Compare commits

...

5 Commits

Author SHA1 Message Date
PRB0t
7f4c97842b
Merge 8edbee2a50 into c5098961b0 2024-08-21 22:32:46 -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
PRB0t
8edbee2a50 🤖 Add NoodleDude extractor 2022-07-22 12:14:48 +02:00
6 changed files with 156 additions and 13 deletions

View File

@ -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()

View File

@ -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',
),
] ]

View File

@ -833,6 +833,7 @@ from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE from .nobelprize import NobelPrizeIE
from .nonktube import NonkTubeIE from .nonktube import NonkTubeIE
from .noodledude import NoodleDudeIE
from .noovo import NoovoIE from .noovo import NoovoIE
from .normalboots import NormalbootsIE from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE from .nosvideo import NosVideoIE

View File

@ -0,0 +1,70 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
import json
class NoodleDudeIE(InfoExtractor):
IE_NAME = 'NoodleDude'
_VALID_URL = r'https?://(www\.)?noodledude\.io/videos/(?P<id>[0-9a-zA-Z_-]+)'
_TEST = {
'url': 'https://www.noodledude.io/videos/kawaii-vs-goth',
'md5': '9d3465ea49d16860a531035517ea8aec',
'info_dict': {
'id': 'kawaii-vs-goth',
'ext': 'mp4',
'title': 'Kawaii VS Goth',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:f16fef1f758a4dc38041bd6648b9d3b2',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, headers={'Referer': 'https://www.noodledude.io/'})
#with open('webpage.tmp', 'w') as f:
#f.write(webpage)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1 id="video-title".*?>(.+?)</h1>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'decription')
print('Title:', title)
print('Description:', description)
iframe_url = self._search_regex(r'<iframe\s*src="(.+?)"', webpage, 'iframe_url', flags=re.MULTILINE)
#print('iframe: ', iframe_url)
iframe_data = self._download_webpage(iframe_url, video_id, headers={'Referer': 'https://www.noodledude.io/'})
#with open('iframe.tmp', 'w') as f:
#f.write(iframe_data)
m3u8_url = self._search_regex(r'<source.*?src="(.+?)"', iframe_data, 'm3u8_url')
print('M3U8:', m3u8_url)
poster_url = self._search_regex(r'<video.*?data-poster="(.+?)"', iframe_data, 'poster_url')
print('Poster:', poster_url)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={'Referer': 'https://iframe.mediadelivery.net/'})
print('Formats:', json.dumps(formats))
for f in formats:
f.setdefault('http_headers', {})['Referer'] = 'https://iframe.mediadelivery.net/'
return {
'id': video_id,
'url': url,
'title': title,
'description': description,
'formats': formats,
'thumbnail': poster_url
#'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}

View File

@ -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

View File

@ -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')