Merge a7c1a558ed into c5098961b0

Now also succeeds with player b12cc44b

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()

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',
+    ),
 ]
 
 

youtube_dl/extractor/camwhoresbay.py

@@ -0,0 +1,128 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+import itertools
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    parse_resolution,
+    sanitize_url,
+    update_url_query,
+)
+
+
+class CamWhoresBayVideoIE(InfoExtractor):
+    IE_NAME = 'camwhoresbay:video'
+    _VALID_URL = r'https?://(?:www\.)?camwhoresbay\.com/videos/(?P<id>[0-9]+)/.+'
+    _TEST = {
+        'url': 'https://www.camwhoresbay.com/videos/484472/kirsten-xxx-2022-01-19/',
+        'md5': 'ae3c5c34866afbd062adf5d2321d66f3',
+        'info_dict': {
+            'id': '484472',
+            'ext': 'mp4',
+            'title': 'Kirsten_Xxx 2022-01-19',
+            'uploader': '789sani',
+            'url': r're:^https?://www\.camwhoresbay\.com/get_file/7/55259a27805bf1313318c14b2afb0dae1fef6e1dd4/484000/484472/484472_720p\.mp4/\?rnd=.+',
+            'thumbnail': r're:^https?://cwbstatic.cdntrex.com/contents/videos_screenshots/484000/484472/preview_720p.mp4.jpg',
+        }
+    }
+
+    @staticmethod
+    def _parse_formats(flashvars):
+        formats = []
+        rnd = flashvars.get('rnd')
+        for k, v in flashvars.items():
+            if re.match(r'^video_(alt_)?url\d?$', k):
+                f = {
+                    'url': update_url_query(v, {'rnd': rnd, })
+                }
+                f.update(parse_resolution(flashvars.get(k + '_text')))
+                formats.append(f)
+        return formats
+
+    @staticmethod
+    def _parse_thumbnails(flashvars):
+        thumbnails = []
+        for k, v in flashvars.items():
+            if re.match(r'^preview_url\d$', k):
+                t = {
+                    'url': sanitize_url(v),
+                    'height': int_or_none(flashvars.get(k.replace('_url', '_height'))),
+                }
+                thumbnails.append(t)
+        return thumbnails
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        if re.search(r'(?s)<div class=\"no-player\"', webpage):
+            print("Video is private, skipping.")
+            return
+
+        title = self._html_search_regex(r'<div class=\"headline\">\n\s*<h1>(.+?)</h1>', webpage, 'title')
+
+        flashvars = self._parse_json(
+            self._search_regex(r'(?s)var\s+flashvars\s*=\s*({.+?})\s*;', webpage, 'flashvars', default='{}'),
+            video_id, transform_source=js_to_json)
+        uploader = self._search_regex(r'''(?s)\bclass\s*=\s*["']avatar["'][^>]+?\btitle\s*=\s*["'](.+)["']''', webpage, 'uploader',
+                                      fatal=False)
+
+        formats = self._parse_formats(flashvars)
+        thumbnails = self._parse_thumbnails(flashvars)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'uploader': uploader,
+            'url': formats[0].get('url'),
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }
+
+
+class CamWhoresBayModelIE(CamWhoresBayVideoIE):
+    IE_NAME = 'camwhoresbay:model'
+    _VALID_URL = r'https?://(?:www\.)?camwhoresbay\.com/models/(?P<id>[0-9a-z\-]+)/?'
+    _MORE_PAGES_INDICATOR = r'''<li\s[^>]*\bclass\s*=\s*["']next["'][^>]*><a\s[^>]*href\s*=\s*["']#videos["']'''
+    _TITLE = None
+    _TITLE_RE = r'''(?is)<div\s[^>]+?\bclass\s*=\s*["']headline["'][^>]*>\s*<h1\s[^>]*>\s*(.*?)'s\s+New\s+Videos\b'''
+    _BASE_URL_TEMPL = 'https://www.camwhoresbay.com/models/%s/?mode=async&function=get_block&block_id=list_videos_common_videos_list&sort_by=post_date&from='
+    _TEST = {
+        'url': 'https://www.camwhoresbay.com/models/kirsten-xxx/',
+        'info_dict': {
+            'id': 'kirsten-xxx',
+            'title': 'Kirsten_xxx',
+        }
+    }
+    _PAGE_SIZE = 35
+
+    def _extract_list_title(self, webpage):
+        return self._html_search_regex(
+            self._TITLE_RE, webpage, 'list title', fatal=False)
+
+    def _title_and_entries(self, model_id, base_url):
+        for page in itertools.count(1):
+            webpage = self._download_webpage('%s%d' % (base_url, page), model_id, 'Downloading page %s' % page)
+
+            if page == 1:
+                yield self._extract_list_title(webpage)
+
+            for video_id in re.findall(
+                    r'(?is)<div\s[^>]*\bclass\s*=\s*["\'.*?\bvideo\-item\b.*?["\'][^>]*>\s*<a\s[^>]*\bhref\s*=\s*["\'](.*?)["\']',
+                    webpage):
+                yield self.url_result(video_id)
+
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+
+    def _extract_videos(self, list_id, base_url):
+        title_and_entries = self._title_and_entries(list_id, base_url)
+        list_title = next(title_and_entries)
+        return self.playlist_result(title_and_entries, list_id, list_title)
+
+    def _real_extract(self, url):
+        model_id = self._match_id(url)
+        return self._extract_videos(model_id, self._BASE_URL_TEMPL % (model_id,))

youtube_dl/extractor/extractors.py

@@ -167,6 +167,10 @@ from .camdemy import (
 )
 from .cammodels import CamModelsIE
 from .camtube import CamTubeIE
+from .camwhoresbay import (
+    CamWhoresBayVideoIE,
+    CamWhoresBayModelIE,
+)
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE

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
 

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')