Compare commits

...

11 Commits

Author SHA1 Message Date
changren-wcr
a6d7994109
Merge 0afddd0b9a 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
wangchangren
0afddd0b9a fix: refactor two extractors into one 2022-06-18 08:56:44 +08:00
wangchangren
9ff181a1ab fix: add new extractor for QingTing 2022-06-16 20:44:05 +08:00
changren-wcr
16e7b15f76
use youtube-dl match function instead of native python re
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:14:08 +08:00
changren-wcr
9a421b4e7e
fix regular search pattern for title
_html_search_regex() has default fatal=True: add a default to fall back to _og_search_title()

allow line break in .*

Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:12:26 +08:00
changren-wcr
87706c5ec8
Use _search_regex() to get proper error reports in youtube-dl
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:08:09 +08:00
changren-wcr
60783025df
remove capture of patterns that aren't used
Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-06-16 19:02:30 +08:00
wangchangren
174624aef8 [QingTing] Add new extractor 2022-06-12 10:58:44 +08:00
6 changed files with 139 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

@ -993,6 +993,7 @@ from .presstv import PressTVIE
from .prosiebensat1 import ProSiebenSat1IE from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE from .puls4 import Puls4IE
from .pyvideo import PyvideoIE from .pyvideo import PyvideoIE
from .qingting import QingTingIE
from .qqmusic import ( from .qqmusic import (
QQMusicIE, QQMusicIE,
QQMusicSingerIE, QQMusicSingerIE,

View File

@ -0,0 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from youtube_dl import utils
class QingTingIE(InfoExtractor):
IE_NAME = 'QingTing'
_VALID_URL = r'''(?x)
(?:https?://)?(?:www\.)?
(?P<m>m\.)?(?:qingting\.fm|qtfm\.cn)/(?(m)v|)
channels/\d+/programs/(?P<id>\d+)'''
_TEST = {
'url': 'https://www.qingting.fm/channels/378005/programs/22257411/',
'md5': '47e6a94f4e621ed832c316fd1888fb3c',
'info_dict': {
'id': '22257411',
'ext': 'mp3',
'title': '用了十年才修改,谁在乎教科书?-睡前消息-蜻蜓FM听头条',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'(?s)<title\b[^>]*>(.*)</title>', webpage, 'title',
default=None) or self._og_search_title(webpage)
urlType = self._search_regex(
self._VALID_URL,
url, 'audio URL', group="m")
if urlType == 'm.':
url = self._search_regex(
r'''("|')audioUrl\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
webpage, 'audio URL', group="url")
test_url = utils.url_or_none(url)
if not test_url:
raise utils.ExtractorError('Invalid audio URL %s' % (url,))
return {
'id': video_id,
'title': title,
'ext': 'mp3',
'url': test_url,
}
else:
url = self._search_regex(
r'''("|')alternate\1\s*:\s*("|')(?P<url>(?:(?!\2).)*)\2''',
webpage, 'alternate URL', group="url")
test_url = utils.url_or_none(url)
if not test_url:
raise utils.ExtractorError('Invalid audio URL %s' % (url,))
return self.url_result(url=test_url, video_id=video_id, video_title=title)

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')