|
delimiter=' ') or parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
|
||||||
duration = parse_duration(self._html_search_meta(
|
duration = parse_duration(self._html_search_meta(
|
||||||
'duration', webpage, 'duration'))
|
['duration', 'og:video:duration'], webpage, 'duration'))
|
||||||
filesize_approx = parse_filesize(self._html_search_meta(
|
filesize_approx = parse_filesize(self._html_search_meta(
|
||||||
'contentSize', webpage, 'file size'))
|
'contentSize', webpage, 'file size', default=None))
|
||||||
bitrate = int_or_none(self._html_search_meta(
|
|
||||||
'bitrate', webpage, 'bitrate'))
|
|
||||||
categories = self._html_search_meta(
|
categories = self._html_search_meta(
|
||||||
'keywords', webpage, 'categories', default='').split(',')
|
'keywords', webpage, 'categories', default='').split(',')
|
||||||
|
|
||||||
age_limit = self._rta_search(webpage)
|
age_limit = self._rta_search(webpage)
|
||||||
|
|
||||||
return {
|
info.update({
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'url': video_url,
|
|
||||||
'ext': ext,
|
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'timestamp': timestamp,
|
'timestamp': timestamp,
|
||||||
'duration': duration,
|
'duration': duration,
|
||||||
'filesize_approx': filesize_approx,
|
'filesize_approx': filesize_approx,
|
||||||
'tbr': bitrate,
|
|
||||||
'categories': categories,
|
'categories': categories,
|
||||||
'age_limit': age_limit,
|
'age_limit': age_limit,
|
||||||
}
|
})
|
||||||
|
return info
|
||||||
|
@ -1659,17 +1659,46 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
def _extract_n_function_name(self, jscode):
|
def _extract_n_function_name(self, jscode):
|
||||||
func_name, idx = self._search_regex(
|
func_name, idx = self._search_regex(
|
||||||
# new: (b=String.fromCharCode(110),c=a.get(b))&&c=nfunc[idx](c)
|
# new: (b=String.fromCharCode(110),c=a.get(b))&&c=nfunc[idx](c)
|
||||||
# or: (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)s
|
# or: (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)
|
||||||
# old: .get("n"))&&(b=nfunc[idx](b)
|
# or: (PL(a),b=a.j.n||null)&&(b=nfunc[idx](b)
|
||||||
# older: .get("n"))&&(b=nfunc(b)
|
# or: (b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
|
||||||
|
# old: (b=a.get("n"))&&(b=nfunc[idx](b)(?P<c>[a-z])\s*=\s*[a-z]\s*
|
||||||
|
# older: (b=a.get("n"))&&(b=nfunc(b)
|
||||||
r'''(?x)
|
r'''(?x)
|
||||||
(?:\(\s*(?P<b>[a-z])\s*=\s*(?:
|
\((?:[\w$()\s]+,)*?\s* # (
|
||||||
|
(?P<b>[a-z])\s*=\s* # b=
|
||||||
|
(?:
|
||||||
|
(?: # expect ,c=a.get(b) (etc)
|
||||||
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
|
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
|
||||||
"n+"\[\s*\+?s*[\w$.]+\s*]
|
"n+"\[\s*\+?s*[\w$.]+\s*]
|
||||||
)\s*,(?P<c>[a-z])\s*=\s*[a-z]\s*)?
|
)\s*(?:,[\w$()\s]+(?=,))*|
|
||||||
\.\s*get\s*\(\s*(?(b)(?P=b)|"n{1,2}")(?:\s*\)){2}\s*&&\s*\(\s*(?(c)(?P=c)|b)\s*=\s*
|
(?P<old>[\w$]+) # a (old[er])
|
||||||
|
)\s*
|
||||||
|
(?(old)
|
||||||
|
# b.get("n")
|
||||||
|
(?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
|
||||||
|
(?:\.\s*n|\[\s*"n"\s*]|\.\s*get\s*\(\s*"n"\s*\))
|
||||||
|
| # ,c=a.get(b)
|
||||||
|
,\s*(?P<c>[a-z])\s*=\s*[a-z]\s*
|
||||||
|
(?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
|
||||||
|
(?:\[\s*(?P=b)\s*]|\.\s*get\s*\(\s*(?P=b)\s*\))
|
||||||
|
)
|
||||||
|
# interstitial junk
|
||||||
|
\s*(?:\|\|\s*null\s*)?(?:\)\s*)?&&\s*(?:\(\s*)?
|
||||||
|
(?(c)(?P=c)|(?P=b))\s*=\s* # [c|b]=
|
||||||
|
# nfunc|nfunc[idx]
|
||||||
(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\)
|
(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\)
|
||||||
''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
|
''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx'),
|
||||||
|
default=(None, None))
|
||||||
|
# thx bashonly: yt-dlp/yt-dlp/pull/10611
|
||||||
|
if not func_name:
|
||||||
|
self.report_warning('Falling back to generic n function search')
|
||||||
|
return self._search_regex(
|
||||||
|
r'''(?xs)
|
||||||
|
(?:(?<=[^\w$])|^) # instead of \b, which ignores $
|
||||||
|
(?P<name>(?!\d)[a-zA-Z\d_$]+)\s*=\s*function\((?!\d)[a-zA-Z\d_$]+\)
|
||||||
|
\s*\{(?:(?!};).)+?["']enhanced_except_
|
||||||
|
''', jscode, 'Initial JS player n function name', group='name')
|
||||||
if not idx:
|
if not idx:
|
||||||
return func_name
|
return func_name
|
||||||
|
|
||||||
|
@ -925,9 +925,16 @@ class JSInterpreter(object):
|
|||||||
obj.reverse()
|
obj.reverse()
|
||||||
return obj
|
return obj
|
||||||
elif member == 'slice':
|
elif member == 'slice':
|
||||||
assertion(isinstance(obj, list), 'must be applied on a list')
|
assertion(isinstance(obj, (list, compat_str)), 'must be applied on a list or string')
|
||||||
assertion(len(argvals) == 1, 'takes exactly one argument')
|
# From [1]:
|
||||||
return obj[argvals[0]:]
|
# .slice() - like [:]
|
||||||
|
# .slice(n) - like [n:] (not [slice(n)]
|
||||||
|
# .slice(m, n) - like [m:n] or [slice(m, n)]
|
||||||
|
# [1] https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/slice
|
||||||
|
assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments')
|
||||||
|
if len(argvals) < 2:
|
||||||
|
argvals += (None,)
|
||||||
|
return obj[slice(*argvals)]
|
||||||
elif member == 'splice':
|
elif member == 'splice':
|
||||||
assertion(isinstance(obj, list), 'must be applied on a list')
|
assertion(isinstance(obj, list), 'must be applied on a list')
|
||||||
assertion(argvals, 'takes one or more arguments')
|
assertion(argvals, 'takes one or more arguments')
|
||||||
|
Loading…
Reference in New Issue
Block a user