[PornHub] Remove extraneous modelhub login code

Merge from master

.github/workflows/ci.yml

@@ -116,29 +116,29 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        os: [ubuntu-22.04]
+        os: [ubuntu-20.04]
         python-version: ${{ fromJSON(needs.select.outputs.cpython-versions) }}
         python-impl: [cpython]
         ytdl-test-set: ${{ fromJSON(needs.select.outputs.test-set) }}
         run-tests-ext: [sh]
         include:
-        - os: windows-2022
+        - os: windows-2019
           python-version: 3.4
           python-impl: cpython
           ytdl-test-set: ${{ contains(needs.select.outputs.test-set, 'core') && 'core' || 'nocore' }}
           run-tests-ext: bat
-        - os: windows-2022
+        - os: windows-2019
           python-version: 3.4
           python-impl: cpython
           ytdl-test-set: ${{ contains(needs.select.outputs.test-set, 'download') && 'download'  || 'nodownload' }}
           run-tests-ext: bat
         # jython
-        - os: ubuntu-22.04
+        - os: ubuntu-20.04
           python-version: 2.7
           python-impl: jython
           ytdl-test-set: ${{ contains(needs.select.outputs.test-set, 'core') && 'core' || 'nocore' }}
           run-tests-ext: sh
-        - os: ubuntu-22.04
+        - os: ubuntu-20.04
           python-version: 2.7
           python-impl: jython
           ytdl-test-set: ${{ contains(needs.select.outputs.test-set, 'download') && 'download'  || 'nodownload' }}
@@ -160,7 +160,7 @@ jobs:
       # NB may run apt-get install in Linux
       uses: ytdl-org/setup-python@v1
       env:
-        # Temporary (?) workaround for Python 3.5 failures - May 2024
+        # Temporary workaround for Python 3.5 failures - May 2024
         PIP_TRUSTED_HOST: "pypi.python.org pypi.org files.pythonhosted.org"
       with:
         python-version: ${{ matrix.python-version }}
@@ -240,10 +240,7 @@ jobs:
       # install 2.7
       shell: bash
       run: |
-        # Ubuntu 22.04 no longer has python-is-python2: fetch it
-        curl -L "http://launchpadlibrarian.net/474693132/python-is-python2_2.7.17-4_all.deb" -o python-is-python2.deb
-        sudo apt-get install -y python2
-        sudo dpkg --force-breaks -i python-is-python2.deb
+        sudo apt-get install -y python2 python-is-python2
         echo "PYTHONHOME=/usr" >> "$GITHUB_ENV"
     #-------- Python 2.6 --
     - name: Set up Python 2.6 environment

test/test_cache.py

@@ -63,21 +63,9 @@ class TestCache(unittest.TestCase):
         obj = {'x': 1, 'y': ['ä', '\\a', True]}
         c.store('test_cache', 'k.', obj)
         self.assertEqual(c.load('test_cache', 'k.', min_ver='1970.01.01'), obj)
-        new_version = '.'.join(('%0.2d' % ((v + 1) if i == 0 else v, )) for i, v in enumerate(version_tuple(__version__)))
+        new_version = '.'.join(('%d' % ((v + 1) if i == 0 else v, )) for i, v in enumerate(version_tuple(__version__)))
         self.assertIs(c.load('test_cache', 'k.', min_ver=new_version), None)
 
-    def test_cache_clear(self):
-        ydl = FakeYDL({
-            'cachedir': self.test_dir,
-        })
-        c = Cache(ydl)
-        c.store('test_cache', 'k.', 'kay')
-        c.store('test_cache', 'l.', 'ell')
-        self.assertEqual(c.load('test_cache', 'k.'), 'kay')
-        c.clear('test_cache', 'k.')
-        self.assertEqual(c.load('test_cache', 'k.'), None)
-        self.assertEqual(c.load('test_cache', 'l.'), 'ell')
-
 
 if __name__ == '__main__':
     unittest.main()

test/test_jsinterp.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -7,14 +6,12 @@ from __future__ import unicode_literals
 import os
 import sys
 import unittest
-
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import math
 import re
-import time
 
-from youtube_dl.compat import compat_str as str
+from youtube_dl.compat import compat_str
 from youtube_dl.jsinterp import JS_Undefined, JSInterpreter
 
 NaN = object()
@@ -22,7 +19,7 @@ NaN = object()
 
 class TestJSInterpreter(unittest.TestCase):
     def _test(self, jsi_or_code, expected, func='f', args=()):
-        if isinstance(jsi_or_code, str):
+        if isinstance(jsi_or_code, compat_str):
             jsi_or_code = JSInterpreter(jsi_or_code)
         got = jsi_or_code.call_function(func, *args)
         if expected is NaN:
@@ -43,27 +40,16 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return 42 + 7;}', 49)
         self._test('function f(){return 42 + undefined;}', NaN)
         self._test('function f(){return 42 + null;}', 42)
-        self._test('function f(){return 1 + "";}', '1')
-        self._test('function f(){return 42 + "7";}', '427')
-        self._test('function f(){return false + true;}', 1)
-        self._test('function f(){return "false" + true;}', 'falsetrue')
-        self._test('function f(){return '
-                   '1 + "2" + [3,4] + {k: 56} + null + undefined + Infinity;}',
-                   '123,4[object Object]nullundefinedInfinity')
 
     def test_sub(self):
         self._test('function f(){return 42 - 7;}', 35)
         self._test('function f(){return 42 - undefined;}', NaN)
         self._test('function f(){return 42 - null;}', 42)
-        self._test('function f(){return 42 - "7";}', 35)
-        self._test('function f(){return 42 - "spam";}', NaN)
 
     def test_mul(self):
         self._test('function f(){return 42 * 7;}', 294)
         self._test('function f(){return 42 * undefined;}', NaN)
         self._test('function f(){return 42 * null;}', 0)
-        self._test('function f(){return 42 * "7";}', 294)
-        self._test('function f(){return 42 * "eggs";}', NaN)
 
     def test_div(self):
         jsi = JSInterpreter('function f(a, b){return a / b;}')
@@ -71,26 +57,17 @@ class TestJSInterpreter(unittest.TestCase):
         self._test(jsi, NaN, args=(JS_Undefined, 1))
         self._test(jsi, float('inf'), args=(2, 0))
         self._test(jsi, 0, args=(0, 3))
-        self._test(jsi, 6, args=(42, 7))
-        self._test(jsi, 0, args=(42, float('inf')))
-        self._test(jsi, 6, args=("42", 7))
-        self._test(jsi, NaN, args=("spam", 7))
 
     def test_mod(self):
         self._test('function f(){return 42 % 7;}', 0)
         self._test('function f(){return 42 % 0;}', NaN)
         self._test('function f(){return 42 % undefined;}', NaN)
-        self._test('function f(){return 42 % "7";}', 0)
-        self._test('function f(){return 42 % "beans";}', NaN)
 
     def test_exp(self):
         self._test('function f(){return 42 ** 2;}', 1764)
         self._test('function f(){return 42 ** undefined;}', NaN)
         self._test('function f(){return 42 ** null;}', 1)
-        self._test('function f(){return undefined ** 0;}', 1)
         self._test('function f(){return undefined ** 42;}', NaN)
-        self._test('function f(){return 42 ** "2";}', 1764)
-        self._test('function f(){return 42 ** "spam";}', NaN)
 
     def test_calc(self):
         self._test('function f(a){return 2*a+1;}', 7, args=[3])
@@ -112,60 +89,13 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return 19 & 21;}', 17)
         self._test('function f(){return 11 >> 2;}', 2)
         self._test('function f(){return []? 2+3: 4;}', 5)
-        # equality
-        self._test('function f(){return 1 == 1}', True)
-        self._test('function f(){return 1 == 1.0}', True)
-        self._test('function f(){return 1 == "1"}', True)
         self._test('function f(){return 1 == 2}', False)
-        self._test('function f(){return 1 != "1"}', False)
-        self._test('function f(){return 1 != 2}', True)
-        self._test('function f(){var x = {a: 1}; var y = x; return x == y}', True)
-        self._test('function f(){var x = {a: 1}; return x == {a: 1}}', False)
-        self._test('function f(){return NaN == NaN}', False)
-        self._test('function f(){return null == undefined}', True)
-        self._test('function f(){return "spam, eggs" == "spam, eggs"}', True)
-        # strict equality
-        self._test('function f(){return 1 === 1}', True)
-        self._test('function f(){return 1 === 1.0}', True)
-        self._test('function f(){return 1 === "1"}', False)
-        self._test('function f(){return 1 === 2}', False)
-        self._test('function f(){var x = {a: 1}; var y = x; return x === y}', True)
-        self._test('function f(){var x = {a: 1}; return x === {a: 1}}', False)
-        self._test('function f(){return NaN === NaN}', False)
-        self._test('function f(){return null === undefined}', False)
-        self._test('function f(){return null === null}', True)
-        self._test('function f(){return undefined === undefined}', True)
-        self._test('function f(){return "uninterned" === "uninterned"}', True)
-        self._test('function f(){return 1 === 1}', True)
-        self._test('function f(){return 1 === "1"}', False)
-        self._test('function f(){return 1 !== 1}', False)
-        self._test('function f(){return 1 !== "1"}', True)
-        # expressions
         self._test('function f(){return 0 && 1 || 2;}', 2)
         self._test('function f(){return 0 ?? 42;}', 0)
         self._test('function f(){return "life, the universe and everything" < 42;}', False)
         # https://github.com/ytdl-org/youtube-dl/issues/32815
         self._test('function f(){return 0  - 7 * - 6;}', 42)
 
-    def test_bitwise_operators_typecast(self):
-        # madness
-        self._test('function f(){return null << 5}', 0)
-        self._test('function f(){return undefined >> 5}', 0)
-        self._test('function f(){return 42 << NaN}', 42)
-        self._test('function f(){return 42 << Infinity}', 42)
-        self._test('function f(){return 0.0 << null}', 0)
-        self._test('function f(){return NaN << 42}', 0)
-        self._test('function f(){return "21.9" << 1}', 42)
-        self._test('function f(){return true << "5";}', 32)
-        self._test('function f(){return true << true;}', 2)
-        self._test('function f(){return "19" & "21.9";}', 17)
-        self._test('function f(){return "19" & false;}', 0)
-        self._test('function f(){return "11.0" >> "2.1";}', 2)
-        self._test('function f(){return 5 ^ 9;}', 12)
-        self._test('function f(){return 0.0 << NaN}', 0)
-        self._test('function f(){return null << undefined}', 0)
-        self._test('function f(){return 21 << 4294967297}', 42)
-
     def test_array_access(self):
         self._test('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}', [5, 2, 7])
 
@@ -180,8 +110,8 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){var x = 20; x = 30 + 1; return x;}', 31)
         self._test('function f(){var x = 20; x += 30 + 1; return x;}', 51)
         self._test('function f(){var x = 20; x -= 30 + 1; return x;}', -11)
-        self._test('function f(){var x = 2; var y = ["a", "b"]; y[x%y["length"]]="z"; return y}', ['z', 'b'])
 
+    @unittest.skip('Not yet fully implemented')
     def test_comments(self):
         self._test('''
             function f() {
@@ -200,15 +130,6 @@ class TestJSInterpreter(unittest.TestCase):
             }
         ''', 3)
 
-        self._test('''
-            function f() {
-                var x = ( /* 1 + */ 2 +
-                          /* 30 * 40 */
-                          50);
-                return x;
-            }
-        ''', 52)
-
     def test_precedence(self):
         self._test('''
             function f() {
@@ -230,34 +151,6 @@ class TestJSInterpreter(unittest.TestCase):
         self._test(jsi, 86000, args=['12/31/1969 18:01:26 MDT'])
         # epoch 0
         self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
-        # undefined
-        self._test(jsi, NaN, args=[JS_Undefined])
-        # y,m,d, ... - may fail with older dates lacking DST data
-        jsi = JSInterpreter(
-            'function f() { return new Date(%s); }'
-            % ('2024, 5, 29, 2, 52, 12, 42',))
-        self._test(jsi, (
-            1719625932042                           # UK value
-            + (
-                + 3600                              # back to GMT
-                + (time.altzone if time.daylight    # host's DST
-                   else time.timezone)
-            ) * 1000))
-        # no arg
-        self.assertAlmostEqual(JSInterpreter(
-            'function f() { return new Date() - 0; }').call_function('f'),
-            time.time() * 1000, delta=100)
-        # Date.now()
-        self.assertAlmostEqual(JSInterpreter(
-            'function f() { return Date.now(); }').call_function('f'),
-            time.time() * 1000, delta=100)
-        # Date.parse()
-        jsi = JSInterpreter('function f(dt) { return Date.parse(dt); }')
-        self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
-        # Date.UTC()
-        jsi = JSInterpreter('function f() { return Date.UTC(%s); }'
-                            % ('1970, 0, 1, 0, 0, 0, 0',))
-        self._test(jsi, 0)
 
     def test_call(self):
         jsi = JSInterpreter('''
@@ -372,28 +265,8 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f() { a=5; return (a -= 1, a+=3, a); }', 7)
         self._test('function f() { return (l=[0,1,2,3], function(a, b){return a+b})((l[1], l[2]), l[3]) }', 5)
 
-    def test_not(self):
-        self._test('function f() { return ! undefined; }', True)
-        self._test('function f() { return !0; }', True)
-        self._test('function f() { return !!0; }', False)
-        self._test('function f() { return ![]; }', False)
-        self._test('function f() { return !0 !== false; }', True)
-
     def test_void(self):
-        self._test('function f() { return void 42; }', JS_Undefined)
-
-    def test_typeof(self):
-        self._test('function f() { return typeof undefined; }', 'undefined')
-        self._test('function f() { return typeof NaN; }', 'number')
-        self._test('function f() { return typeof Infinity; }', 'number')
-        self._test('function f() { return typeof true; }', 'boolean')
-        self._test('function f() { return typeof null; }', 'object')
-        self._test('function f() { return typeof "a string"; }', 'string')
-        self._test('function f() { return typeof 42; }', 'number')
-        self._test('function f() { return typeof 42.42; }', 'number')
-        self._test('function f() { var g = function(){}; return typeof g; }', 'function')
-        self._test('function f() { return typeof {key: "value"}; }', 'object')
-        # not yet implemented: Symbol, BigInt
+        self._test('function f() { return void 42; }', None)
 
     def test_return_function(self):
         jsi = JSInterpreter('''
@@ -410,7 +283,7 @@ class TestJSInterpreter(unittest.TestCase):
     def test_undefined(self):
         self._test('function f() { return undefined === undefined; }', True)
         self._test('function f() { return undefined; }', JS_Undefined)
-        self._test('function f() { return undefined ?? 42; }', 42)
+        self._test('function f() {return undefined ?? 42; }', 42)
         self._test('function f() { let v; return v; }', JS_Undefined)
         self._test('function f() { let v; return v**0; }', 1)
         self._test('function f() { let v; return [v>42, v<=42, v&&42, 42&&v]; }',
@@ -451,19 +324,8 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f() { let a; return a?.qq; }', JS_Undefined)
         self._test('function f() { let a = {m1: 42, m2: 0 }; return a?.qq; }', JS_Undefined)
 
-    def test_indexing(self):
-        self._test('function f() { return [1, 2, 3, 4][3]}', 4)
-        self._test('function f() { return [1, [2, [3, [4]]]][1][1][1][0]}', 4)
-        self._test('function f() { var o = {1: 2, 3: 4}; return o[3]}', 4)
-        self._test('function f() { var o = {1: 2, 3: 4}; return o["3"]}', 4)
-        self._test('function f() { return [1, [2, {3: [4]}]][1][1]["3"][0]}', 4)
-        self._test('function f() { return [1, 2, 3, 4].length}', 4)
-        self._test('function f() { var o = {1: 2, 3: 4}; return o.length}', JS_Undefined)
-        self._test('function f() { var o = {1: 2, 3: 4}; o["length"] = 42; return o.length}', 42)
-
     def test_regex(self):
         self._test('function f() { let a=/,,[/,913,/](,)}/; }', None)
-        self._test('function f() { let a=/,,[/,913,/](,)}/; return a.source;  }', ',,[/,913,/](,)}')
 
         jsi = JSInterpreter('''
             function x() { let a=/,,[/,913,/](,)}/; "".replace(a, ""); return a; }
@@ -511,6 +373,13 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return -524999584 << 5}', 379882496)
         self._test('function f(){return 1236566549 << 5}', 915423904)
 
+    def test_bitwise_operators_typecast(self):
+        # madness
+        self._test('function f(){return null << 5}', 0)
+        self._test('function f(){return undefined >> 5}', 0)
+        self._test('function f(){return 42 << NaN}', 42)
+        self._test('function f(){return 42 << Infinity}', 42)
+
     def test_negative(self):
         self._test('function f(){return 2    *    -2.0    ;}', -4)
         self._test('function f(){return 2    -    - -2    ;}', 0)
@@ -542,19 +411,10 @@ class TestJSInterpreter(unittest.TestCase):
             self._test(jsi, 't-e-s-t', args=[test_input, '-'])
             self._test(jsi, '', args=[[], '-'])
 
-        self._test('function f(){return '
-                   '[1, 1.0, "abc", {a: 1}, null, undefined, Infinity, NaN].join()}',
-                   '1,1,abc,[object Object],,,Infinity,NaN')
-        self._test('function f(){return '
-                   '[1, 1.0, "abc", {a: 1}, null, undefined, Infinity, NaN].join("~")}',
-                   '1~1~abc~[object Object]~~~Infinity~NaN')
-
     def test_split(self):
         test_result = list('test')
         tests = [
             'function f(a, b){return a.split(b)}',
-            'function f(a, b){return a["split"](b)}',
-            'function f(a, b){let x = ["split"]; return a[x[0]](b)}',
             'function f(a, b){return String.prototype.split.call(a, b)}',
             'function f(a, b){return String.prototype.split.apply(a, [b])}',
         ]
@@ -564,18 +424,6 @@ class TestJSInterpreter(unittest.TestCase):
             self._test(jsi, test_result, args=['t-e-s-t', '-'])
             self._test(jsi, [''], args=['', '-'])
             self._test(jsi, [], args=['', ''])
-        # RegExp split
-        self._test('function f(){return "test".split(/(?:)/)}',
-                   ['t', 'e', 's', 't'])
-        self._test('function f(){return "t-e-s-t".split(/[es-]+/)}',
-                   ['t', 't'])
-        # from MDN: surrogate pairs aren't handled: case 1 fails
-        # self._test('function f(){return "😄😄".split(/(?:)/)}',
-        #            ['\ud83d', '\ude04', '\ud83d', '\ude04'])
-        # case 2 beats Py3.2: it gets the case 1 result
-        if sys.version_info >= (2, 6) and not ((3, 0) <= sys.version_info < (3, 3)):
-            self._test('function f(){return "😄😄".split(/(?:)/u)}',
-                       ['😄', '😄'])
 
     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])
@@ -605,53 +453,6 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return "012345678".slice(-1, 1)}', '')
         self._test('function f(){return "012345678".slice(-3, -1)}', '67')
 
-    def test_splice(self):
-        self._test('function f(){var T = ["0", "1", "2"]; T["splice"](2, 1, "0")[0]; return T }', ['0', '1', '0'])
-
-    def test_pop(self):
-        # pop
-        self._test('function f(){var a = [0, 1, 2, 3, 4, 5, 6, 7, 8]; return [a.pop(), a]}',
-                   [8, [0, 1, 2, 3, 4, 5, 6, 7]])
-        self._test('function f(){return [].pop()}', JS_Undefined)
-        # push
-        self._test('function f(){var a = [0, 1, 2]; return [a.push(3, 4), a]}',
-                   [5, [0, 1, 2, 3, 4]])
-        self._test('function f(){var a = [0, 1, 2]; return [a.push(), a]}',
-                   [3, [0, 1, 2]])
-
-    def test_shift(self):
-        # shift
-        self._test('function f(){var a = [0, 1, 2, 3, 4, 5, 6, 7, 8]; return [a.shift(), a]}',
-                   [0, [1, 2, 3, 4, 5, 6, 7, 8]])
-        self._test('function f(){return [].shift()}', JS_Undefined)
-        # unshift
-        self._test('function f(){var a = [0, 1, 2]; return [a.unshift(3, 4), a]}',
-                   [5, [3, 4, 0, 1, 2]])
-        self._test('function f(){var a = [0, 1, 2]; return [a.unshift(), a]}',
-                   [3, [0, 1, 2]])
-
-    def test_forEach(self):
-        self._test('function f(){var ret = []; var l = [4, 2]; '
-                   'var log = function(e,i,a){ret.push([e,i,a]);}; '
-                   'l.forEach(log); '
-                   'return [ret.length, ret[0][0], ret[1][1], ret[0][2]]}',
-                   [2, 4, 1, [4, 2]])
-        self._test('function f(){var ret = []; var l = [4, 2]; '
-                   'var log = function(e,i,a){this.push([e,i,a]);}; '
-                   'l.forEach(log, ret); '
-                   'return [ret.length, ret[0][0], ret[1][1], ret[0][2]]}',
-                   [2, 4, 1, [4, 2]])
-
-    def test_extract_function(self):
-        jsi = JSInterpreter('function a(b) { return b + 1; }')
-        func = jsi.extract_function('a')
-        self.assertEqual(func([2]), 3)
-
-    def test_extract_function_with_global_stack(self):
-        jsi = JSInterpreter('function c(d) { return d + e + f + g; }')
-        func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
-        self.assertEqual(func([1]), 1111)
-
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -13,7 +12,6 @@ import re
 import string
 
 from youtube_dl.compat import (
-    compat_contextlib_suppress,
     compat_open as open,
     compat_str,
     compat_urlretrieve,
@@ -52,93 +50,23 @@ _SIG_TESTS = [
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
         84,
-        '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>',
+        '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
         83,
-        '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F',
+        '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
         '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
-        '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B',
+        '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
         '312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
         '112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
-    ),
-    (
-        'https://www.youtube.com/s/player/6ed0d907/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'AOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL2QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
-    ),
-    (
-        'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-    ),
-    (
-        'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
-    ),
-    (
-        'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
-    ),
-    (
-        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-    ),
-    (
-        'https://www.youtube.com/s/player/363db69b/player_ias_tce.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-    ),
-    (
-        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
-    ),
-    (
-        'https://www.youtube.com/s/player/4fcd6e4a/player_ias_tce.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player_ias.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player_ias_tce.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
-    ),
-    (
-        'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
-    ),
-    (
-        'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
-        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
-        'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
-    ),
+    )
 ]
 
 _NSIG_TESTS = [
@@ -208,16 +136,12 @@ _NSIG_TESTS = [
     ),
     (
         'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
-        'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
+        '-Txvy6bT5R6LqgnQNx', 'dcklJCnRUHbgSg',
     ),
     (
         'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
         'B2j7f_UPT4rfje85Lu_e', 'm5DmNymaGQ5RdQ',
     ),
-    (
-        'https://www.youtube.com/s/player/7a062b77/player_ias.vflset/en_US/base.js',
-        'NRcE3y3mVtm_cV-W', 'VbsCYUATvqlt5w',
-    ),
     (
         'https://www.youtube.com/s/player/dac945fd/player_ias.vflset/en_US/base.js',
         'o8BkRxXhuYsBCWi6RplPdP', '3Lx32v_hmzTm6A',
@@ -228,11 +152,7 @@ _NSIG_TESTS = [
     ),
     (
         'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
-        'aCi3iElgd2kq0bxVbQ', 'QX1y8jGb2IbZ0w',
-    ),
-    (
-        'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
-        '1wWCVpRR96eAmMI87L', 'KSkWAVv1ZQxC3A',
+        'qO0NiMtYQ7TeJnfFG2', 'k9cuJDHNS5O7kQ',
     ),
     (
         'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
@@ -262,94 +182,6 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
         'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
     ),
-    (
-        'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
-        'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ',
-    ),
-    (
-        'https://www.youtube.com/s/player/f8f53e1a/player_ias.vflset/en_US/base.js',
-        'VTQOUOv0mCIeJ7i8kZB', 'kcfD8wy0sNLyNQ',
-    ),
-    (
-        'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
-        'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
-    ),
-    (
-        'https://www.youtube.com/s/player/9c6dfc4a/player_ias.vflset/en_US/base.js',
-        'jbu7ylIosQHyJyJV', 'uwI0ESiynAmhNg',
-    ),
-    (
-        'https://www.youtube.com/s/player/f6e09c70/player_ias.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
-    ),
-    (
-        'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
-    ),
-    (
-        'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
-        'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
-    ),
-    (
-        'https://www.youtube.com/s/player/d50f54ef/player_ias_tce.vflset/en_US/base.js',
-        'Ha7507LzRmH3Utygtj', 'XFTb2HoeOE5MHg',
-    ),
-    (
-        'https://www.youtube.com/s/player/074a8365/player_ias_tce.vflset/en_US/base.js',
-        'Ha7507LzRmH3Utygtj', 'ufTsrE0IVYrkl8v',
-    ),
-    (
-        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
-        'N5uAlLqm0eg1GyHO', 'dCBQOejdq5s-ww',
-    ),
-    (
-        'https://www.youtube.com/s/player/69f581a5/tv-player-ias.vflset/tv-player-ias.js',
-        '-qIP447rVlTTwaZjY', 'KNcGOksBAvwqQg',
-    ),
-    (
-        'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
-        'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
-    ),
-    (
-        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
-        'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
-    ),
-    (
-        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
-        'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
-    ),
-    (
-        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
-        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
-    ),
-    (
-        'https://www.youtube.com/s/player/4fcd6e4a/tv-player-ias.vflset/tv-player-ias.js',
-        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/tv-player-ias.vflset/tv-player-ias.js',
-        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
-        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
-    ),
-    (
-        'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
-        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
-    ),
-    (
-        'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
-        'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
-    ),
-    (
-        'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
-        'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
-    ),
-    (
-        'https://www.youtube.com/s/player/aa3fc80b/player_ias.vflset/en_US/base.js',
-        '0qY9dal2uzOnOGwa-48hha', 'VSh1KDfQMk-eag',
-    ),
 ]
 
 
@@ -362,8 +194,6 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
-            ('https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js', 'e7567ecf'),
-            ('https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js', '643afba4'),
             # obsolete
             ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
             ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -373,9 +203,8 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
         )
-        ie = YoutubeIE(FakeYDL({'cachedir': False}))
         for player_url, expected_player_id in PLAYER_URLS:
-            player_id = ie._extract_player_info(player_url)
+            player_id = YoutubeIE._extract_player_info(player_url)
             self.assertEqual(player_id, expected_player_id)
 
 
@@ -387,19 +216,21 @@ class TestSignature(unittest.TestCase):
             os.mkdir(self.TESTDATA_DIR)
 
     def tearDown(self):
-        with compat_contextlib_suppress(OSError):
+        try:
             for f in os.listdir(self.TESTDATA_DIR):
                 os.remove(f)
+        except OSError:
+            pass
 
 
 def t_factory(name, sig_func, url_pattern):
     def make_tfunc(url, sig_input, expected_sig):
         m = url_pattern.match(url)
-        assert m, '{0!r} should follow URL format'.format(url)
-        test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
+        assert m, '%r should follow URL format' % url
+        test_id = m.group('id')
 
         def test_func(self):
-            basename = 'player-{0}.js'.format(test_id)
+            basename = 'player-{0}-{1}.js'.format(name, test_id)
             fn = os.path.join(self.TESTDATA_DIR, basename)
 
             if not os.path.exists(fn):
@@ -414,7 +245,7 @@ def t_factory(name, sig_func, url_pattern):
 
 
 def signature(jscode, sig_input):
-    func = YoutubeIE(FakeYDL({'cachedir': False}))._parse_sig_js(jscode)
+    func = YoutubeIE(FakeYDL())._parse_sig_js(jscode)
     src_sig = (
         compat_str(string.printable[:sig_input])
         if isinstance(sig_input, int) else sig_input)
@@ -422,23 +253,17 @@ def signature(jscode, sig_input):
 
 
 def n_sig(jscode, sig_input):
-    ie = YoutubeIE(FakeYDL({'cachedir': False}))
-    jsi = JSInterpreter(jscode)
-    jsi, _, func_code = ie._extract_n_function_code_jsi(sig_input, jsi)
-    return ie._extract_n_function_from_code(jsi, func_code)(sig_input)
+    funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode)
+    return JSInterpreter(jscode).call_function(funcname, sig_input)
 
 
 make_sig_test = t_factory(
-    'signature', signature,
-    re.compile(r'''(?x)
-        .+/(?P<h5>html5)?player(?(h5)(?:-en_US)?-|/)(?P<id>[a-zA-Z0-9/._-]+)
-        (?(h5)/(?:watch_as3|html5player))?\.js$
-    '''))
+    'signature', signature, re.compile(r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$'))
 for test_spec in _SIG_TESTS:
     make_sig_test(*test_spec)
 
 make_nsig_test = t_factory(
-    'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_/.-]+)\.js$'))
+    'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_-]+)/.+.js$'))
 for test_spec in _NSIG_TESTS:
     make_nsig_test(*test_spec)
 

youtube_dl/YoutubeDL.py

@@ -540,14 +540,10 @@ class YoutubeDL(object):
         """Print message to stdout if not in quiet mode."""
         return self.to_stdout(message, skip_eol, check_quiet=True)
 
-    def _write_string(self, s, out=None, only_once=False, _cache=set()):
-        if only_once and s in _cache:
-            return
+    def _write_string(self, s, out=None):
         write_string(s, out=out, encoding=self.params.get('encoding'))
-        if only_once:
-            _cache.add(s)
 
-    def to_stdout(self, message, skip_eol=False, check_quiet=False, only_once=False):
+    def to_stdout(self, message, skip_eol=False, check_quiet=False):
         """Print message to stdout if not in quiet mode."""
         if self.params.get('logger'):
             self.params['logger'].debug(message)
@@ -556,9 +552,9 @@ class YoutubeDL(object):
             terminator = ['\n', ''][skip_eol]
             output = message + terminator
 
-            self._write_string(output, self._screen_file, only_once=only_once)
+            self._write_string(output, self._screen_file)
 
-    def to_stderr(self, message, only_once=False):
+    def to_stderr(self, message):
         """Print message to stderr."""
         assert isinstance(message, compat_str)
         if self.params.get('logger'):
@@ -566,7 +562,7 @@ class YoutubeDL(object):
         else:
             message = self._bidi_workaround(message)
             output = message + '\n'
-            self._write_string(output, self._err_file, only_once=only_once)
+            self._write_string(output, self._err_file)
 
     def to_console_title(self, message):
         if not self.params.get('consoletitle', False):
@@ -645,11 +641,18 @@ class YoutubeDL(object):
             raise DownloadError(message, exc_info)
         self._download_retcode = 1
 
-    def report_warning(self, message, only_once=False):
+    def report_warning(self, message, only_once=False, _cache={}):
         '''
         Print the message to stderr, it will be prefixed with 'WARNING:'
         If stderr is a tty file the 'WARNING:' will be colored
         '''
+        if only_once:
+            m_hash = hash((self, message))
+            m_cnt = _cache.setdefault(m_hash, 0)
+            _cache[m_hash] = m_cnt + 1
+            if m_cnt > 0:
+                return
+
         if self.params.get('logger') is not None:
             self.params['logger'].warning(message)
         else:
@@ -660,7 +663,7 @@ class YoutubeDL(object):
             else:
                 _msg_header = 'WARNING:'
             warning_message = '%s %s' % (_msg_header, message)
-            self.to_stderr(warning_message, only_once=only_once)
+            self.to_stderr(warning_message)
 
     def report_error(self, message, *args, **kwargs):
         '''
@@ -674,16 +677,6 @@ class YoutubeDL(object):
         kwargs['message'] = '%s %s' % (_msg_header, message)
         self.trouble(*args, **kwargs)
 
-    def write_debug(self, message, only_once=False):
-        '''Log debug message or Print message to stderr'''
-        if not self.params.get('verbose', False):
-            return
-        message = '[debug] {0}'.format(message)
-        if self.params.get('logger'):
-            self.params['logger'].debug(message)
-        else:
-            self.to_stderr(message, only_once)
-
     def report_unscoped_cookies(self, *args, **kwargs):
         # message=None, tb=False, is_error=False
         if len(args) <= 2:
@@ -2521,7 +2514,7 @@ class YoutubeDL(object):
                 self.get_encoding()))
         write_string(encoding_str, encoding=None)
 
-        writeln_debug = lambda *s: self.write_debug(''.join(s))
+        writeln_debug = lambda *s: self._write_string('[debug] %s\n' % (''.join(s), ))
         writeln_debug('youtube-dl version ', __version__)
         if _LAZY_LOADER:
             writeln_debug('Lazy loading extractors enabled')

youtube_dl/__init__.py

@@ -18,7 +18,7 @@ from .compat import (
     compat_getpass,
     compat_register_utf8,
     compat_shlex_split,
-    _workaround_optparse_bug9161,
+    workaround_optparse_bug9161,
 )
 from .utils import (
     _UnsafeExtensionError,
@@ -50,7 +50,7 @@ def _real_main(argv=None):
     # Compatibility fix for Windows
     compat_register_utf8()
 
-    _workaround_optparse_bug9161()
+    workaround_optparse_bug9161()
 
     setproctitle('youtube-dl')
 
@@ -409,8 +409,6 @@ def _real_main(argv=None):
         'include_ads': opts.include_ads,
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
-        'youtube_player_js_version': opts.youtube_player_js_version,
-        'youtube_player_js_variant': opts.youtube_player_js_variant,
         'encoding': opts.encoding,
         'extract_flat': opts.extract_flat,
         'mark_watched': opts.mark_watched,

youtube_dl/cache.py

@@ -1,4 +1,3 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
 import errno
@@ -11,14 +10,12 @@ import traceback
 from .compat import (
     compat_getenv,
     compat_open as open,
-    compat_os_makedirs,
 )
 from .utils import (
     error_to_compat_str,
-    escape_rfc3986,
     expand_path,
     is_outdated_version,
-    traverse_obj,
+    try_get,
     write_json_file,
 )
 from .version import __version__
@@ -33,35 +30,23 @@ class Cache(object):
     def __init__(self, ydl):
         self._ydl = ydl
 
-    def _write_debug(self, *args, **kwargs):
-        self._ydl.write_debug(*args, **kwargs)
-
-    def _report_warning(self, *args, **kwargs):
-        self._ydl.report_warning(*args, **kwargs)
-
-    def _to_screen(self, *args, **kwargs):
-        self._ydl.to_screen(*args, **kwargs)
-
-    def _get_param(self, k, default=None):
-        return self._ydl.params.get(k, default)
-
     def _get_root_dir(self):
-        res = self._get_param('cachedir')
+        res = self._ydl.params.get('cachedir')
         if res is None:
             cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
             res = os.path.join(cache_root, self._YTDL_DIR)
         return expand_path(res)
 
     def _get_cache_fn(self, section, key, dtype):
-        assert re.match(r'^[\w.-]+$', section), \
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \
             'invalid section %r' % section
-        key = escape_rfc3986(key, safe='').replace('%', ',')  # encode non-ascii characters
+        assert re.match(r'^[a-zA-Z0-9_.-]+$', key), 'invalid key %r' % key
         return os.path.join(
             self._get_root_dir(), section, '%s.%s' % (key, dtype))
 
     @property
     def enabled(self):
-        return self._get_param('cachedir') is not False
+        return self._ydl.params.get('cachedir') is not False
 
     def store(self, section, key, data, dtype='json'):
         assert dtype in ('json',)
@@ -71,75 +56,61 @@ class Cache(object):
 
         fn = self._get_cache_fn(section, key, dtype)
         try:
-            compat_os_makedirs(os.path.dirname(fn), exist_ok=True)
-            self._write_debug('Saving {section}.{key} to cache'.format(section=section, key=key))
+            try:
+                os.makedirs(os.path.dirname(fn))
+            except OSError as ose:
+                if ose.errno != errno.EEXIST:
+                    raise
             write_json_file({self._VERSION_KEY: __version__, 'data': data}, fn)
         except Exception:
             tb = traceback.format_exc()
-            self._report_warning('Writing cache to {fn!r} failed: {tb}'.format(fn=fn, tb=tb))
-
-    def clear(self, section, key, dtype='json'):
-
-        if not self.enabled:
-            return
-
-        fn = self._get_cache_fn(section, key, dtype)
-        self._write_debug('Clearing {section}.{key} from cache'.format(section=section, key=key))
-        try:
-            os.remove(fn)
-        except Exception as e:
-            if getattr(e, 'errno') == errno.ENOENT:
-                # file not found
-                return
-            tb = traceback.format_exc()
-            self._report_warning('Clearing cache from {fn!r} failed: {tb}'.format(fn=fn, tb=tb))
+            self._ydl.report_warning(
+                'Writing cache to %r failed: %s' % (fn, tb))
 
     def _validate(self, data, min_ver):
-        version = traverse_obj(data, self._VERSION_KEY)
+        version = try_get(data, lambda x: x[self._VERSION_KEY])
         if not version:  # Backward compatibility
             data, version = {'data': data}, self._DEFAULT_VERSION
         if not is_outdated_version(version, min_ver or '0', assume_new=False):
             return data['data']
-        self._write_debug('Discarding old cache from version {version} (needs {min_ver})'.format(version=version, min_ver=min_ver))
+        self._ydl.to_screen(
+            'Discarding old cache from version {version} (needs {min_ver})'.format(**locals()))
 
-    def load(self, section, key, dtype='json', default=None, **kw_min_ver):
+    def load(self, section, key, dtype='json', default=None, min_ver=None):
         assert dtype in ('json',)
-        min_ver = kw_min_ver.get('min_ver')
 
         if not self.enabled:
             return default
 
         cache_fn = self._get_cache_fn(section, key, dtype)
         try:
-            with open(cache_fn, encoding='utf-8') as cachef:
-                self._write_debug('Loading {section}.{key} from cache'.format(section=section, key=key), only_once=True)
-                return self._validate(json.load(cachef), min_ver)
-        except (ValueError, KeyError):
             try:
-                file_size = 'size: %d' % os.path.getsize(cache_fn)
-            except (OSError, IOError) as oe:
-                file_size = error_to_compat_str(oe)
-            self._report_warning('Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
-        except Exception as e:
-            if getattr(e, 'errno') == errno.ENOENT:
-                # no cache available
-                return
-            self._report_warning('Cache retrieval from %s failed' % (cache_fn,))
+                with open(cache_fn, 'r', encoding='utf-8') as cachef:
+                    return self._validate(json.load(cachef), min_ver)
+            except ValueError:
+                try:
+                    file_size = os.path.getsize(cache_fn)
+                except (OSError, IOError) as oe:
+                    file_size = error_to_compat_str(oe)
+                self._ydl.report_warning(
+                    'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
+        except IOError:
+            pass  # No cache available
 
         return default
 
     def remove(self):
         if not self.enabled:
-            self._to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
+            self._ydl.to_screen('Cache is disabled (Did you combine --no-cache-dir and --rm-cache-dir?)')
             return
 
         cachedir = self._get_root_dir()
         if not any((term in cachedir) for term in ('cache', 'tmp')):
-            raise Exception('Not removing directory %s - this does not look like a cache dir' % (cachedir,))
+            raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
 
-        self._to_screen(
-            'Removing cache dir %s .' % (cachedir,), skip_eol=True, ),
+        self._ydl.to_screen(
+            'Removing cache dir %s .' % cachedir, skip_eol=True)
         if os.path.exists(cachedir):
-            self._to_screen('.', skip_eol=True)
+            self._ydl.to_screen('.', skip_eol=True)
             shutil.rmtree(cachedir)
-        self._to_screen('.')
+        self._ydl.to_screen('.')

youtube_dl/casefold.py

@@ -10,10 +10,9 @@ from .compat import (
 # https://github.com/unicode-org/icu/blob/main/icu4c/source/data/unidata/CaseFolding.txt
 # In case newly foldable Unicode characters are defined, paste the new version
 # of the text inside the ''' marks.
-# The text is expected to have only blank lines and lines with 1st character #,
+# The text is expected to have only blank lines andlines with 1st character #,
 # all ignored, and fold definitions like this:
-# `from_hex_code; status; space_separated_to_hex_code_list; comment`
-# Only `status` C/F are used.
+# `from_hex_code; space_separated_to_hex_code_list; comment`
 
 _map_str = '''
 # CaseFolding-15.0.0.txt
@@ -1658,6 +1657,11 @@ _map = dict(
 del _map_str
 
 
-def _casefold(s):
+def casefold(s):
     assert isinstance(s, compat_str)
     return ''.join((_map.get(c, c) for c in s))
+
+
+__all__ = [
+    'casefold',
+]

youtube_dl/compat.py

@@ -16,6 +16,7 @@ import os
 import platform
 import re
 import shlex
+import shutil
 import socket
 import struct
 import subprocess
@@ -23,15 +24,11 @@ import sys
 import types
 import xml.etree.ElementTree
 
-_IDENTITY = lambda x: x
-
 # naming convention
 # 'compat_' + Python3_name.replace('.', '_')
 # other aliases exist for convenience and/or legacy
-# wrap disposable test values in type() to reclaim storage
 
-# deal with critical unicode/str things first:
-# compat_str, compat_basestring, compat_chr
+# deal with critical unicode/str things first
 try:
     # Python 2
     compat_str, compat_basestring, compat_chr = (
@@ -42,23 +39,18 @@ except NameError:
         str, (str, bytes), chr
     )
 
-
-# compat_casefold
+# casefold
 try:
     compat_str.casefold
     compat_casefold = lambda s: s.casefold()
 except AttributeError:
-    from .casefold import _casefold as compat_casefold
+    from .casefold import casefold as compat_casefold
 
-
-# compat_collections_abc
 try:
     import collections.abc as compat_collections_abc
 except ImportError:
     import collections as compat_collections_abc
 
-
-# compat_urllib_request
 try:
     import urllib.request as compat_urllib_request
 except ImportError:  # Python 2
@@ -87,15 +79,11 @@ except TypeError:
     _add_init_method_arg(compat_urllib_request.Request)
     del _add_init_method_arg
 
-
-# compat_urllib_error
 try:
     import urllib.error as compat_urllib_error
 except ImportError:  # Python 2
     import urllib2 as compat_urllib_error
 
-
-# compat_urllib_parse
 try:
     import urllib.parse as compat_urllib_parse
 except ImportError:  # Python 2
@@ -110,23 +98,17 @@ except ImportError:  # Python 2
 compat_urlparse = compat_urllib_parse
 compat_urllib_parse_urlparse = compat_urllib_parse.urlparse
 
-
-# compat_urllib_response
 try:
     import urllib.response as compat_urllib_response
 except ImportError:  # Python 2
     import urllib as compat_urllib_response
 
-
-# compat_urllib_response.addinfourl
 try:
     compat_urllib_response.addinfourl.status
 except AttributeError:
     # .getcode() is deprecated in Py 3.
     compat_urllib_response.addinfourl.status = property(lambda self: self.getcode())
 
-
-# compat_http_cookiejar
 try:
     import http.cookiejar as compat_cookiejar
 except ImportError:  # Python 2
@@ -145,16 +127,12 @@ else:
     compat_cookiejar_Cookie = compat_cookiejar.Cookie
 compat_http_cookiejar_Cookie = compat_cookiejar_Cookie
 
-
-# compat_http_cookies
 try:
     import http.cookies as compat_cookies
 except ImportError:  # Python 2
     import Cookie as compat_cookies
 compat_http_cookies = compat_cookies
 
-
-# compat_http_cookies_SimpleCookie
 if sys.version_info[0] == 2 or sys.version_info < (3, 3):
     class compat_cookies_SimpleCookie(compat_cookies.SimpleCookie):
         def load(self, rawdata):
@@ -177,15 +155,11 @@ else:
     compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
 compat_http_cookies_SimpleCookie = compat_cookies_SimpleCookie
 
-
-# compat_html_entities, probably useless now
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
     import htmlentitydefs as compat_html_entities
 
-
-# compat_html_entities_html5
 try:  # Python >= 3.3
     compat_html_entities_html5 = compat_html_entities.html5
 except AttributeError:
@@ -2434,24 +2408,18 @@ except AttributeError:
     # Py < 3.1
     compat_http_client.HTTPResponse.getcode = lambda self: self.status
 
-
-# compat_urllib_HTTPError
 try:
     from urllib.error import HTTPError as compat_HTTPError
 except ImportError:  # Python 2
     from urllib2 import HTTPError as compat_HTTPError
 compat_urllib_HTTPError = compat_HTTPError
 
-
-# compat_urllib_request_urlretrieve
 try:
     from urllib.request import urlretrieve as compat_urlretrieve
 except ImportError:  # Python 2
     from urllib import urlretrieve as compat_urlretrieve
 compat_urllib_request_urlretrieve = compat_urlretrieve
 
-
-# compat_html_parser_HTMLParser, compat_html_parser_HTMLParseError
 try:
     from HTMLParser import (
         HTMLParser as compat_HTMLParser,
@@ -2464,33 +2432,22 @@ except ImportError:  # Python 3
         # HTMLParseError was deprecated in Python 3.3 and removed in
         # Python 3.5. Introducing dummy exception for Python >3.5 for compatible
         # and uniform cross-version exception handling
-
         class compat_HTMLParseError(Exception):
             pass
-
 compat_html_parser_HTMLParser = compat_HTMLParser
 compat_html_parser_HTMLParseError = compat_HTMLParseError
 
-
-# compat_subprocess_get_DEVNULL
 try:
     _DEVNULL = subprocess.DEVNULL
     compat_subprocess_get_DEVNULL = lambda: _DEVNULL
 except AttributeError:
     compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
 
-
-# compat_http_server
 try:
     import http.server as compat_http_server
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
-
-# compat_urllib_parse_unquote_to_bytes,
-# compat_urllib_parse_unquote, compat_urllib_parse_unquote_plus,
-# compat_urllib_parse_urlencode,
-# compat_urllib_parse_parse_qs
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
@@ -2498,7 +2455,8 @@ try:
     from urllib.parse import urlencode as compat_urllib_parse_urlencode
     from urllib.parse import parse_qs as compat_parse_qs
 except ImportError:  # Python 2
-    _asciire = getattr(compat_urllib_parse, '_asciire', None) or re.compile(r'([\x00-\x7f]+)')
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile(r'([\x00-\x7f]+)'))
 
     # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
@@ -2566,21 +2524,24 @@ except ImportError:  # Python 2
     # Possible solutions are to either port it from python 3 with all
     # the friends or manually ensure input query contains only byte strings.
     # We will stick with latter thus recursively encoding the whole query.
-    def compat_urllib_parse_urlencode(query, doseq=0, safe='', encoding='utf-8', errors='strict'):
-
+    def compat_urllib_parse_urlencode(query, doseq=0, encoding='utf-8'):
         def encode_elem(e):
             if isinstance(e, dict):
                 e = encode_dict(e)
             elif isinstance(e, (list, tuple,)):
-                e = type(e)(encode_elem(el) for el in e)
+                list_e = encode_list(e)
+                e = tuple(list_e) if isinstance(e, tuple) else list_e
             elif isinstance(e, compat_str):
-                e = e.encode(encoding, errors)
+                e = e.encode(encoding)
             return e
 
         def encode_dict(d):
-            return tuple((encode_elem(k), encode_elem(v)) for k, v in d.items())
+            return dict((encode_elem(k), encode_elem(v)) for k, v in d.items())
 
-        return compat_urllib_parse._urlencode(encode_elem(query), doseq=doseq).decode('ascii')
+        def encode_list(l):
+            return [encode_elem(e) for e in l]
+
+        return compat_urllib_parse._urlencode(encode_elem(query), doseq=doseq)
 
     # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
     # Python 2's version is apparently totally broken
@@ -2635,61 +2596,8 @@ except ImportError:  # Python 2
             ('parse_qs', compat_parse_qs)):
         setattr(compat_urllib_parse, name, fix)
 
-    try:
-        all(chr(i) in b'' for i in range(256))
-    except TypeError:
-        # not all chr(i) are str: patch Python2 quote
-
-        _safemaps = getattr(compat_urllib_parse, '_safemaps', {})
-        _always_safe = frozenset(compat_urllib_parse.always_safe)
-
-        def _quote(s, safe='/'):
-            """quote('abc def') -> 'abc%20def'"""
-
-            if not s and s is not None:  # fast path
-                return s
-            safe = frozenset(safe)
-            cachekey = (safe, _always_safe)
-            try:
-                safe_map = _safemaps[cachekey]
-            except KeyError:
-                safe = _always_safe | safe
-                safe_map = {}
-                for i in range(256):
-                    c = chr(i)
-                    safe_map[c] = (
-                        c if (i < 128 and c in safe)
-                        else b'%{0:02X}'.format(i))
-                _safemaps[cachekey] = safe_map
-
-            if safe.issuperset(s):
-                return s
-            return ''.join(safe_map[c] for c in s)
-
-        # linked code
-        def _quote_plus(s, safe=''):
-            return (
-                _quote(s, safe + b' ').replace(b' ', b'+') if b' ' in s
-                else _quote(s, safe))
-
-        # linked code
-        def _urlcleanup():
-            if compat_urllib_parse._urlopener:
-                compat_urllib_parse._urlopener.cleanup()
-            _safemaps.clear()
-            compat_urllib_parse.ftpcache.clear()
-
-        for name, fix in (
-                ('quote', _quote),
-                ('quote_plus', _quote_plus),
-                ('urlcleanup', _urlcleanup)):
-            setattr(compat_urllib_parse, '_' + name, getattr(compat_urllib_parse, name))
-            setattr(compat_urllib_parse, name, fix)
-
 compat_urllib_parse_parse_qs = compat_parse_qs
 
-
-# compat_urllib_request_DataHandler
 try:
     from urllib.request import DataHandler as compat_urllib_request_DataHandler
 except ImportError:  # Python < 3.4
@@ -2724,20 +2632,16 @@ except ImportError:  # Python < 3.4
 
             return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
 
-
-# compat_xml_etree_ElementTree_ParseError
 try:
     from xml.etree.ElementTree import ParseError as compat_xml_parse_error
 except ImportError:  # Python 2.6
     from xml.parsers.expat import ExpatError as compat_xml_parse_error
 compat_xml_etree_ElementTree_ParseError = compat_xml_parse_error
 
-
-# compat_xml_etree_ElementTree_Element
-_etree = xml.etree.ElementTree
+etree = xml.etree.ElementTree
 
 
-class _TreeBuilder(_etree.TreeBuilder):
+class _TreeBuilder(etree.TreeBuilder):
     def doctype(self, name, pubid, system):
         pass
 
@@ -2746,7 +2650,7 @@ try:
     # xml.etree.ElementTree.Element is a method in Python <=2.6 and
     # the following will crash with:
     #  TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types
-    isinstance(None, _etree.Element)
+    isinstance(None, etree.Element)
     from xml.etree.ElementTree import Element as compat_etree_Element
 except TypeError:  # Python <=2.6
     from xml.etree.ElementTree import _ElementInterface as compat_etree_Element
@@ -2754,12 +2658,12 @@ compat_xml_etree_ElementTree_Element = compat_etree_Element
 
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
-        return _etree.XML(text, parser=_etree.XMLParser(target=_TreeBuilder()))
+        return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
 else:
     # python 2.x tries to encode unicode strings with ascii (see the
     # XMLParser._fixtext method)
     try:
-        _etree_iter = _etree.Element.iter
+        _etree_iter = etree.Element.iter
     except AttributeError:  # Python <=2.6
         def _etree_iter(root):
             for el in root.findall('*'):
@@ -2771,29 +2675,27 @@ else:
     # 2.7 source
     def _XML(text, parser=None):
         if not parser:
-            parser = _etree.XMLParser(target=_TreeBuilder())
+            parser = etree.XMLParser(target=_TreeBuilder())
         parser.feed(text)
         return parser.close()
 
     def _element_factory(*args, **kwargs):
-        el = _etree.Element(*args, **kwargs)
+        el = etree.Element(*args, **kwargs)
         for k, v in el.items():
             if isinstance(v, bytes):
                 el.set(k, v.decode('utf-8'))
         return el
 
     def compat_etree_fromstring(text):
-        doc = _XML(text, parser=_etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory)))
+        doc = _XML(text, parser=etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory)))
         for el in _etree_iter(doc):
             if el.text is not None and isinstance(el.text, bytes):
                 el.text = el.text.decode('utf-8')
         return doc
 
-
-# compat_xml_etree_register_namespace
-try:
-    compat_etree_register_namespace = _etree.register_namespace
-except AttributeError:
+if hasattr(etree, 'register_namespace'):
+    compat_etree_register_namespace = etree.register_namespace
+else:
     def compat_etree_register_namespace(prefix, uri):
         """Register a namespace prefix.
         The registry is global, and any existing mapping for either the
@@ -2802,16 +2704,14 @@ except AttributeError:
         attributes in this namespace will be serialized with prefix if possible.
         ValueError is raised if prefix is reserved or is invalid.
         """
-        if re.match(r'ns\d+$', prefix):
-            raise ValueError('Prefix format reserved for internal use')
-        for k, v in list(_etree._namespace_map.items()):
+        if re.match(r"ns\d+$", prefix):
+            raise ValueError("Prefix format reserved for internal use")
+        for k, v in list(etree._namespace_map.items()):
             if k == uri or v == prefix:
-                del _etree._namespace_map[k]
-        _etree._namespace_map[uri] = prefix
+                del etree._namespace_map[k]
+        etree._namespace_map[uri] = prefix
 compat_xml_etree_register_namespace = compat_etree_register_namespace
 
-
-# compat_xpath, compat_etree_iterfind
 if sys.version_info < (2, 7):
     # Here comes the crazy part: In 2.6, if the xpath is a unicode,
     # .//node does not match if a node is a direct child of . !
@@ -2998,6 +2898,7 @@ if sys.version_info < (2, 7):
         def __init__(self, root):
             self.root = root
 
+    ##
     # Generate all matching objects.
 
     def compat_etree_iterfind(elem, path, namespaces=None):
@@ -3032,15 +2933,13 @@ if sys.version_info < (2, 7):
 
 
 else:
+    compat_xpath = lambda xpath: xpath
     compat_etree_iterfind = lambda element, match: element.iterfind(match)
-    compat_xpath = _IDENTITY
 
 
-# compat_os_name
 compat_os_name = os._name if os.name == 'java' else os.name
 
 
-# compat_shlex_quote
 if compat_os_name == 'nt':
     def compat_shlex_quote(s):
         return s if re.match(r'^[-_\w./]+$', s) else '"%s"' % s.replace('"', '\\"')
@@ -3055,7 +2954,6 @@ else:
                 return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
-# compat_shlex.split
 try:
     args = shlex.split('中文')
     assert (isinstance(args, list)
@@ -3071,7 +2969,6 @@ except (AssertionError, UnicodeEncodeError):
         return list(map(lambda s: s.decode('utf-8'), shlex.split(s, comments, posix)))
 
 
-# compat_ord
 def compat_ord(c):
     if isinstance(c, int):
         return c
@@ -3079,7 +2976,6 @@ def compat_ord(c):
         return ord(c)
 
 
-# compat_getenv, compat_os_path_expanduser, compat_setenv
 if sys.version_info >= (3, 0):
     compat_getenv = os.getenv
     compat_expanduser = os.path.expanduser
@@ -3167,22 +3063,6 @@ else:
 compat_os_path_expanduser = compat_expanduser
 
 
-# compat_os_makedirs
-try:
-    os.makedirs('.', exist_ok=True)
-    compat_os_makedirs = os.makedirs
-except TypeError:  # < Py3.2
-    from errno import EEXIST as _errno_EEXIST
-
-    def compat_os_makedirs(name, mode=0o777, exist_ok=False):
-        try:
-            return os.makedirs(name, mode=mode)
-        except OSError as ose:
-            if not (exist_ok and ose.errno == _errno_EEXIST):
-                raise
-
-
-# compat_os_path_realpath
 if compat_os_name == 'nt' and sys.version_info < (3, 8):
     # os.path.realpath on Windows does not follow symbolic links
     # prior to Python 3.8 (see https://bugs.python.org/issue9949)
@@ -3196,7 +3076,6 @@ else:
 compat_os_path_realpath = compat_realpath
 
 
-# compat_print
 if sys.version_info < (3, 0):
     def compat_print(s):
         from .utils import preferredencoding
@@ -3207,7 +3086,6 @@ else:
         print(s)
 
 
-# compat_getpass_getpass
 if sys.version_info < (3, 0) and sys.platform == 'win32':
     def compat_getpass(prompt, *args, **kwargs):
         if isinstance(prompt, compat_str):
@@ -3220,42 +3098,36 @@ else:
 compat_getpass_getpass = compat_getpass
 
 
-# compat_input
 try:
     compat_input = raw_input
 except NameError:  # Python 3
     compat_input = input
 
 
-# compat_kwargs
 # Python < 2.6.5 require kwargs to be bytes
 try:
-    (lambda x: x)(**{'x': 0})
+    def _testfunc(x):
+        pass
+    _testfunc(**{'x': 0})
 except TypeError:
     def compat_kwargs(kwargs):
         return dict((bytes(k), v) for k, v in kwargs.items())
 else:
-    compat_kwargs = _IDENTITY
+    compat_kwargs = lambda kwargs: kwargs
 
 
-# compat_numeric_types
 try:
     compat_numeric_types = (int, float, long, complex)
 except NameError:  # Python 3
     compat_numeric_types = (int, float, complex)
 
 
-# compat_integer_types
 try:
     compat_integer_types = (int, long)
 except NameError:  # Python 3
     compat_integer_types = (int, )
 
-# compat_int
-compat_int = compat_integer_types[-1]
 
-
-# compat_socket_create_connection
 if sys.version_info < (2, 7):
     def compat_socket_create_connection(address, timeout, source_address=None):
         host, port = address
@@ -3282,7 +3154,6 @@ else:
     compat_socket_create_connection = socket.create_connection
 
 
-# compat_contextlib_suppress
 try:
     from contextlib import suppress as compat_contextlib_suppress
 except ImportError:
@@ -3325,12 +3196,12 @@ except AttributeError:
                         # repeated .close() is OK, but just in case
                         with compat_contextlib_suppress(EnvironmentError):
                             f.close()
-            popen.wait()
+                popen.wait()
 
 
 # Fix https://github.com/ytdl-org/youtube-dl/issues/4223
 # See http://bugs.python.org/issue9161 for what is broken
-def _workaround_optparse_bug9161():
+def workaround_optparse_bug9161():
     op = optparse.OptionParser()
     og = optparse.OptionGroup(op, 'foo')
     try:
@@ -3349,10 +3220,9 @@ def _workaround_optparse_bug9161():
         optparse.OptionGroup.add_option = _compat_add_option
 
 
-# compat_shutil_get_terminal_size
-try:
-    from shutil import get_terminal_size as compat_get_terminal_size  # Python >= 3.3
-except ImportError:
+if hasattr(shutil, 'get_terminal_size'):  # Python >= 3.3
+    compat_get_terminal_size = shutil.get_terminal_size
+else:
     _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
 
     def compat_get_terminal_size(fallback=(80, 24)):
@@ -3382,33 +3252,27 @@ except ImportError:
                 columns = _columns
             if lines is None or lines <= 0:
                 lines = _lines
-
         return _terminal_size(columns, lines)
 
-compat_shutil_get_terminal_size = compat_get_terminal_size
 
-
-# compat_itertools_count
 try:
-    type(itertools.count(start=0, step=1))
+    itertools.count(start=0, step=1)
     compat_itertools_count = itertools.count
-except TypeError:  # Python 2.6 lacks step
+except TypeError:  # Python 2.6
     def compat_itertools_count(start=0, step=1):
         while True:
             yield start
             start += step
 
 
-# compat_tokenize_tokenize
 if sys.version_info >= (3, 0):
     from tokenize import tokenize as compat_tokenize_tokenize
 else:
     from tokenize import generate_tokens as compat_tokenize_tokenize
 
 
-# compat_struct_pack, compat_struct_unpack, compat_Struct
 try:
-    type(struct.pack('!I', 0))
+    struct.pack('!I', 0)
 except TypeError:
     # In Python 2.6 and 2.7.x < 2.7.7, struct requires a bytes argument
     # See https://bugs.python.org/issue19099
@@ -3440,10 +3304,8 @@ else:
         compat_Struct = struct.Struct
 
 
-# builtins returning an iterator
-
-# compat_map, compat_filter
-# supposedly the same versioning as for zip below
+# compat_map/filter() returning an iterator, supposedly the
+# same versioning as for zip below
 try:
     from future_builtins import map as compat_map
 except ImportError:
@@ -3460,7 +3322,6 @@ except ImportError:
     except ImportError:
         compat_filter = filter
 
-# compat_zip
 try:
     from future_builtins import zip as compat_zip
 except ImportError:  # not 2.6+ or is 3.x
@@ -3470,7 +3331,6 @@ except ImportError:  # not 2.6+ or is 3.x
         compat_zip = zip
 
 
-# compat_itertools_zip_longest
 # method renamed between Py2/3
 try:
     from itertools import zip_longest as compat_itertools_zip_longest
@@ -3478,8 +3338,7 @@ except ImportError:
     from itertools import izip_longest as compat_itertools_zip_longest
 
 
-# compat_collections_chain_map
-# collections.ChainMap: new class
+# new class in collections
 try:
     from collections import ChainMap as compat_collections_chain_map
     # Py3.3's ChainMap is deficient
@@ -3535,22 +3394,19 @@ except ImportError:
         def new_child(self, m=None, **kwargs):
             m = m or {}
             m.update(kwargs)
-            # support inheritance !
-            return type(self)(m, *self.maps)
+            return compat_collections_chain_map(m, *self.maps)
 
         @property
         def parents(self):
-            return type(self)(*(self.maps[1:]))
+            return compat_collections_chain_map(*(self.maps[1:]))
 
 
-# compat_re_Pattern, compat_re_Match
 # Pythons disagree on the type of a pattern (RegexObject, _sre.SRE_Pattern, Pattern, ...?)
 compat_re_Pattern = type(re.compile(''))
 # and on the type of a match
 compat_re_Match = type(re.match('a', 'a'))
 
 
-# compat_base64_b64decode
 if sys.version_info < (3, 3):
     def compat_b64decode(s, *args, **kwargs):
         if isinstance(s, compat_str):
@@ -3562,7 +3418,6 @@ else:
 compat_base64_b64decode = compat_b64decode
 
 
-# compat_ctypes_WINFUNCTYPE
 if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0):
     # PyPy2 prior to version 5.4.0 expects byte strings as Windows function
     # names, see the original PyPy issue [1] and the youtube-dl one [2].
@@ -3581,7 +3436,6 @@ else:
         return ctypes.WINFUNCTYPE(*args, **kwargs)
 
 
-# compat_open
 if sys.version_info < (3, 0):
     # open(file, mode='r', buffering=- 1, encoding=None, errors=None, newline=None, closefd=True) not: opener=None
     def compat_open(file_, *args, **kwargs):
@@ -3609,28 +3463,18 @@ except AttributeError:
     def compat_datetime_timedelta_total_seconds(td):
         return (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
 
-
 # optional decompression packages
-# compat_brotli
 # PyPi brotli package implements 'br' Content-Encoding
 try:
     import brotli as compat_brotli
 except ImportError:
     compat_brotli = None
-# compat_ncompress
 # PyPi ncompress package implements 'compress' Content-Encoding
 try:
     import ncompress as compat_ncompress
 except ImportError:
     compat_ncompress = None
 
-# compat_zstandard
-# PyPi zstandard package implements 'zstd' Content-Encoding (RFC 8878 7.2)
-try:
-    import zstandard as compat_zstandard
-except ImportError:
-    compat_zstandard = None
-
 
 legacy = [
     'compat_HTMLParseError',
@@ -3647,7 +3491,6 @@ legacy = [
     'compat_getpass',
     'compat_parse_qs',
     'compat_realpath',
-    'compat_shlex_split',
     'compat_urllib_parse_parse_qs',
     'compat_urllib_parse_unquote',
     'compat_urllib_parse_unquote_plus',
@@ -3661,6 +3504,8 @@ legacy = [
 
 
 __all__ = [
+    'compat_html_parser_HTMLParseError',
+    'compat_html_parser_HTMLParser',
     'compat_Struct',
     'compat_base64_b64decode',
     'compat_basestring',
@@ -3669,9 +3514,13 @@ __all__ = [
     'compat_chr',
     'compat_collections_abc',
     'compat_collections_chain_map',
+    'compat_datetime_timedelta_total_seconds',
+    'compat_http_cookiejar',
+    'compat_http_cookiejar_Cookie',
+    'compat_http_cookies',
+    'compat_http_cookies_SimpleCookie',
     'compat_contextlib_suppress',
     'compat_ctypes_WINFUNCTYPE',
-    'compat_datetime_timedelta_total_seconds',
     'compat_etree_fromstring',
     'compat_etree_iterfind',
     'compat_filter',
@@ -3680,16 +3529,9 @@ __all__ = [
     'compat_getpass_getpass',
     'compat_html_entities',
     'compat_html_entities_html5',
-    'compat_html_parser_HTMLParseError',
-    'compat_html_parser_HTMLParser',
-    'compat_http_cookiejar',
-    'compat_http_cookiejar_Cookie',
-    'compat_http_cookies',
-    'compat_http_cookies_SimpleCookie',
     'compat_http_client',
     'compat_http_server',
     'compat_input',
-    'compat_int',
     'compat_integer_types',
     'compat_itertools_count',
     'compat_itertools_zip_longest',
@@ -3699,7 +3541,6 @@ __all__ = [
     'compat_numeric_types',
     'compat_open',
     'compat_ord',
-    'compat_os_makedirs',
     'compat_os_name',
     'compat_os_path_expanduser',
     'compat_os_path_realpath',
@@ -3709,7 +3550,7 @@ __all__ = [
     'compat_register_utf8',
     'compat_setenv',
     'compat_shlex_quote',
-    'compat_shutil_get_terminal_size',
+    'compat_shlex_split',
     'compat_socket_create_connection',
     'compat_str',
     'compat_struct_pack',
@@ -3729,5 +3570,5 @@ __all__ = [
     'compat_xml_etree_register_namespace',
     'compat_xpath',
     'compat_zip',
-    'compat_zstandard',
+    'workaround_optparse_bug9161',
 ]

youtube_dl/downloader/common.py

@@ -11,7 +11,6 @@ from ..utils import (
     decodeArgument,
     encodeFilename,
     error_to_compat_str,
-    float_or_none,
     format_bytes,
     shell_quote,
     timeconvert,
@@ -368,27 +367,14 @@ class FileDownloader(object):
                 })
                 return True
 
-        min_sleep_interval, max_sleep_interval = (
-            float_or_none(self.params.get(interval), default=0)
-            for interval in ('sleep_interval', 'max_sleep_interval'))
-
-        sleep_note = ''
-        available_at = info_dict.get('available_at')
-        if available_at:
-            forced_sleep_interval = available_at - int(time.time())
-            if forced_sleep_interval > min_sleep_interval:
-                sleep_note = 'as required by the site'
-                min_sleep_interval = forced_sleep_interval
-            if forced_sleep_interval > max_sleep_interval:
-                max_sleep_interval = forced_sleep_interval
-
-        sleep_interval = random.uniform(
-            min_sleep_interval, max_sleep_interval or min_sleep_interval)
-
-        if sleep_interval > 0:
+        min_sleep_interval = self.params.get('sleep_interval')
+        if min_sleep_interval:
+            max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
+            sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
             self.to_screen(
-                '[download] Sleeping %.2f seconds %s...' % (
-                    sleep_interval, sleep_note))
+                '[download] Sleeping %s seconds...' % (
+                    int(sleep_interval) if sleep_interval.is_integer()
+                    else '%.2f' % sleep_interval))
             time.sleep(sleep_interval)
 
         return self.real_download(filename, info_dict)

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    IE_DESC = 'CC视频'
+    _IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    IE_DESC = 'cloudy.ec'
+    _IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,8 +422,6 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
-    # supply this in public subclasses: used in supported sites list, etc
-    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""
@@ -505,7 +503,7 @@ class InfoExtractor(object):
         if not self._x_forwarded_for_ip:
 
             # Geo bypass mechanism is explicitly disabled by user
-            if not self.get_param('geo_bypass', True):
+            if not self._downloader.params.get('geo_bypass', True):
                 return
 
             if not geo_bypass_context:
@@ -527,7 +525,7 @@ class InfoExtractor(object):
 
             # Explicit IP block specified by user, use it right away
             # regardless of whether extractor is geo bypassable or not
-            ip_block = self.get_param('geo_bypass_ip_block', None)
+            ip_block = self._downloader.params.get('geo_bypass_ip_block', None)
 
             # Otherwise use random IP block from geo bypass context but only
             # if extractor is known as geo bypassable
@@ -538,8 +536,8 @@ class InfoExtractor(object):
 
             if ip_block:
                 self._x_forwarded_for_ip = GeoUtils.random_ipv4(ip_block)
-                if self.get_param('verbose', False):
-                    self.to_screen(
+                if self._downloader.params.get('verbose', False):
+                    self._downloader.to_screen(
                         '[debug] Using fake IP %s as X-Forwarded-For.'
                         % self._x_forwarded_for_ip)
                 return
@@ -548,7 +546,7 @@ class InfoExtractor(object):
 
             # Explicit country code specified by user, use it right away
             # regardless of whether extractor is geo bypassable or not
-            country = self.get_param('geo_bypass_country', None)
+            country = self._downloader.params.get('geo_bypass_country', None)
 
             # Otherwise use random country code from geo bypass context but
             # only if extractor is known as geo bypassable
@@ -559,8 +557,8 @@ class InfoExtractor(object):
 
             if country:
                 self._x_forwarded_for_ip = GeoUtils.random_ipv4(country)
-                if self.get_param('verbose', False):
-                    self.to_screen(
+                if self._downloader.params.get('verbose', False):
+                    self._downloader.to_screen(
                         '[debug] Using fake IP %s (%s) as X-Forwarded-For.'
                         % (self._x_forwarded_for_ip, country.upper()))
 
@@ -586,9 +584,9 @@ class InfoExtractor(object):
             raise ExtractorError('An extractor error has occurred.', cause=e)
 
     def __maybe_fake_ip_and_retry(self, countries):
-        if (not self.get_param('geo_bypass_country', None)
+        if (not self._downloader.params.get('geo_bypass_country', None)
                 and self._GEO_BYPASS
-                and self.get_param('geo_bypass', True)
+                and self._downloader.params.get('geo_bypass', True)
                 and not self._x_forwarded_for_ip
                 and countries):
             country_code = random.choice(countries)
@@ -698,7 +696,7 @@ class InfoExtractor(object):
             if fatal:
                 raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
             else:
-                self.report_warning(errmsg)
+                self._downloader.report_warning(errmsg)
                 return False
 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
@@ -770,11 +768,11 @@ class InfoExtractor(object):
             webpage_bytes = prefix + webpage_bytes
         if not encoding:
             encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
-        if self.get_param('dump_intermediate_pages', False):
+        if self._downloader.params.get('dump_intermediate_pages', False):
             self.to_screen('Dumping request to ' + urlh.geturl())
             dump = base64.b64encode(webpage_bytes).decode('ascii')
-            self.to_screen(dump)
-        if self.get_param('write_pages', False):
+            self._downloader.to_screen(dump)
+        if self._downloader.params.get('write_pages', False):
             basen = '%s_%s' % (video_id, urlh.geturl())
             if len(basen) > 240:
                 h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
@@ -976,9 +974,19 @@ class InfoExtractor(object):
         """Print msg to screen, prefixing it with '[ie_name]'"""
         self._downloader.to_screen(self.__ie_msg(msg))
 
-    def write_debug(self, msg, only_once=False):
+    def write_debug(self, msg, only_once=False, _cache=[]):
         '''Log debug message or Print message to stderr'''
-        self._downloader.write_debug(self.__ie_msg(msg), only_once=only_once)
+        if not self.get_param('verbose', False):
+            return
+        message = '[debug] ' + self.__ie_msg(msg)
+        logger = self.get_param('logger')
+        if logger:
+            logger.debug(message)
+        else:
+            if only_once and hash(message) in _cache:
+                return
+            self._downloader.to_stderr(message)
+            _cache.append(hash(message))
 
     # name, default=None, *args, **kwargs
     def get_param(self, name, *args, **kwargs):
@@ -1074,7 +1082,7 @@ class InfoExtractor(object):
                 if mobj:
                     break
 
-        if not self.get_param('no_color') and compat_os_name != 'nt' and sys.stderr.isatty():
+        if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty():
             _name = '\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -1092,7 +1100,7 @@ class InfoExtractor(object):
         elif fatal:
             raise RegexNotFoundError('Unable to extract %s' % _name)
         else:
-            self.report_warning('unable to extract %s' % _name + bug_reports_message())
+            self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
             return None
 
     def _search_json(self, start_pattern, string, name, video_id, **kwargs):
@@ -1162,7 +1170,7 @@ class InfoExtractor(object):
         username = None
         password = None
 
-        if self.get_param('usenetrc', False):
+        if self._downloader.params.get('usenetrc', False):
             try:
                 netrc_machine = netrc_machine or self._NETRC_MACHINE
                 info = netrc.netrc().authenticators(netrc_machine)
@@ -1173,7 +1181,7 @@ class InfoExtractor(object):
                     raise netrc.NetrcParseError(
                         'No authenticators for %s' % netrc_machine)
             except (AttributeError, IOError, netrc.NetrcParseError) as err:
-                self.report_warning(
+                self._downloader.report_warning(
                     'parsing .netrc: %s' % error_to_compat_str(err))
 
         return username, password
@@ -1210,10 +1218,10 @@ class InfoExtractor(object):
         """
         if self._downloader is None:
             return None
+        downloader_params = self._downloader.params
 
-        twofactor = self.get_param('twofactor')
-        if twofactor is not None:
-            return twofactor
+        if downloader_params.get('twofactor') is not None:
+            return downloader_params['twofactor']
 
         return compat_getpass('Type %s and press [Return]: ' % note)
 
@@ -1348,7 +1356,7 @@ class InfoExtractor(object):
         elif fatal:
             raise RegexNotFoundError('Unable to extract JSON-LD')
         else:
-            self.report_warning('unable to extract JSON-LD %s' % bug_reports_message())
+            self._downloader.report_warning('unable to extract JSON-LD %s' % bug_reports_message())
             return {}
 
     def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
@@ -1579,7 +1587,7 @@ class InfoExtractor(object):
 
             if f.get('vcodec') == 'none':  # audio only
                 preference -= 50
-                if self.get_param('prefer_free_formats'):
+                if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
                     ORDER = ['webm', 'opus', 'ogg', 'mp3', 'aac', 'm4a']
@@ -1591,7 +1599,7 @@ class InfoExtractor(object):
             else:
                 if f.get('acodec') == 'none':  # video only
                     preference -= 40
-                if self.get_param('prefer_free_formats'):
+                if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['flv', 'mp4', 'webm']
                 else:
                     ORDER = ['webm', 'flv', 'mp4']
@@ -1657,7 +1665,7 @@ class InfoExtractor(object):
         """ Either "http:" or "https:", depending on the user's preferences """
         return (
             'http:'
-            if self.get_param('prefer_insecure', False)
+            if self._downloader.params.get('prefer_insecure', False)
             else 'https:')
 
     def _proto_relative_url(self, url, scheme=None):
@@ -3162,7 +3170,7 @@ class InfoExtractor(object):
                     # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
                     # of jwplayer.flash.swf
                     rtmp_url_parts = re.split(
-                        r'((?:mp4|mp3|flv):)', source_url, maxsplit=1)
+                        r'((?:mp4|mp3|flv):)', source_url, 1)
                     if len(rtmp_url_parts) == 3:
                         rtmp_url, prefix, play_path = rtmp_url_parts
                         a_format.update({
@@ -3189,7 +3197,7 @@ class InfoExtractor(object):
             if fatal:
                 raise ExtractorError(msg)
             else:
-                self.report_warning(msg)
+                self._downloader.report_warning(msg)
         return res
 
     def _float(self, v, name, fatal=False, **kwargs):
@@ -3199,7 +3207,7 @@ class InfoExtractor(object):
             if fatal:
                 raise ExtractorError(msg)
             else:
-                self.report_warning(msg)
+                self._downloader.report_warning(msg)
         return res
 
     def _set_cookie(self, domain, name, value, expire_time=None, port=None,
@@ -3208,12 +3216,12 @@ class InfoExtractor(object):
             0, name, value, port, port is not None, domain, True,
             domain.startswith('.'), path, True, secure, expire_time,
             discard, None, None, rest)
-        self.cookiejar.set_cookie(cookie)
+        self._downloader.cookiejar.set_cookie(cookie)
 
     def _get_cookies(self, url):
         """ Return a compat_cookies_SimpleCookie with the cookies for the url """
         req = sanitized_Request(url)
-        self.cookiejar.add_cookie_header(req)
+        self._downloader.cookiejar.add_cookie_header(req)
         return compat_cookies_SimpleCookie(req.get_header('Cookie'))
 
     def _apply_first_set_cookie_header(self, url_handle, cookie):
@@ -3273,8 +3281,8 @@ class InfoExtractor(object):
         return not any_restricted
 
     def extract_subtitles(self, *args, **kwargs):
-        if (self.get_param('writesubtitles', False)
-                or self.get_param('listsubtitles')):
+        if (self._downloader.params.get('writesubtitles', False)
+                or self._downloader.params.get('listsubtitles')):
             return self._get_subtitles(*args, **kwargs)
         return {}
 
@@ -3295,11 +3303,7 @@ class InfoExtractor(object):
         """ Merge subtitle dictionaries, language by language. """
 
         # ..., * , target=None
-        target = kwargs.get('target')
-        if target is None:
-            target = dict(subtitle_dict1)
-        else:
-            subtitle_dicts = (subtitle_dict1,) + subtitle_dicts
+        target = kwargs.get('target') or dict(subtitle_dict1)
 
         for subtitle_dict in subtitle_dicts:
             for lang in subtitle_dict:
@@ -3307,8 +3311,8 @@ class InfoExtractor(object):
         return target
 
     def extract_automatic_captions(self, *args, **kwargs):
-        if (self.get_param('writeautomaticsub', False)
-                or self.get_param('listsubtitles')):
+        if (self._downloader.params.get('writeautomaticsub', False)
+                or self._downloader.params.get('listsubtitles')):
             return self._get_automatic_captions(*args, **kwargs)
         return {}
 
@@ -3316,9 +3320,9 @@ class InfoExtractor(object):
         raise NotImplementedError('This method must be implemented by subclasses')
 
     def mark_watched(self, *args, **kwargs):
-        if (self.get_param('mark_watched', False)
+        if (self._downloader.params.get('mark_watched', False)
                 and (self._get_login_info()[0] is not None
-                     or self.get_param('cookiefile') is not None)):
+                     or self._downloader.params.get('cookiefile') is not None)):
             self._mark_watched(*args, **kwargs)
 
     def _mark_watched(self, *args, **kwargs):
@@ -3326,7 +3330,7 @@ class InfoExtractor(object):
 
     def geo_verification_headers(self):
         headers = {}
-        geo_verification_proxy = self.get_param('geo_verification_proxy')
+        geo_verification_proxy = self._downloader.params.get('geo_verification_proxy')
         if geo_verification_proxy:
             headers['Ytdl-request-proxy'] = geo_verification_proxy
         return headers

youtube_dl/extractor/itv.py

@@ -35,6 +35,15 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
+    def _search_nextjs_data(self, webpage, video_id, **kw):
+        transform_source = kw.pop('transform_source', None)
+        fatal = kw.pop('fatal', True)
+        return self._parse_json(
+            self._search_regex(
+                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
+                webpage, 'next.js data', group='js', fatal=fatal, **kw),
+            video_id, transform_source=transform_source, fatal=fatal)
+
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -100,9 +109,7 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    IE_DESC = 'ITVX'
-    _WORKING = False
-
+    _IE_DESC = 'ITVX'
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -263,7 +270,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -316,7 +323,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/pornhub.py

@@ -7,30 +7,35 @@ import operator
 import re
 
 from .common import InfoExtractor
+
 from ..compat import (
     compat_HTTPError,
-    compat_str,
-    compat_urllib_request,
 )
 from .openload import PhantomJSwrapper
 from ..utils import (
+    clean_html,
     determine_ext,
+    extract_attributes,
     ExtractorError,
+    get_element_by_class,
+    get_element_by_id,
     int_or_none,
     merge_dicts,
-    NO_DEFAULT,
-    orderedSet,
+    parse_count,
     remove_quotes,
-    str_to_int,
+    remove_start,
+    T,
+    traverse_obj,
     update_url_query,
-    urlencode_postdata,
     url_or_none,
+    urlencode_postdata,
+    urljoin,
 )
 
 
 class PornHubBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'pornhub'
-    _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubthbh7ap3u\.onion)'
+    _PORNHUB_HOST_RE = r'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd\.onion)'
 
     def _download_webpage_handle(self, *args, **kwargs):
         def dl(*args, **kwargs):
@@ -47,10 +52,7 @@ class PornHubBaseIE(InfoExtractor):
                 r'<body\b[^>]+\bonload=["\']go\(\)',
                 r'document\.cookie\s*=\s*["\']RNKEY=',
                 r'document\.location\.reload\(true\)')):
-            url_or_request = args[0]
-            url = (url_or_request.get_full_url()
-                   if isinstance(url_or_request, compat_urllib_request.Request)
-                   else url_or_request)
+            url = urlh.geturl()
             phantom = PhantomJSwrapper(self, required_version='2.0')
             phantom.get(url, html=webpage)
             webpage, urlh = dl(*args, **kwargs)
@@ -60,11 +62,17 @@ class PornHubBaseIE(InfoExtractor):
     def _real_initialize(self):
         self._logged_in = False
 
+    def _set_age_cookies(self, host):
+        self._set_cookie(host, 'age_verified', '1')
+        self._set_cookie(host, 'accessAgeDisclaimerPH', '1')
+        self._set_cookie(host, 'accessAgeDisclaimerUK', '1')
+        self._set_cookie(host, 'accessPH', '1')
+
     def _login(self, host):
         if self._logged_in:
             return
 
-        site = host.split('.')[0]
+        site = host.split('.', 1)[0]
 
         # Both sites pornhub and pornhubpremium have separate accounts
         # so there should be an option to provide credentials for both.
@@ -81,9 +89,9 @@ class PornHubBaseIE(InfoExtractor):
             login_url, None, 'Downloading %s login page' % site)
 
         def is_logged(webpage):
-            return any(re.search(p, webpage) for p in (
-                r'class=["\']signOut',
-                r'>Sign\s+[Oo]ut\s*<'))
+            return bool(
+                get_element_by_id('profileMenuDropdown', webpage)
+                or get_element_by_class('ph-icon-logout', webpage))
 
         if is_logged(login_page):
             self._logged_in = True
@@ -92,12 +100,12 @@ class PornHubBaseIE(InfoExtractor):
         login_form = self._hidden_inputs(login_page)
 
         login_form.update({
-            'username': username,
+            'email': username,
             'password': password,
         })
 
         response = self._download_json(
-            'https://www.%s/front/authenticate' % host, None,
+            'https://www.%s/front/authenticate' % host, 'login',
             'Logging in to %s' % site,
             data=urlencode_postdata(login_form),
             headers={
@@ -119,17 +127,12 @@ class PornHubBaseIE(InfoExtractor):
 
 
 class PornHubIE(PornHubBaseIE):
-    IE_DESC = 'PornHub and Thumbzilla'
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:
-                            (?:[^/]+\.)?
-                            %s
-                            /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
-                            (?:www\.)?thumbzilla\.com/video/
-                        )
-                        (?P<id>[\da-z]+)
-                    ''' % PornHubBaseIE._PORNHUB_HOST_RE
+    IE_DESC = 'PornHub'  # Thumbzilla -> Redtube.com, Modelhub -> uviu.com
+    _PORNHUB_PATH_RE = r'/(?:(?:view_video\.php%s)\?(?:.+&)?viewkey=%s)(?P<id>[\da-z]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?%s%s' % (
+        PornHubBaseIE._PORNHUB_HOST_RE, _PORNHUB_PATH_RE % ('|video/show', '|embed/'))
+    _PORNHUB_PATH_RE = _PORNHUB_PATH_RE % ('', '')
+    _EMBED_REGEX = [r'<iframe\s[^>]*?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)']
     _TESTS = [{
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
         'md5': 'a6391306d050e4547f62b3f485dd9ba9',
@@ -138,6 +141,7 @@ class PornHubIE(PornHubBaseIE):
             'ext': 'mp4',
             'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
             'uploader': 'Babes',
+            'uploader_id': '/users/babes-com',
             'upload_date': '20130628',
             'timestamp': 1372447216,
             'duration': 361,
@@ -148,6 +152,10 @@ class PornHubIE(PornHubBaseIE):
             'age_limit': 18,
             'tags': list,
             'categories': list,
+            'cast': list,
+        },
+        'params': {
+            'format': '[format_id!^=hls]',
         },
     }, {
         # non-ASCII title
@@ -189,14 +197,27 @@ class PornHubIE(PornHubBaseIE):
             'categories': list,
             'subtitles': {
                 'en': [{
-                    "ext": 'srt'
-                }]
+                    'ext': 'srt',
+                }],
             },
         },
         'params': {
             'skip_download': True,
         },
         'skip': 'This video has been disabled',
+    }, {
+        'url': 'http://www.pornhub.com/view_video.php?viewkey=ph601dc30bae19a',
+        'info_dict': {
+            'id': 'ph601dc30bae19a',
+            'ext': 'mp4',
+            'timestamp': 1612564932,
+            'age_limit': 18,
+            'uploader': 'Projekt Melody',
+            'uploader_id': 'projekt-melody',
+            'upload_date': '20210205',
+            'title': '"Welcome to My Pussy Mansion" - CB Stream (02/03/21)',
+            'thumbnail': r're:https?://.+',
+        },
     }, {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
         'only_matching': True,
@@ -216,9 +237,6 @@ class PornHubIE(PornHubBaseIE):
         # private video
         'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
         'only_matching': True,
-    }, {
-        'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
-        'only_matching': True,
     }, {
         'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
         'only_matching': True,
@@ -244,28 +262,36 @@ class PornHubIE(PornHubBaseIE):
         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5a9813bfa7156',
         'only_matching': True,
     }, {
-        'url': 'http://pornhubthbh7ap3u.onion/view_video.php?viewkey=ph5a9813bfa7156',
+        'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/view_video.php?viewkey=ph5a9813bfa7156',
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
-            webpage)
+    @classmethod
+    def _extract_urls(cls, webpage):
+        def yield_urls():
+            for p in cls._EMBED_REGEX:
+                for from_ in re.finditer(p, webpage):
+                    yield from_.group('url')
+
+        return list(yield_urls())
 
     def _extract_count(self, pattern, webpage, name):
-        return str_to_int(self._search_regex(
+        return parse_count(self._search_regex(
             pattern, webpage, '%s count' % name, fatal=False))
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        for _ in range(2):
+            mobj = self._match_valid_url(url)
+            video_id = mobj.group('id') if mobj else self._generic_id(url)
+            _, urlh = self._download_webpage_handle(url, video_id)
+            if url == urlh.geturl():
+                break
+            url = urlh.geturl()
+
         host = mobj.group('host') or 'pornhub.com'
-        video_id = mobj.group('id')
 
         self._login(host)
-
-        self._set_cookie(host, 'age_verified', '1')
+        self._set_age_cookies(host)
 
         def dl_webpage(platform):
             self._set_cookie(host, 'platform', platform)
@@ -276,7 +302,7 @@ class PornHubIE(PornHubBaseIE):
         webpage = dl_webpage('pc')
 
         error_msg = self._html_search_regex(
-            (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+            (r'(?s)<div[^>]+class=("|\')(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
              r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
             webpage, 'error message', default=None, group='error')
         if error_msg:
@@ -285,9 +311,9 @@ class PornHubIE(PornHubBaseIE):
                 'PornHub said: %s' % error_msg,
                 expected=True, video_id=video_id)
 
-        if any(re.search(p, webpage) for p in (
-                r'class=["\']geoBlocked["\']',
-                r'>\s*This content is unavailable in your country')):
+        if bool(get_element_by_class('geoBlocked', webpage)
+                or self._search_regex(
+                    r'>\s*This content is (unavailable) in your country', webpage, 'geo-restriction', default=False)):
             self.raise_geo_restricted()
 
         # video_title from flashvars contains whitespace instead of non-ASCII (see
@@ -304,36 +330,34 @@ class PornHubIE(PornHubBaseIE):
         video_urls_set = set()
         subtitles = {}
 
-        flashvars = self._parse_json(
-            self._search_regex(
-                r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
-            video_id)
-        if flashvars:
-            subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
-            if subtitle_url:
-                subtitles.setdefault('en', []).append({
-                    'url': subtitle_url,
-                    'ext': 'srt',
-                })
-            thumbnail = flashvars.get('image_url')
-            duration = int_or_none(flashvars.get('video_duration'))
-            media_definitions = flashvars.get('mediaDefinitions')
-            if isinstance(media_definitions, list):
-                for definition in media_definitions:
-                    if not isinstance(definition, dict):
-                        continue
-                    video_url = definition.get('videoUrl')
-                    if not video_url or not isinstance(video_url, compat_str):
-                        continue
-                    if video_url in video_urls_set:
-                        continue
-                    video_urls_set.add(video_url)
-                    video_urls.append(
-                        (video_url, int_or_none(definition.get('quality'))))
-        else:
-            thumbnail, duration = [None] * 2
+        def add_video_url(video_url, quality=None):
+            v_url = url_or_none(video_url)
+            if not v_url:
+                return
+            if v_url in video_urls_set:
+                return
+            video_urls.append((v_url, quality))
+            video_urls_set.add(v_url)
 
-        def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
+        flashvars = self._search_json(r'var\s+flashvars_\d+\s*=', webpage, 'flashvars', video_id)
+        flashvars = traverse_obj(flashvars, {
+            'closedCaptionsFile': ('closedCaptionsFile', T(url_or_none)),
+            'image_url': ('image_url', T(url_or_none)),
+            'video_duration': ('video_duration', T(int_or_none)),
+            'mediaDefinitions': ('mediaDefinitions', lambda _, v: v['videoUrl']),
+        }) or {}
+        subtitle_url = flashvars.get('closedCaptionsFile')
+        if subtitle_url:
+            subtitles.setdefault('en', []).append({
+                'url': subtitle_url,
+                'ext': 'srt',
+            })
+        thumbnail = flashvars.get('image_url')
+        duration = flashvars.get('video_duration')
+        for definition in flashvars.get('mediaDefinitions') or []:
+            add_video_url(definition['videoUrl'], int_or_none(definition.get('quality')))
+
+        def extract_js_vars(webpage, pattern, default=None):
             assignments = self._search_regex(
                 pattern, webpage, 'encoded url', default=default)
             if not assignments:
@@ -363,51 +387,33 @@ class PornHubIE(PornHubBaseIE):
                 js_vars[vname] = parse_js_value(value)
             return js_vars
 
-        def add_video_url(video_url):
-            v_url = url_or_none(video_url)
-            if not v_url:
-                return
-            if v_url in video_urls_set:
-                return
-            video_urls.append((v_url, None))
-            video_urls_set.add(v_url)
-
         def parse_quality_items(quality_items):
             q_items = self._parse_json(quality_items, video_id, fatal=False)
-            if not isinstance(q_items, list):
-                return
-            for item in q_items:
-                if isinstance(item, dict):
-                    add_video_url(item.get('url'))
+            for v_url in traverse_obj(q_items, (Ellipsis, 'url')):
+                add_video_url(v_url)
 
         if not video_urls:
             FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
             js_vars = extract_js_vars(
-                webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
-                default=None)
-            if js_vars:
-                for key, format_url in js_vars.items():
-                    if key.startswith(FORMAT_PREFIXES[-1]):
-                        parse_quality_items(format_url)
-                    elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
-                        add_video_url(format_url)
-            if not video_urls and re.search(
-                    r'<[^>]+\bid=["\']lockedPlayer', webpage):
+                webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES))
+            for key, format_url in js_vars.items():
+                if key.startswith(FORMAT_PREFIXES[-1]):
+                    parse_quality_items(format_url)
+                elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
+                    add_video_url(format_url)
+            if not video_urls and get_element_by_id('lockedPlayer', webpage):
                 raise ExtractorError(
                     'Video %s is locked' % video_id, expected=True)
 
         if not video_urls:
             js_vars = extract_js_vars(
                 dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
-            add_video_url(js_vars['mediastring'])
+            add_video_url(traverse_obj(js_vars, 'mediastring'))
 
         for mobj in re.finditer(
                 r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
                 webpage):
-            video_url = mobj.group('url')
-            if video_url not in video_urls_set:
-                video_urls.append((video_url, None))
-                video_urls_set.add(video_url)
+            add_video_url(mobj.group('url'))
 
         upload_date = None
         formats = []
@@ -433,6 +439,13 @@ class PornHubIE(PornHubBaseIE):
                 'height': height,
             })
 
+        if not video_urls:
+            # import here to avoid mutually recursive dependency
+            from .generic import GenericIE
+            ret = GenericIE.generic_url_result(url, video_id=video_id, video_title=title, force_videoid=True)
+            ret['_type'] = 'url_transparent'
+            return ret
+
         for video_url, height in video_urls:
             if not upload_date:
                 upload_date = self._search_regex(
@@ -440,52 +453,55 @@ class PornHubIE(PornHubBaseIE):
                 if upload_date:
                     upload_date = upload_date.replace('/', '')
             if '/video/get_media' in video_url:
+                # self._set_cookie(host, 'platform', 'tv')
                 medias = self._download_json(video_url, video_id, fatal=False)
-                if isinstance(medias, list):
-                    for media in medias:
-                        if not isinstance(media, dict):
-                            continue
-                        video_url = url_or_none(media.get('videoUrl'))
-                        if not video_url:
-                            continue
-                        height = int_or_none(media.get('quality'))
-                        add_format(video_url, height)
+                for media in traverse_obj(medias, lambda _, v: v['videoUrl']):
+                    video_url = url_or_none(media['videoUrl'])
+                    if not video_url:
+                        continue
+                    height = int_or_none(media.get('quality'))
+                    add_format(video_url, height)
                 continue
             add_format(video_url)
+
         self._sort_formats(
             formats, field_preference=('height', 'width', 'fps', 'format_id'))
 
+        model_profile = self._search_json(
+            r'var\s+MODEL_PROFILE\s*=', webpage, 'model profile', video_id, fatal=False)
         video_uploader = self._html_search_regex(
             r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
-            webpage, 'uploader', default=None)
+            webpage, 'uploader', default=None) or model_profile.get('username')
 
         def extract_vote_count(kind, name):
             return self._extract_count(
-                (r'<span[^>]+\bclass="votes%s"[^>]*>([\d,\.]+)</span>' % kind,
+                (r'<span[^>]+\bclass="votes%s"[^>]*>(\d[\d,\.]*[kKmM]?)</span>' % kind,
                  r'<span[^>]+\bclass=["\']votes%s["\'][^>]*\bdata-rating=["\'](\d+)' % kind),
                 webpage, name)
 
         view_count = self._extract_count(
-            r'<span class="count">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
+            r'<span class="count">(\d[\d,\.]*[kKmM]?)</span> [Vv]iews', webpage, 'view')
         like_count = extract_vote_count('Up', 'like')
         dislike_count = extract_vote_count('Down', 'dislike')
         comment_count = self._extract_count(
-            r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
+            r'All Comments\s*<span>\((\d[\d,\.]*[kKmM]?)\)', webpage, 'comment')
 
         def extract_list(meta_key):
             div = self._search_regex(
                 r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
                 % meta_key, webpage, meta_key, default=None)
             if div:
-                return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
+                return [clean_html(x) for x in re.findall(r'(?s)<a[^>]+\bhref=[^>]+>.+?</a>', div)]
 
         info = self._search_json_ld(webpage, video_id, default={})
         # description provided in JSON-LD is irrelevant
-        info['description'] = None
+        for k in ('url', 'description'):
+            info.pop(k, None)
 
-        return merge_dicts({
+        return merge_dicts(info, {
             'id': video_id,
             'uploader': video_uploader,
+            'uploader_id': remove_start(model_profile.get('modelProfileLink'), '/model/'),
             'upload_date': upload_date,
             'title': title,
             'thumbnail': thumbnail,
@@ -498,8 +514,9 @@ class PornHubIE(PornHubBaseIE):
             'age_limit': 18,
             'tags': extract_list('tags'),
             'categories': extract_list('categories'),
+            'cast': extract_list('pornstars'),
             'subtitles': subtitles,
-        }, info)
+        })
 
 
 class PornHubPlaylistBaseIE(PornHubBaseIE):
@@ -512,65 +529,28 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
         # drop-down menu that uses similar pattern for videos (see
         # https://github.com/ytdl-org/youtube-dl/issues/11594).
         container = self._search_regex(
-            r'(?s)(<div[^>]+class=["\']container.+)', webpage,
+            r'(?s)(<div\s[^>]*class=["\']container.+)', webpage,
             'container', default=webpage)
 
+        def entries():
+            seen_ids = set()
+            for m in re.finditer(r'<\w+\s[^>]*(?<!-)\bhref\s*=\s*.("|\'|\b)%s\1[^>]*>' % (PornHubIE._PORNHUB_PATH_RE,), container):
+                video_id = m.group('id')
+                if video_id:
+                    if video_id in seen_ids:
+                        continue
+                    seen_ids.add(video_id)
+                elt = extract_attributes(m.group(0))
+                video_url = urljoin(host, elt.get('href'))
+                yield video_url, video_id, elt.get('title')
+
         return [
             self.url_result(
-                'http://www.%s/%s' % (host, video_url),
-                PornHubIE.ie_key(), video_title=title)
-            for video_url, title in orderedSet(re.findall(
-                r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
-                container))
+                video_url, PornHubIE.ie_key(), video_title=title, video_id=video_id)
+            for video_url, video_id, title in entries()
         ]
 
 
-class PornHubUserIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
-    _TESTS = [{
-        'url': 'https://www.pornhub.com/model/zoe_ph',
-        'playlist_mincount': 118,
-    }, {
-        'url': 'https://www.pornhub.com/pornstar/liz-vicious',
-        'info_dict': {
-            'id': 'liz-vicious',
-        },
-        'playlist_mincount': 118,
-    }, {
-        'url': 'https://www.pornhub.com/users/russianveet69',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.pornhub.com/channels/povd',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
-        'only_matching': True,
-    }, {
-        # Unavailable via /videos page, but available with direct pagination
-        # on pornstar page (see [1]), requires premium
-        # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
-        'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
-        'only_matching': True,
-    }, {
-        # Same as before, multi page
-        'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
-        'only_matching': True,
-    }, {
-        'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        user_id = mobj.group('id')
-        videos_url = '%s/videos' % mobj.group('url')
-        page = self._extract_page(url)
-        if page:
-            videos_url = update_url_query(videos_url, {'page': page})
-        return self.url_result(
-            videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
-
-
 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
     @staticmethod
     def _has_more(webpage):
@@ -617,23 +597,77 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
             page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
-            for e in page_entries:
-                yield e
+            for from_ in page_entries:
+                yield from_
             if not self._has_more(webpage):
                 break
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        mobj = self._match_valid_url(url)
         host = mobj.group('host')
         item_id = mobj.group('id')
 
         self._login(host)
+        self._set_age_cookies(host)
 
         return self.playlist_result(self._entries(url, host, item_id), item_id)
 
 
+class PornHubUserIE(PornHubPagedPlaylistBaseIE):
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?P<id>(?:(?:user|channel)s|model|pornstar)/[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
+    _TESTS = [{
+        'url': 'https://www.pornhub.com/model/zoe_ph',
+        'info_dict': {
+            'id': 'zoe_ph',
+        },
+        'playlist_mincount': 118,
+    }, {
+        'url': 'https://www.pornhub.com/pornstar/liz-vicious',
+        'info_dict': {
+            'id': 'liz-vicious',
+        },
+        'playlist_mincount': 118,
+    }, {
+        'url': 'https://www.pornhub.com/users/russianveet69',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/channels/povd',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
+        'only_matching': True,
+    }, {
+        # Unavailable via /videos page, but available with direct pagination
+        # on pornstar page (see [1]), requires premium
+        # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
+        'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
+        'only_matching': True,
+    }, {
+        # Same as before, multi page
+        'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
+        'only_matching': True,
+    }, {
+        'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        user_id, host = mobj.group('id', 'host')
+        videos_url = '%s/videos' % mobj.group('url')
+        page = self._extract_page(url)
+        if page:
+            videos_url = update_url_query(videos_url, {'page': page})
+
+        self._login(host)
+
+        return self.playlist_result(self._entries(videos_url, host, user_id), user_id.split('/')[-1])
+        # return self.url_result(
+        #     videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
+
+
 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
+    _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/|gif/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
     _TESTS = [{
         'url': 'https://www.pornhub.com/model/zoe_ph/videos',
         'only_matching': True,
@@ -642,16 +676,20 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
         'only_matching': True,
     }, {
         'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
-        'info_dict': {
-            'id': 'pornstar/jenny-blighe/videos',
-        },
-        'playlist_mincount': 149,
+        'only_matching': True,
     }, {
-        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
+        'url': 'https://www.pornhub.com/pornstar/kylie-quinn/videos',
         'info_dict': {
-            'id': 'pornstar/jenny-blighe/videos',
+            'id': 'pornstar/kylie-quinn/videos',
         },
-        'playlist_mincount': 40,
+        'playlist_mincount': 80,
+    }, {
+        'url': 'https://www.pornhub.com/pornstar/kylie-quinn/videos?page=2',
+        'info_dict': {
+            'id': 'pornstar/kylie-quinn/videos',
+        },
+        # specific page: process just that page
+        'playlist_count': 40,
     }, {
         # default sorting as Top Rated Videos
         'url': 'https://www.pornhub.com/channels/povd/videos',
@@ -727,27 +765,14 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
         'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
         'only_matching': True,
     }, {
-        'url': 'https://www.pornhub.com/playlist/44121572',
-        'info_dict': {
-            'id': 'playlist/44121572',
-        },
-        'playlist_mincount': 132,
-    }, {
-        'url': 'https://www.pornhub.com/playlist/4667351',
-        'only_matching': True,
-    }, {
-        'url': 'https://de.pornhub.com/playlist/4667351',
-        'only_matching': True,
-    }, {
-        'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph/videos',
+        'url': 'https://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/model/zoe_ph/videos',
         'only_matching': True,
     }]
 
     @classmethod
     def suitable(cls, url):
-        return (False
-                if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
-                else super(PornHubPagedVideoListIE, cls).suitable(url))
+        return (not any(ph.suitable(url) for ph in (PornHubIE, PornHubUserIE, PornHubUserVideosUploadIE))
+                and super(PornHubPagedVideoListIE, cls).suitable(url))
 
 
 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
@@ -762,6 +787,62 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
         'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
         'only_matching': True,
     }, {
-        'url': 'http://pornhubthbh7ap3u.onion/pornstar/jenny-blighe/videos/upload',
+        'url': 'http://pornhubvybmsymdol4iibwgwtkpwmeyd6luq2gxajgjzfjvotyt5zhyd.onion/pornstar/jenny-blighe/videos/upload',
         'only_matching': True,
     }]
+
+
+class PornHubPlaylistIE(PornHubPlaylistBaseIE):
+    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
+    _TESTS = [{
+        'url': 'https://www.pornhub.com/playlist/44121572',
+        'info_dict': {
+            'id': '44121572',
+        },
+        'playlist_mincount': 55,
+    }, {
+        'url': 'https://www.pornhub.com/playlist/4667351',
+        'only_matching': True,
+    }, {
+        'url': 'https://de.pornhub.com/playlist/4667351',
+        'only_matching': True,
+    }, {
+        'url': 'https://de.pornhub.com/playlist/4667351?page=2',
+        'only_matching': True,
+    }]
+
+    def _entries(self, url, host, item_id):
+        webpage = self._download_webpage(url, item_id, 'Downloading page 1')
+        playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
+        video_count = int_or_none(
+            self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
+        token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
+        page_count = (video_count - 36 + 39) // 40 + 1
+        page_entries = self._extract_entries(webpage, host)
+
+        def download_page(page_num):
+            note = 'Downloading page {0}'.format(page_num)
+            page_url = 'https://www.{0}/playlist/viewChunked'.format(host)
+            return self._download_webpage(page_url, item_id, note, query={
+                'id': playlist_id,
+                'page': page_num,
+                'token': token,
+            })
+
+        for page_num in range(1, page_count + 1):
+            if page_num > 1:
+                webpage = download_page(page_num)
+                page_entries = self._extract_entries(webpage, host)
+            if not page_entries:
+                break
+            for from_ in page_entries:
+                yield from_
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        host, item_id = mobj.group('host', 'id')
+
+        self._login(host)
+        self._set_age_cookies(host)
+
+        return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    IE_NAME = 'senate.gov'
+    _IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/options.py

@@ -404,10 +404,6 @@ def parseOpts(overrideArguments=None):
         '-F', '--list-formats',
         action='store_true', dest='listformats',
         help='List all available formats of requested videos')
-    video_format.add_option(
-        '--no-list-formats',
-        action='store_false', dest='listformats',
-        help='Do not list available formats of requested videos (default)')
     video_format.add_option(
         '--youtube-include-dash-manifest',
         action='store_true', dest='youtube_include_dash_manifest', default=True,
@@ -416,17 +412,6 @@ def parseOpts(overrideArguments=None):
         '--youtube-skip-dash-manifest',
         action='store_false', dest='youtube_include_dash_manifest',
         help='Do not download the DASH manifests and related data on YouTube videos')
-    video_format.add_option(
-        '--youtube-player-js-variant',
-        action='store', dest='youtube_player_js_variant',
-        help='For YouTube, the player javascript variant to use for n/sig deciphering; `actual` to follow the site; default `%default`.',
-        choices=('actual', 'main', 'tcc', 'tce', 'es5', 'es6', 'tv', 'tv_es6', 'phone', 'tablet'),
-        default='main', metavar='VARIANT')
-    video_format.add_option(
-        '--youtube-player-js-version',
-        action='store', dest='youtube_player_js_version',
-        help='For YouTube, the player javascript version to use for n/sig deciphering, specified as `signature_timestamp@hash`, or `actual` to follow the site; default `%default`',
-        default='20348@0004de42', metavar='STS@HASH')
     video_format.add_option(
         '--merge-output-format',
         action='store', dest='merge_output_format', metavar='FORMAT', default=None,

youtube_dl/utils.py

@@ -4204,16 +4204,12 @@ def lowercase_escape(s):
         s)
 
 
-def escape_rfc3986(s, safe=None):
+def escape_rfc3986(s):
     """Escape non-ASCII characters as suggested by RFC 3986"""
     if sys.version_info < (3, 0):
         s = _encode_compat_str(s, 'utf-8')
-        if safe is not None:
-            safe = _encode_compat_str(safe, 'utf-8')
-    if safe is None:
-        safe = b"%/;:@&=+$,!~*'()?#[]"
     # ensure unicode: after quoting, it can always be converted
-    return compat_str(compat_urllib_parse.quote(s, safe))
+    return compat_str(compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]"))
 
 
 def escape_url(url):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2025.04.07'
+__version__ = '2021.12.17'