Compare commits

...

22 Commits

Author SHA1 Message Date
wfaulk
0d0ed5f9b3
Merge 92d09b249d into c5098961b0 2024-08-21 22:32:43 -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
wfaulk
92d09b249d
Update youtube_dl/extractor/tubitv.py
Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-05-11 14:13:50 -04:00
wfaulk
0f8938bd1e
Update youtube_dl/extractor/tubitv.py
Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-05-11 14:13:38 -04:00
dirkf
7607aa7589
Merge branch 'master' into tubitv-live 2023-04-06 00:05:56 +01:00
William Faulk
fab9851619 better test for description 2023-02-13 09:07:53 -05:00
William Faulk
83a70160ae Add live stream support for TubiTv 2023-02-11 23:01:57 -05:00
fonkap
70a4a8b752
[StreamsbIE] Add extractor for streamsb.com (viewsb.com) (#31517)
* Add extractor for streamsb.com (viewsb.com)

* make data url using app.js version

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:54:45 +00:00
fonkap
99c3cf6419
[KommunetvIE] Add extractor for kommunetv.no (#31516)
* Add extractor for kommunetv.no
* Using utils.update_url instead of regex

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:47:43 +00:00
fonkap
cf5fb7e139
[FileMoonIE] Add extractor for filemoon.sx (#31515)
---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-11 02:37:45 +00:00
teddy171
9256b026d0
[feat]: Add support to external downloader aria2p (#31500)
* feat: add class Aria2pFD

* feat: create call_downloader function

* feat: a colorful download interface to aria2pFD

* feat: change value name

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Typo in suggestion

* fix: remove unused value

* fix: add not function to return value(0 is normal); add total_seconds to download.eta(timedelta object); add waiting status when hook progress

* fix: remove unuse method ..utils.format_bytes

* fix: be up to flake8

* fix: be up to flake8

* Apply suggestions from code review

* [feat] test external downloader aria2p

* [feat] test external downloader aria2p

* [fix] test_external_downloader.py

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Apply suggestions from code review

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update test/test_external_downloader.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update test/test_external_downloader.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* Update youtube_dl/downloader/external.py

Co-authored-by: dirkf <fieldhouse@gmx.net>

* refactoring code and fix bugs

* Apply suggestions from code review

* Rename test_external_downloader.py to test_downloader_external.py

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-09 20:19:27 +00:00
Valentin Metz
80c0228777
[rbgtum] Add new extractor (#31305)
* [rbgtum] Add new extractor

* Small update, force CI

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2023-02-09 11:25:28 +00:00
dirkf
bcf597ea17 [YouTube] Fix tests 2023-02-09 11:01:57 +00:00
dirkf
f640916de1 [YouTube] Refresh compat/utils usage
* import parse_qs()
* import parse_qs in lazy_extractors (clears old TODO)
* clean up old compiled lazy_extractors for Py2
* use update_url()
2023-02-09 11:01:57 +00:00
dirkf
b337af9c62 [compat] Update test_compat
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
a6f7d10d44 [utils] Add parse_qs, update_url
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
9ca224b697 [compat] Systematise compat_ naming
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
ce81ae3846 [test] Fix TestAgeRestriction
* age restriction may cause DownloadError
* update obsolete test URLs
[skip ci]
2023-02-09 11:01:57 +00:00
dirkf
2be0cd2616 [YouTube] Add signatureTimestamp for age-gate bypass 2023-02-09 11:01:57 +00:00
dirkf
b14b33a2e9 [YouTube] Bypass age-gating for certain restricted videos
* Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client

* Also add and fix tests

* Introduce and use new utility function `update_url()`
2023-02-09 11:01:57 +00:00
5 changed files with 103 additions and 36 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

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
@ -13,38 +14,29 @@ from ..utils import (
class TubiTvIE(InfoExtractor): class TubiTvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows|live)/(?P<id>[0-9]+)'
_LOGIN_URL = 'http://tubitv.com/login' _LOGIN_URL = 'http://tubitv.com/login'
_NETRC_MACHINE = 'tubitv' _NETRC_MACHINE = 'tubitv'
_GEO_COUNTRIES = ['US'] _GEO_COUNTRIES = ['US']
_TESTS = [{ _TESTS = [{
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday', 'url': 'https://tubitv.com/movies/229877/carnival-of-souls',
'md5': '43ac06be9326f41912dc64ccf7a80320', 'md5': '275a9f78428cfd6428520989408bcfe9',
'info_dict': { 'info_dict': {
'id': '283829', 'id': '229877',
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Comedian at The Friday', 'title': 'Carnival of Souls',
'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.', 'description': 'After a traumatic accident, a woman becomes drawn to a mysterious abandoned carnival.',
'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434', 'uploader_id': 'da2522b1c94be4a578da6ba674925159',
}, },
}, { }, {
'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories', 'url': 'https://tubitv.com/live/715943/wb-tv-watchlist',
'only_matching': True,
}, {
'url': 'http://tubitv.com/movies/383676/tracker',
'only_matching': True,
}, {
'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
'info_dict': { 'info_dict': {
'id': '560057', 'id': '715943',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Penitentiary', 'title': 'WB TV Watchlist',
'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9', 'description': compat_str,
'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2', 'uploader_id': 'a12923a141282c8b62e593bac425db99',
'release_year': 1979, 'is_live': True,
},
'params': {
'skip_download': True,
}, },
}] }]
@ -76,7 +68,7 @@ class TubiTvIE(InfoExtractor):
title = video_data['title'] title = video_data['title']
formats = self._extract_m3u8_formats( formats = self._extract_m3u8_formats(
self._proto_relative_url(video_data['url']), self._proto_relative_url(traverse_obj(video_data, 'url', ('video_resources', 0, 'manifest', 'url'))),
video_id, 'mp4', 'm3u8_native') video_id, 'mp4', 'm3u8_native')
self._sort_formats(formats) self._sort_formats(formats)
@ -97,6 +89,8 @@ class TubiTvIE(InfoExtractor):
'url': self._proto_relative_url(sub_url), 'url': self._proto_relative_url(sub_url),
}) })
is_live = ('live' in video_data.get('tags') or []) or None
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
@ -107,4 +101,5 @@ class TubiTvIE(InfoExtractor):
'duration': int_or_none(video_data.get('duration')), 'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('publisher_id'), 'uploader_id': video_data.get('publisher_id'),
'release_year': int_or_none(video_data.get('year')), 'release_year': int_or_none(video_data.get('year')),
'is_live': is_live,
} }

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* # (
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)| (?P<b>[a-z])\s*=\s* # b=
"n+"\[\s*\+?s*[\w$.]+\s*] (?:
)\s*,(?P<c>[a-z])\s*=\s*[a-z]\s*)? (?: # expect ,c=a.get(b) (etc)
\.\s*get\s*\(\s*(?(b)(?P=b)|"n{1,2}")(?:\s*\)){2}\s*&&\s*\(\s*(?(c)(?P=c)|b)\s*=\s* String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\) "n+"\[\s*\+?s*[\w$.]+\s*]
''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) )\s*(?:,[\w$()\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: 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')