Merge 48d0994b5b into c5098961b0

[Youtube] Rework n function extraction pattern
Now also succeeds with player b12cc44b
2024-12-23 12:40:11 +09:00 · 2024-08-21 22:32:57 -04:00 · 2024-08-06 20:59:09 +01:00 · 2024-08-06 20:51:38 +01:00 · 2024-08-01 19:18:34 +01:00 · 2022-02-15 12:22:58 +01:00
10 changed files with 192 additions and 321 deletions
--- a/test/test_jsinterp.py
+++ b/test/test_jsinterp.py
@ -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()
--- a/test/test_youtube_signature.py
+++ b/test/test_youtube_signature.py
@ -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',
+    ),
 ]


--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@ -371,7 +371,6 @@ from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .expotv import ExpoTVIE
 from .expressen import ExpressenIE
-from .extremetube import ExtremeTubeIE
 from .eyedotv import EyedoTVIE
 from .facebook import (
    FacebookIE,
@ -562,7 +561,6 @@ from .kaltura import KalturaIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
-from .keezmovies import KeezMoviesIE
 from .ketnet import KetnetIE
 from .khanacademy import (
    KhanAcademyIE,
@ -713,10 +711,6 @@ from .mlb import (
 )
 from .mnet import MnetIE
 from .moevideo import MoeVideoIE
-from .mofosex import (
-    MofosexIE,
-    MofosexEmbedIE,
-)
 from .mojvideo import MojvideoIE
 from .morningstar import MorningstarIE
 from .motherless import (
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@ -1,50 +0,0 @@
-from __future__ import unicode_literals
-
-from ..utils import str_to_int
-from .keezmovies import KeezMoviesIE
-
-
-class ExtremeTubeIE(KeezMoviesIE):
-    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
-    _TESTS = [{
-        'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '92feaafa4b58e82f261e5419f39c60cb',
-        'info_dict': {
-            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-            'ext': 'mp4',
-            'title': 'Music Video 14 british euro brit european cumshots swallow',
-            'uploader': 'anonim',
-            'view_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        'url': 'http://www.extremetube.com/gay/video/abcde-1234',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.extremetube.com/video/652431',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
-
-        if not info['title']:
-            info['title'] = self._search_regex(
-                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
-
-        uploader = self._html_search_regex(
-            r'Uploaded by:\s*</[^>]+>\s*<a[^>]+>(.+?)</a>',
-            webpage, 'uploader', fatal=False)
-        view_count = str_to_int(self._search_regex(
-            r'Views:\s*</[^>]+>\s*<[^>]+>([\d,\.]+)</',
-            webpage, 'view count', fatal=False))
-
-        info.update({
-            'uploader': uploader,
-            'view_count': view_count,
-        })
-
-        return info
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@ -66,7 +66,6 @@ from .tnaflix import TNAFlixNetworkEmbedIE
 from .drtuber import DrTuberIE
 from .redtube import RedTubeIE
 from .tube8 import Tube8IE
-from .mofosex import MofosexEmbedIE
 from .spankwire import SpankwireIE
 from .youporn import YouPornIE
 from .vimeo import (
@ -3044,11 +3043,6 @@ class GenericIE(InfoExtractor):
        if tube8_urls:
            return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())

-        # Look for embedded Mofosex player
-        mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
-        if mofosex_urls:
-            return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
-
        # Look for embedded Spankwire player
        spankwire_urls = SpankwireIE._extract_urls(webpage)
        if spankwire_urls:
--- a/youtube_dl/extractor/keezmovies.py
+++ b/youtube_dl/extractor/keezmovies.py
@ -1,133 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..aes import aes_decrypt_text
-from ..compat import compat_urllib_parse_unquote
-from ..utils import (
-    determine_ext,
-    ExtractorError,
-    int_or_none,
-    str_to_int,
-    strip_or_none,
-    url_or_none,
-)
-
-
-class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
-        'md5': '2ac69cdb882055f71d82db4311732a1a',
-        'info_dict': {
-            'id': '18070681',
-            'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
-            'ext': 'mp4',
-            'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
-            'thumbnail': None,
-            'view_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        'url': 'http://www.keezmovies.com/video/18070681',
-        'only_matching': True,
-    }]
-
-    def _extract_info(self, url, fatal=True):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = (mobj.group('display_id')
-                      if 'display_id' in mobj.groupdict()
-                      else None) or mobj.group('id')
-
-        webpage = self._download_webpage(
-            url, display_id, headers={'Cookie': 'age_verified=1'})
-
-        formats = []
-        format_urls = set()
-
-        title = None
-        thumbnail = None
-        duration = None
-        encrypted = False
-
-        def extract_format(format_url, height=None):
-            format_url = url_or_none(format_url)
-            if not format_url or not format_url.startswith(('http', '//')):
-                return
-            if format_url in format_urls:
-                return
-            format_urls.add(format_url)
-            tbr = int_or_none(self._search_regex(
-                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
-            if not height:
-                height = int_or_none(self._search_regex(
-                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
-            if encrypted:
-                format_url = aes_decrypt_text(
-                    video_url, title, 32).decode('utf-8')
-            formats.append({
-                'url': format_url,
-                'format_id': '%dp' % height if height else None,
-                'height': height,
-                'tbr': tbr,
-            })
-
-        flashvars = self._parse_json(
-            self._search_regex(
-                r'flashvars\s*=\s*({.+?});', webpage,
-                'flashvars', default='{}'),
-            display_id, fatal=False)
-
-        if flashvars:
-            title = flashvars.get('video_title')
-            thumbnail = flashvars.get('image_url')
-            duration = int_or_none(flashvars.get('video_duration'))
-            encrypted = flashvars.get('encrypted') is True
-            for key, value in flashvars.items():
-                mobj = re.search(r'quality_(\d+)[pP]', key)
-                if mobj:
-                    extract_format(value, int(mobj.group(1)))
-            video_url = flashvars.get('video_url')
-            if video_url and determine_ext(video_url, None):
-                extract_format(video_url)
-
-        video_url = self._html_search_regex(
-            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
-            webpage, 'video url', default=None, group='url')
-        if video_url:
-            extract_format(compat_urllib_parse_unquote(video_url))
-
-        if not formats:
-            if 'title="This video is no longer available"' in webpage:
-                raise ExtractorError(
-                    'Video %s is no longer available' % video_id, expected=True)
-
-        try:
-            self._sort_formats(formats)
-        except ExtractorError:
-            if fatal:
-                raise
-
-        if not title:
-            title = self._html_search_regex(
-                r'<h1[^>]*>([^<]+)', webpage, 'title')
-
-        return webpage, {
-            'id': video_id,
-            'display_id': display_id,
-            'title': strip_or_none(title),
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'age_limit': 18,
-            'formats': formats,
-        }
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url, fatal=False)
-        if not info['formats']:
-            return self.url_result(url, 'Generic')
-        info['view_count'] = str_to_int(self._search_regex(
-            r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
-        return info
--- a/youtube_dl/extractor/mofosex.py
+++ b/youtube_dl/extractor/mofosex.py
@ -1,79 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    str_to_int,
-    unified_strdate,
-)
-from .keezmovies import KeezMoviesIE
-
-
-class MofosexIE(KeezMoviesIE):
-    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
-    _TESTS = [{
-        'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
-        'md5': '558fcdafbb63a87c019218d6e49daf8a',
-        'info_dict': {
-            'id': '318131',
-            'display_id': 'amateur-teen-playing-and-masturbating-318131',
-            'ext': 'mp4',
-            'title': 'amateur teen playing and masturbating',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20121114',
-            'view_count': int,
-            'like_count': int,
-            'dislike_count': int,
-            'age_limit': 18,
-        }
-    }, {
-        # This video is no longer available
-        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
-
-        view_count = str_to_int(self._search_regex(
-            r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
-        like_count = int_or_none(self._search_regex(
-            r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
-            'like count', fatal=False))
-        dislike_count = int_or_none(self._search_regex(
-            r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
-            'like count', fatal=False))
-        upload_date = unified_strdate(self._html_search_regex(
-            r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
-
-        info.update({
-            'view_count': view_count,
-            'like_count': like_count,
-            'dislike_count': dislike_count,
-            'upload_date': upload_date,
-            'thumbnail': self._og_search_thumbnail(webpage),
-        })
-
-        return info
-
-
-class MofosexEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
-        'only_matching': True,
-    }]
-
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)',
-            webpage)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self.url_result(
-            'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id),
-            ie=MofosexIE.ie_key(), video_id=video_id)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@ -3,32 +3,33 @@ from __future__ import unicode_literals
 import re

 from ..utils import (
+    determine_ext,
+    ExtractorError,
    int_or_none,
    str_to_int,
+    url_or_none,
 )
-from .keezmovies import KeezMoviesIE
+from .common import InfoExtractor
+from ..aes import aes_decrypt_text
+from ..compat import compat_urllib_parse_unquote


-class Tube8IE(KeezMoviesIE):
+class Tube8IE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
    _TESTS = [{
-        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
-        'md5': '65e20c48e6abff62ed0c3965fff13a39',
+        'url': 'https://www.tube8.com/erotic/playtime/81807731/',
+        'md5': 'fefa69ff76debaa63aa59374bfc51c95',
        'info_dict': {
-            'id': '229795',
-            'display_id': 'kasia-music-video',
+            'id': '81807731',
+            'display_id': 'playtime',
            'ext': 'mp4',
-            'description': 'hot teen Kasia grinding',
-            'uploader': 'unknown',
-            'title': 'Kasia music video',
+            'uploader': 'kikkijay-ph',
+            'title': 'Playtime',
            'age_limit': 18,
-            'duration': 230,
-            'categories': ['Teen'],
-            'tags': ['dancing'],
+            'duration': 988,
+            'categories': ['Erotic'],
+            'tags': ['adult toys', 'big boobs', 'butt', 'masturbate'],
        },
-    }, {
-        'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
-        'only_matching': True,
    }]

    @staticmethod
@ -38,49 +39,121 @@ class Tube8IE(KeezMoviesIE):
            webpage)

    def _real_extract(self, url):
-        webpage, info = self._extract_info(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')

-        if not info['title']:
-            info['title'] = self._html_search_regex(
-                r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
+        webpage = self._download_webpage(
+            url, display_id, headers={'Cookie': 'age_verified=1'})

-        description = self._html_search_regex(
-            r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
-        uploader = self._html_search_regex(
-            r'<span class="username">\s*(.+?)\s*<',
-            webpage, 'uploader', fatal=False)
+        formats = []
+        format_urls = set()
+
+        title = None
+        thumbnail = None
+        duration = None
+        encrypted = False
+
+        def extract_format(format_url, height=None):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//')):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            uploader = flashvars.get('sponsor')
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(compat_urllib_parse_unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                raise ExtractorError(
+                    'Video %s is no longer available' % video_id, expected=True)
+
+        self._sort_formats(formats)
+
+        if not title:
+            title = self._html_search_regex([
+                r'<h1[^>]*>([^<]+)'
+                r'videoTitle\s*=\s*"([^"]+)'], webpage, 'title', default=display_id.capitalize())

        like_count = int_or_none(self._search_regex(
-            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
+            r'rupVar\s*=\s*(\d+);', webpage, 'like count', fatal=False))
        dislike_count = int_or_none(self._search_regex(
-            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
+            r'rdownVar\s*=\s*(\d+);', webpage, 'dislike count', fatal=False))
        view_count = str_to_int(self._search_regex(
            r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
            webpage, 'view count', fatal=False))
        comment_count = str_to_int(self._search_regex(
-            r'<span id="allCommentsCount">(\d+)</span>',
+            r'<span id="allCommentsCount">\((\d+)\)</span>',
            webpage, 'comment count', fatal=False))

        category = self._search_regex(
-            r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
+            r'videoCategoryByName\s*=\s*"([^"]+)";',
            webpage, 'category', fatal=False)
        categories = [category] if category else None

        tags_str = self._search_regex(
-            r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
+            r"(?s)<li\s+class\s*=\s*'video-tag'\s+data-esp-node\s*=\s*'tag'>(.*?)</div>",
            webpage, 'tags', fatal=False)
        tags = [t for t in re.findall(
            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None

-        info.update({
-            'description': description,
+        return {
            'uploader': uploader,
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
+            'formats': formats,
            'view_count': view_count,
            'like_count': like_count,
            'dislike_count': dislike_count,
            'comment_count': comment_count,
            'categories': categories,
            'tags': tags,
-        })
-
-        return info
+        }
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@ -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

--- a/youtube_dl/jsinterp.py
+++ b/youtube_dl/jsinterp.py
@ -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')
Author	SHA1	Message	Date
marieell	f46d98349d	Merge `48d0994b5b` into `c5098961b0`	2024-08-21 22:32:57 -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
marieell	48d0994b5b	[tube8] Fix extractor a bit, replace broken test	2022-02-15 12:22:58 +01:00
marieell	7561727db6	Remove extractors for dead pages They all redirect to youporn.com.	2022-02-15 09:41:32 +01:00