Compare commits

...

5 Commits

Author SHA1 Message Date
Petr Tesarik
890a635f89
Merge fe02a15b1c into c5098961b0 2024-08-21 22:32:49 -04:00
dirkf
c5098961b0 [Youtube] Rework n function extraction pattern
Now also succeeds with player b12cc44b
2024-08-06 20:59:09 +01:00
dirkf
dbc08fba83 [jsinterp] Improve slice implementation for player b12cc44b
Partly taken from yt-dlp/yt-dlp#10664, thx seproDev
        Fixes #32896
2024-08-06 20:51:38 +01:00
Aiur Adept
71223bff39
[Youtube] Fix nsig extraction for player 20dfca59 (#32891)
* dirkf's patch for nsig extraction
* add generic search per  yt-dlp/yt-dlp/pull/10611 - thx bashonly

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2024-08-01 19:18:34 +01:00
Petr Tesarik
fe02a15b1c Add extractor for www.mujrozhlas.cz
Signed-off-by: Petr Tesarik <petr@tesarici.cz>
2023-02-05 17:04:02 +01:00
6 changed files with 181 additions and 13 deletions

View File

@ -425,6 +425,34 @@ class TestJSInterpreter(unittest.TestCase):
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__':
unittest.main()

View File

@ -174,6 +174,14 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
'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',
),
]

View File

@ -736,6 +736,7 @@ from .mtv import (
MTVJapanIE,
)
from .muenchentv import MuenchenTVIE
from .mujrozhlas import MujRozhlasIE
from .mwave import MwaveIE, MwaveMeetGreetIE
from .mychannels import MyChannelsIE
from .myspace import MySpaceIE, MySpaceAlbumIE

View File

@ -0,0 +1,95 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
ExtractorError,
js_to_json,
)
class MujRozhlasIE(InfoExtractor):
IE_NAME = 'mujRozhlas'
IE_DESC = 'https://www.mujrozhlas.cz/'
_VALID_URL = r'https?://www\.mujrozhlas\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [
{
'url': 'https://www.mujrozhlas.cz/vinohradska-12/zadne-dalsi-pusy-konec-prchala-spol-muze-znamenat-babisuv-odchod-z-politiky-tipuje',
'md5': '34ecaa47f64079a63d6b80498c280e9d',
'info_dict': {
'id': '0c54ba72-93dd-3a29-b567-910d3d8c71a8',
'ext': 'mp3',
'title': 'Žádné další pusy. Konec Prchala a spol. může znamenat Babišův odchod z politiky, tipuje politolog',
'description': 'md5:ec0610bdb1f591061dbd224d2dd9c19e',
},
},
{
'url': 'https://www.mujrozhlas.cz/kazki/princi-ta-zliy-drakon',
'md5': 'cbad6f68db6dc4d6d798d69b5d258aa5',
'info_dict': {
'id': 'ec5f53b2-3910-448e-8e7f-d6d1a19f4926',
'ext': 'm4a',
'title': 'Принці та злий дракон',
'description': 'md5:b21701e09c2b509c4451194af7ac271b',
},
'params': {
'format': 'hls-128',
},
},
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_data = self._search_regex(
r'\bvar dl = ({[^\n]+});',
webpage, 'player data', default=None)
if not player_data:
raise ExtractorError('Could not find player data')
player_data = self._parse_json(player_data, display_id, js_to_json)
audio_id = player_data['contentId']
bundle = player_data['siteEntityBundle']
if bundle not in ('episode', 'serialPart'):
raise ExtractorError('Unsupported entity: {0}'.format(bundle))
url = 'https://api.mujrozhlas.cz/episodes/{0}'.format(player_data['contentId'])
webpage = self._download_webpage(url, audio_id)
attr = self._parse_json(webpage, audio_id)['data']['attributes']
formats = []
for link in attr['audioLinks']:
variant = link['variant']
if variant == 'hls':
formats.extend(self._extract_m3u8_formats(
link['url'], audio_id, 'm4a', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif variant == 'dash':
formats.extend(self._extract_mpd_formats(
link['url'], audio_id, mpd_id='dash', fatal=False))
elif variant == 'mp3':
url = link['url']
m = re.search(
r'(?P<proto>[^:]+):(?:.*/)*(?P<id>[^.]+)\.(?P<ext>[^/.]+)$',
url)
bitrate = link['bitrate']
formats.append({
'url': link['url'],
'protocol': m.group('proto'),
'ext': m.group('ext'),
'format_id': '-'.join(('mp3', str(bitrate))),
'vcodec': 'none',
'abr': bitrate,
'tbr': bitrate,
})
self._sort_formats(formats)
return {
'id': audio_id,
'title': attr['title'],
'description': clean_html(attr['description']),
'formats': formats,
}

View File

@ -1659,17 +1659,46 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_n_function_name(self, jscode):
func_name, idx = self._search_regex(
# 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
# old: .get("n"))&&(b=nfunc[idx](b)
# older: .get("n"))&&(b=nfunc(b)
# or: (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)
# or: (PL(a),b=a.j.n||null)&&(b=nfunc[idx](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)
(?:\(\s*(?P<b>[a-z])\s*=\s*(?:
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
"n+"\[\s*\+?s*[\w$.]+\s*]
)\s*,(?P<c>[a-z])\s*=\s*[a-z]\s*)?
\.\s*get\s*\(\s*(?(b)(?P=b)|"n{1,2}")(?:\s*\)){2}\s*&&\s*\(\s*(?(c)(?P=c)|b)\s*=\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'))
\((?:[\w$()\s]+,)*?\s* # (
(?P<b>[a-z])\s*=\s* # b=
(?:
(?: # expect ,c=a.get(b) (etc)
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
"n+"\[\s*\+?s*[\w$.]+\s*]
)\s*(?:,[\w$()\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*\(\s*[\w$]+\s*\)
''', 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:
return func_name

View File

@ -925,9 +925,16 @@ class JSInterpreter(object):
obj.reverse()
return obj
elif member == 'slice':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(len(argvals) == 1, 'takes exactly one argument')
return obj[argvals[0]:]
assertion(isinstance(obj, (list, compat_str)), 'must be applied on a list or string')
# From [1]:
# .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':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(argvals, 'takes one or more arguments')