better reader

# Conflicts:
#	.github/workflows/core.yml
#	requirements.txt
#	test/test_networking.py
#	test/test_socks.py
#	yt_dlp/YoutubeDL.py
#	yt_dlp/dependencies/__init__.py
#	yt_dlp/networking/__init__.py

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting that yt-dlp is broken on a **supported** site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -64,7 +64,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -72,8 +72,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting a new site support request
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -76,7 +76,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -84,8 +84,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm requesting a site-specific feature
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -72,7 +72,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -80,8 +80,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting a bug unrelated to a specific site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -57,7 +57,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -65,8 +65,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -20,7 +20,7 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
@@ -53,7 +53,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -61,7 +61,7 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell

.github/ISSUE_TEMPLATE/6_question.yml

@@ -26,7 +26,7 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.10.07** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2023.10.13** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
           required: true
@@ -59,7 +59,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2023.10.07 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.10.13 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -67,7 +67,7 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2023.10.07, Current version: 2023.10.07
+        Latest version: 2023.10.13, Current version: 2023.10.13
-        yt-dlp is up to date (2023.10.07)
+        yt-dlp is up to date (2023.10.13)
         <more lines>
       render: shell

.github/workflows/core.yml

@@ -32,10 +32,8 @@ jobs:
       uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install pytest
-      run: pip install pytest
     - name: Install dependencies
-      run: pip install -r requirements.txt
+      run: pip install pytest -r requirements.txt
     - name: Run tests
       continue-on-error: False
       run: |

CONTRIBUTORS

@@ -509,3 +509,7 @@ handlerug
 jiru
 madewokherd
 xofe
+awalgarg
+midnightveil
+naginatana
+Riteo

Changelog.md

@@ -4,6 +4,30 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2023.10.13
+
+#### Core changes
+- [Ensure thumbnail output directory exists](https://github.com/yt-dlp/yt-dlp/commit/2acd1d555ef89851c73773776715d3de9a0e30b9) ([#7985](https://github.com/yt-dlp/yt-dlp/issues/7985)) by [Riteo](https://github.com/Riteo)
+- **utils**
+    - `js_to_json`: [Fix `Date` constructor parsing](https://github.com/yt-dlp/yt-dlp/commit/9d7ded6419089c1bf252496073f73ad90ed71004) ([#8295](https://github.com/yt-dlp/yt-dlp/issues/8295)) by [awalgarg](https://github.com/awalgarg), [Grub4K](https://github.com/Grub4K)
+    - `write_xattr`: [Use `os.setxattr` if available](https://github.com/yt-dlp/yt-dlp/commit/84e26038d4002e763ea51ca1bdce4f7e63c540bf) ([#8205](https://github.com/yt-dlp/yt-dlp/issues/8205)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
+
+#### Extractor changes
+- **artetv**: [Support age-restricted content](https://github.com/yt-dlp/yt-dlp/commit/09f815ad52843219a7ee3f2a0dddf6c250c91f0c) ([#8301](https://github.com/yt-dlp/yt-dlp/issues/8301)) by [StefanLobbenmeier](https://github.com/StefanLobbenmeier)
+- **jtbc**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/b286ec68f1f28798b3e371f888a2ed97d399cf77) ([#8314](https://github.com/yt-dlp/yt-dlp/issues/8314)) by [seproDev](https://github.com/seproDev)
+- **mbn**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e030b6b6fba7b2f4614ad2ab9f7649d40a2dd305) ([#8312](https://github.com/yt-dlp/yt-dlp/issues/8312)) by [seproDev](https://github.com/seproDev)
+- **nhk**: [Fix Japanese-language VOD extraction](https://github.com/yt-dlp/yt-dlp/commit/4de94b9e165bfd6421a692f5f2eabcdb08edcb71) ([#8309](https://github.com/yt-dlp/yt-dlp/issues/8309)) by [garret1317](https://github.com/garret1317)
+- **radiko**: [Fix bug with `downloader_options`](https://github.com/yt-dlp/yt-dlp/commit/b9316642313bbc9e209ac0d2276d37ba60bceb49) by [bashonly](https://github.com/bashonly)
+- **tenplay**: [Add support for seasons](https://github.com/yt-dlp/yt-dlp/commit/88a99c87b680ae59002534a517e191f46c42cbd4) ([#7939](https://github.com/yt-dlp/yt-dlp/issues/7939)) by [midnightveil](https://github.com/midnightveil)
+- **youku**: [Improve tudou.com support](https://github.com/yt-dlp/yt-dlp/commit/b7098d46b552a9322c6cea39ba80be5229f922de) ([#8160](https://github.com/yt-dlp/yt-dlp/issues/8160)) by [naginatana](https://github.com/naginatana)
+- **youtube**: [Fix bug with `--extractor-retries inf`](https://github.com/yt-dlp/yt-dlp/commit/feebf6d02fc9651331eee2af5e08e6112288163b) ([#8328](https://github.com/yt-dlp/yt-dlp/issues/8328)) by [Grub4K](https://github.com/Grub4K)
+
+#### Downloader changes
+- **fragment**: [Improve progress calculation](https://github.com/yt-dlp/yt-dlp/commit/1c51c520f7b511ebd9e4eb7322285a8c31eedbbd) ([#8241](https://github.com/yt-dlp/yt-dlp/issues/8241)) by [Grub4K](https://github.com/Grub4K)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [b634ba7](https://github.com/yt-dlp/yt-dlp/commit/b634ba742d8f38ce9ecfa0546485728b0c6c59d1) by [bashonly](https://github.com/bashonly), [gamer191](https://github.com/gamer191)
+
 ### 2023.10.07
 
 #### Extractor changes

README.md

@@ -89,7 +89,6 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
     * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326) **\***
     * Supports some (but not all) age-gated content without cookies
     * Download livestreams from the start using `--live-from-start` (*experimental*)
-    * `255kbps` audio is extracted (if available) from YouTube Music when premium cookies are given
     * Channel URLs download all uploads of the channel, including shorts and live
 
 * **Cookies from browser**: Cookies can be automatically extracted from all major web browsers using `--cookies-from-browser BROWSER[+KEYRING][:PROFILE][::CONTAINER]`
@@ -158,6 +157,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
 * yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [~~aria2c~~](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is
 * yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this
+* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
 
 For ease of use, a few more compat options are available:
 
@@ -165,7 +165,7 @@ For ease of use, a few more compat options are available:
 * `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter`
 * `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter`
 * `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization,no-youtube-prefer-utc-upload-date`
-* `--compat-options 2022`: Same as `--compat-options playlist-match-filter,no-external-downloader-progress`. Use this to enable all future compat options
+* `--compat-options 2022`: Same as `--compat-options playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler`. Use this to enable all future compat options
 
 
 # INSTALLATION
@@ -275,6 +275,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
 * [**certifi**](https://github.com/certifi/python-certifi)\* - Provides Mozilla's root certificate bundle. Licensed under [MPLv2](https://github.com/certifi/python-certifi/blob/master/LICENSE)
 * [**brotli**](https://github.com/google/brotli)\* or [**brotlicffi**](https://github.com/python-hyper/brotlicffi) - [Brotli](https://en.wikipedia.org/wiki/Brotli) content encoding support. Both licensed under MIT <sup>[1](https://github.com/google/brotli/blob/master/LICENSE) [2](https://github.com/python-hyper/brotlicffi/blob/master/LICENSE) </sup>
 * [**websockets**](https://github.com/aaugustin/websockets)\* - For downloading over websocket. Licensed under [BSD-3-Clause](https://github.com/aaugustin/websockets/blob/main/LICENSE)
+* [**requests**](https://github.com/psf/requests)\* - HTTP library. For HTTPS proxy and persistent connections support. Licensed under [Apache-2.0](https://github.com/psf/requests/blob/main/LICENSE)
 
 ### Metadata
 
@@ -915,7 +916,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     Defaults to ~/.netrc
     --netrc-cmd NETRC_CMD           Command to execute to get the credentials
                                     for an extractor.
-    --video-password PASSWORD       Video password (vimeo, youku)
+    --video-password PASSWORD       Video-specific password
     --ap-mso MSO                    Adobe Pass multiple-system operator (TV
                                     provider) identifier, use --ap-list-mso for
                                     a list of available MSOs

devscripts/make_changelog.py

@@ -56,6 +56,7 @@ class CommitGroup(enum.Enum):
                 },
                 cls.MISC: {
                     'build',
+                    'ci',
                     'cleanup',
                     'devscripts',
                     'docs',

requirements.txt

@@ -3,4 +3,6 @@ pycryptodomex
 websockets
 brotli; platform_python_implementation=='CPython'
 brotlicffi; platform_python_implementation!='CPython'
-certifi
+certifi
+requests>=2.31.0,<3
+urllib3>=1.26.17,<3

setup.py

@@ -62,7 +62,14 @@ def py2exe_params():
             'compressed': 1,
             'optimize': 2,
             'dist_dir': './dist',
-            'excludes': ['Crypto', 'Cryptodome'],  # py2exe cannot import Crypto
+            'excludes': [
+                # py2exe cannot import Crypto
+                'Crypto',
+                'Cryptodome',
+                # py2exe appears to confuse this with our socks library.
+                # We don't use pysocks and urllib3.contrib.socks would fail to import if tried.
+                'urllib3.contrib.socks'
+            ],
             'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
             # Modules that are only imported dynamically must be added here
             'includes': ['yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated',

supportedsites.md

@@ -657,6 +657,8 @@
  - **Joj**
  - **Jove**
  - **JStream**
+ - **JTBC**: jtbc.co.kr
+ - **JTBC:program**
  - **JWPlatform**
  - **Kakao**
  - **Kaltura**
@@ -766,6 +768,7 @@
  - **massengeschmack.tv**
  - **Masters**
  - **MatchTV**
+ - **MBN**: mbn.co.kr (매일방송)
  - **MDR**: MDR.DE and KiKA
  - **MedalTV**
  - **media.ccc.de**
@@ -1468,6 +1471,7 @@
  - **Tempo**
  - **TennisTV**: [*tennistv*](## "netrc machine")
  - **TenPlay**: [*10play*](## "netrc machine")
+ - **TenPlaySeason**
  - **TF1**
  - **TFO**
  - **TheHoleTv**

test/test_networking.py

@@ -28,7 +28,7 @@ from http.cookiejar import CookieJar
 
 from test.helper import FakeYDL, http_server_port
 from yt_dlp.cookies import YoutubeDLCookieJar
-from yt_dlp.dependencies import brotli
+from yt_dlp.dependencies import brotli, requests, urllib3
 from yt_dlp.networking import (
     HEADRequest,
     PUTRequest,
@@ -43,6 +43,7 @@ from yt_dlp.networking.exceptions import (
     HTTPError,
     IncompleteRead,
     NoSupportingHandlers,
+    ProxyError,
     RequestError,
     SSLError,
     TransportError,
@@ -309,7 +310,7 @@ class TestRequestHandlerBase:
 
 
 class TestHTTPRequestHandler(TestRequestHandlerBase):
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_verify_cert(self, handler):
         with handler() as rh:
             with pytest.raises(CertificateVerifyError):
@@ -320,7 +321,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert r.status == 200
             r.close()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_ssl_error(self, handler):
         # HTTPS server with too old TLS version
         # XXX: is there a better way to test this than to create a new server?
@@ -338,7 +339,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
                 validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_percent_encode(self, handler):
         with handler() as rh:
             # Unicode characters should be encoded with uppercase percent-encoding
@@ -350,7 +351,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert res.status == 200
             res.close()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_remove_dot_segments(self, handler):
         with handler() as rh:
             # This isn't a comprehensive test,
@@ -366,14 +367,14 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             res.close()
 
     # Not supported by CurlCFFI (non-standard)
-    @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests'], indirect=True)
     def test_unicode_path_redirection(self, handler):
         with handler() as rh:
             r = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/302-non-ascii-redirect'))
             assert r.url == f'http://127.0.0.1:{self.http_port}/%E4%B8%AD%E6%96%87.html'
             r.close()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_raise_http_error(self, handler):
         with handler() as rh:
             for bad_status in (400, 500, 599, 302):
@@ -383,7 +384,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             # Should not raise an error
             validate_and_send(rh, Request('http://127.0.0.1:%d/gen_200' % self.http_port)).close()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_response_url(self, handler):
         with handler() as rh:
             # Response url should be that of the last url in redirect chain
@@ -395,7 +396,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             res2.close()
 
     # Covers some basic cases we expect some level of consistency between request handlers for
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     @pytest.mark.parametrize('redirect_status,method,expected', [
         # A 303 must either use GET or HEAD for subsequent request
         (303, 'POST', ('', 'GET', False)),
@@ -437,7 +438,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert expected[1] == res.headers.get('method')
             assert expected[2] == ('content-length' in headers.decode().lower())
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_request_cookie_header(self, handler):
         # We should accept a Cookie header being passed as in normal headers and handle it appropriately.
         with handler(verbose=True) as rh:
@@ -470,19 +471,19 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert b'cookie: test=ytdlp' not in data.lower()
             assert b'cookie: test=test3' in data.lower()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_redirect_loop(self, handler):
         with handler() as rh:
             with pytest.raises(HTTPError, match='redirect loop'):
                 validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/redirect_loop'))
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_incompleteread(self, handler):
         with handler(timeout=2) as rh:
             with pytest.raises(IncompleteRead, match='13 bytes read, 234221 more expected'):
                 validate_and_send(rh, Request('http://127.0.0.1:%d/incompleteread' % self.http_port)).read()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_cookies(self, handler):
         cookiejar = YoutubeDLCookieJar()
         cookiejar.set_cookie(http.cookiejar.Cookie(
@@ -499,7 +500,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
                 rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': cookiejar})).read()
             assert b'cookie: test=ytdlp' in data.lower()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_headers(self, handler):
 
         with handler(headers=HTTPHeaderDict({'test1': 'test', 'test2': 'test2'})) as rh:
@@ -515,7 +516,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert b'test2: test2' not in data
             assert b'test3: test3' in data
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_timeout(self, handler):
         with handler() as rh:
             # Default timeout is 20 seconds, so this should go through
@@ -531,7 +532,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             validate_and_send(
                 rh, Request(f'http://127.0.0.1:{self.http_port}/timeout_1', extensions={'timeout': 4}))
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_source_address(self, handler):
         source_address = f'127.0.0.{random.randint(5, 255)}'
         with handler(source_address=source_address) as rh:
@@ -540,13 +541,13 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert source_address == data
 
     # Not supported by CurlCFFI
-    @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests'], indirect=True)
     def test_gzip_trailing_garbage(self, handler):
         with handler() as rh:
             data = validate_and_send(rh, Request(f'http://localhost:{self.http_port}/trailing_garbage')).read().decode()
             assert data == '<html><video src="/vid.mp4" /></html>'
 
-    @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests'], indirect=True)
     @pytest.mark.skipif(not brotli, reason='brotli support is not installed')
     def test_brotli(self, handler):
         with handler() as rh:
@@ -557,7 +558,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert res.headers.get('Content-Encoding') == 'br'
             assert res.read() == b'<html><video src="/vid.mp4" /></html>'
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_deflate(self, handler):
         with handler() as rh:
             res = validate_and_send(
@@ -567,7 +568,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert res.headers.get('Content-Encoding') == 'deflate'
             assert res.read() == b'<html><video src="/vid.mp4" /></html>'
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_gzip(self, handler):
         with handler() as rh:
             res = validate_and_send(
@@ -577,7 +578,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert res.headers.get('Content-Encoding') == 'gzip'
             assert res.read() == b'<html><video src="/vid.mp4" /></html>'
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_multiple_encodings(self, handler):
         with handler() as rh:
             for pair in ('gzip,deflate', 'deflate, gzip', 'gzip, gzip', 'deflate, deflate'):
@@ -588,8 +589,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
                 assert res.headers.get('Content-Encoding') == pair
                 assert res.read() == b'<html><video src="/vid.mp4" /></html>'
 
-    # Not supported by Curl
+    # Not supported by curl_cffi
-    @pytest.mark.parametrize('handler', ['Urllib'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests'], indirect=True)
     def test_unsupported_encoding(self, handler):
         with handler() as rh:
             res = validate_and_send(
@@ -599,7 +600,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
             assert res.headers.get('Content-Encoding') == 'unsupported'
             assert res.read() == b'raw'
 
-    @pytest.mark.parametrize('handler', ['CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_read(self, handler):
         with handler() as rh:
             res = validate_and_send(
@@ -632,7 +633,7 @@ class TestHTTPProxy(TestRequestHandlerBase):
         cls.geo_proxy_thread.daemon = True
         cls.geo_proxy_thread.start()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_http_proxy(self, handler):
         http_proxy = f'http://127.0.0.1:{self.proxy_port}'
         geo_proxy = f'http://127.0.0.1:{self.geo_port}'
@@ -658,7 +659,7 @@ class TestHTTPProxy(TestRequestHandlerBase):
             assert res != f'normal: {real_url}'
             assert 'Accept' in res
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_noproxy(self, handler):
         with handler(proxies={'proxy': f'http://127.0.0.1:{self.proxy_port}'}) as rh:
             # NO_PROXY
@@ -668,7 +669,7 @@ class TestHTTPProxy(TestRequestHandlerBase):
                     'utf-8')
                 assert 'Accept' in nop_response
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_allproxy(self, handler):
         url = 'http://foo.com/bar'
         with handler() as rh:
@@ -676,7 +677,7 @@ class TestHTTPProxy(TestRequestHandlerBase):
                 'utf-8')
             assert response == f'normal: {url}'
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_http_proxy_with_idn(self, handler):
         with handler(proxies={
             'http': f'http://127.0.0.1:{self.proxy_port}',
@@ -713,27 +714,27 @@ class TestClientCertificate:
         ) as rh:
             validate_and_send(rh, Request(f'https://127.0.0.1:{self.port}/video.html')).read().decode()
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_certificate_combined_nopass(self, handler):
         self._run_test(handler, client_cert={
             'client_certificate': os.path.join(self.certdir, 'clientwithkey.crt'),
         })
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_certificate_nocombined_nopass(self, handler):
         self._run_test(handler, client_cert={
             'client_certificate': os.path.join(self.certdir, 'client.crt'),
             'client_certificate_key': os.path.join(self.certdir, 'client.key'),
         })
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_certificate_combined_pass(self, handler):
         self._run_test(handler, client_cert={
             'client_certificate': os.path.join(self.certdir, 'clientwithencryptedkey.crt'),
             'client_certificate_password': 'foobar',
         })
 
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_certificate_nocombined_pass(self, handler):
         self._run_test(handler, client_cert={
             'client_certificate': os.path.join(self.certdir, 'client.crt'),
@@ -817,6 +818,75 @@ class TestUrllibRequestHandler(TestRequestHandlerBase):
             assert not isinstance(exc_info.value, TransportError)
 
 
+class TestRequestsRequestHandler(TestRequestHandlerBase):
+    @pytest.mark.parametrize('raised,expected', [
+        (lambda: requests.exceptions.ConnectTimeout(), TransportError),
+        (lambda: requests.exceptions.ReadTimeout(), TransportError),
+        (lambda: requests.exceptions.Timeout(), TransportError),
+        (lambda: requests.exceptions.ConnectionError(), TransportError),
+        (lambda: requests.exceptions.ProxyError(), ProxyError),
+        (lambda: requests.exceptions.SSLError('12[CERTIFICATE_VERIFY_FAILED]34'), CertificateVerifyError),
+        (lambda: requests.exceptions.SSLError(), SSLError),
+        (lambda: requests.exceptions.InvalidURL(), RequestError),
+        (lambda: requests.exceptions.InvalidHeader(), RequestError),
+        # catch-all: https://github.com/psf/requests/blob/main/src/requests/adapters.py#L535
+        (lambda: urllib3.exceptions.HTTPError(), TransportError),
+        (lambda: requests.exceptions.RequestException(), RequestError)
+        #  (lambda: requests.exceptions.TooManyRedirects(), HTTPError) - Needs a response object
+    ])
+    @pytest.mark.parametrize('handler', ['Requests'], indirect=True)
+    def test_request_error_mapping(self, handler, monkeypatch, raised, expected):
+        with handler() as rh:
+            def mock_get_instance(*args, **kwargs):
+                class MockSession:
+                    def request(self, *args, **kwargs):
+                        raise raised()
+                return MockSession()
+
+            monkeypatch.setattr(rh, '_get_instance', mock_get_instance)
+
+            with pytest.raises(expected) as exc_info:
+                rh.send(Request('http://fake'))
+
+            assert exc_info.type is expected
+
+    @pytest.mark.parametrize('raised,expected,match', [
+        (lambda: urllib3.exceptions.SSLError(), SSLError, None),
+        (lambda: urllib3.exceptions.TimeoutError(), TransportError, None),
+        (lambda: urllib3.exceptions.ReadTimeoutError(None, None, None), TransportError, None),
+        (lambda: urllib3.exceptions.ProtocolError(), TransportError, None),
+        (lambda: urllib3.exceptions.DecodeError(), TransportError, None),
+        (lambda: urllib3.exceptions.HTTPError(), TransportError, None),  # catch-all
+        (
+            lambda: urllib3.exceptions.ProtocolError('error', http.client.IncompleteRead(partial=b'abc', expected=4)),
+            IncompleteRead,
+            '3 bytes read, 4 more expected'
+        ),
+        (
+            lambda: urllib3.exceptions.ProtocolError('error', urllib3.exceptions.IncompleteRead(partial=3, expected=5)),
+            IncompleteRead,
+            '3 bytes read, 5 more expected'
+        ),
+    ])
+    @pytest.mark.parametrize('handler', ['Requests'], indirect=True)
+    def test_response_error_mapping(self, handler, monkeypatch, raised, expected, match):
+        from urllib3.response import HTTPResponse as Urllib3Response
+        from requests.models import Response as RequestsResponse
+        from yt_dlp.networking._requests import RequestsResponseAdapter
+        requests_res = RequestsResponse()
+        requests_res.raw = Urllib3Response(body=b'', status=200)
+        res = RequestsResponseAdapter(requests_res)
+
+        def mock_read(*args, **kwargs):
+            raise raised()
+        monkeypatch.setattr(res.fp, 'read', mock_read)
+
+        with pytest.raises(expected, match=match) as exc_info:
+            res.read()
+
+        assert exc_info.type is expected
+
+
 class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
 
     @pytest.mark.parametrize('handler', ['CurlCFFI'], indirect=True)
@@ -891,6 +961,10 @@ class TestRequestHandlerValidation:
             ('file', UnsupportedRequest, {}),
             ('file', False, {'enable_file_urls': True}),
         ]),
+        ('Requests', [
+            ('http', False, {}),
+            ('https', False, {}),
+        ]),
         ('CurlCFFI', [
             ('http', False, {}),
             ('https', False, {}),
@@ -910,6 +984,14 @@ class TestRequestHandlerValidation:
             ('socks5h', False),
             ('socks', UnsupportedRequest),
         ]),
+        ('Requests', [
+            ('http', False),
+            ('https', False),
+            ('socks4', False),
+            ('socks4a', False),
+            ('socks5', False),
+            ('socks5h', False),
+        ]),
         ('CurlCFFI', [
             ('http', False),
             ('https', False),
@@ -928,6 +1010,10 @@ class TestRequestHandlerValidation:
             ('all', False),
             ('unrelated', False),
         ]),
+        ('Requests', [
+            ('all', False),
+            ('unrelated', False),
+        ]),
         ('CurlCFFI', [
             ('all', False),
             ('unrelated', False),
@@ -946,6 +1032,13 @@ class TestRequestHandlerValidation:
             ({'timeout': 'notatimeout'}, AssertionError),
             ({'unsupported': 'value'}, UnsupportedRequest),
         ]),
+        ('Requests', [
+            ({'cookiejar': 'notacookiejar'}, AssertionError),
+            ({'cookiejar': YoutubeDLCookieJar()}, False),
+            ({'timeout': 1}, False),
+            ({'timeout': 'notatimeout'}, AssertionError),
+            ({'unsupported': 'value'}, UnsupportedRequest),
+        ]),
         ('CurlCFFI', [
             ({'cookiejar': 'notacookiejar'}, AssertionError),
             ({'cookiejar': YoutubeDLCookieJar()}, False),
@@ -971,7 +1064,7 @@ class TestRequestHandlerValidation:
     def test_url_scheme(self, handler, scheme, fail, handler_kwargs):
         run_validation(handler, fail, Request(f'{scheme}://'), **(handler_kwargs or {}))
 
-    @pytest.mark.parametrize('handler,fail', [('Urllib', False), ('CurlCFFI', False)], indirect=['handler'])
+    @pytest.mark.parametrize('handler,fail', [('Urllib', False), ('Requests', False), ('CurlCFFI', False)], indirect=['handler'])
     def test_no_proxy(self, handler, fail):
         run_validation(handler, fail, Request('http://', proxies={'no': '127.0.0.1,github.com'}))
         run_validation(handler, fail, Request('http://'), proxies={'no': '127.0.0.1,github.com'})
@@ -994,13 +1087,13 @@ class TestRequestHandlerValidation:
         run_validation(handler, fail, Request('http://', proxies={'http': f'{scheme}://example.com'}))
         run_validation(handler, fail, Request('http://'), proxies={'http': f'{scheme}://example.com'})
 
-    @pytest.mark.parametrize('handler', ['Urllib', HTTPSupportedRH, 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', HTTPSupportedRH, 'Requests', 'CurlCFFI'], indirect=True)
     def test_empty_proxy(self, handler):
         run_validation(handler, False, Request('http://', proxies={'http': None}))
         run_validation(handler, False, Request('http://'), proxies={'http': None})
 
     @pytest.mark.parametrize('proxy_url', ['//example.com', 'example.com', '127.0.0.1', '/a/b/c'])
-    @pytest.mark.parametrize('handler', ['Urllib', 'CurlCFFI'], indirect=True)
+    @pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
     def test_invalid_proxy_url(self, handler, proxy_url):
         run_validation(handler, UnsupportedRequest, Request('http://', proxies={'http': proxy_url}))
 
@@ -1304,6 +1397,13 @@ class TestYoutubeDLNetworking:
             rh = self.build_handler(ydl, UrllibRH)
             assert rh.enable_file_urls is True
 
+    def test_compat_opt_prefer_urllib(self):
+        # This assumes urllib only has a preference when this compat opt is given
+        with FakeYDL({'compat_opts': ['prefer-legacy-http-handler']}) as ydl:
+            director = ydl.build_request_director([UrllibRH])
+            assert len(director.preferences) == 1
+            assert director.preferences.pop()(UrllibRH, None)
+
 
 class TestRequest:
 

test/test_socks.py

@@ -263,7 +263,7 @@ def ctx(request):
 
 
 class TestSocks4Proxy:
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks4_no_auth(self, handler, ctx):
         with handler() as rh:
             with ctx.socks_server(Socks4ProxyHandler) as server_address:
@@ -271,7 +271,7 @@ class TestSocks4Proxy:
                     rh, proxies={'all': f'socks4://{server_address}'})
                 assert response['version'] == 4
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks4_auth(self, handler, ctx):
         with handler() as rh:
             with ctx.socks_server(Socks4ProxyHandler, user_id='user') as server_address:
@@ -281,18 +281,15 @@ class TestSocks4Proxy:
                     rh, proxies={'all': f'socks4://user:@{server_address}'})
                 assert response['version'] == 4
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks4a_ipv4_target(self, handler, ctx):
         with ctx.socks_server(Socks4ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks4a://{server_address}'}) as rh:
                 response = ctx.socks_info_request(rh, target_domain='127.0.0.1')
                 assert response['version'] == 4
-                assert (
+                assert (response['ipv4_address'] == '127.0.0.1') != (response['domain_address'] == '127.0.0.1')
-                    (response['ipv4_address'] == '127.0.0.1' and response['domain_address'] is None)
-                    or (response['ipv4_address'] is None and response['domain_address'] == '127.0.0.1')
-                )
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks4a_domain_target(self, handler, ctx):
         with ctx.socks_server(Socks4ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks4a://{server_address}'}) as rh:
@@ -301,7 +298,7 @@ class TestSocks4Proxy:
                 assert response['ipv4_address'] is None
                 assert response['domain_address'] == 'localhost'
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_ipv4_client_source_address(self, handler, ctx):
         with ctx.socks_server(Socks4ProxyHandler) as server_address:
             source_address = f'127.0.0.{random.randint(5, 255)}'
@@ -311,7 +308,7 @@ class TestSocks4Proxy:
                 assert response['client_address'][0] == source_address
                 assert response['version'] == 4
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     @pytest.mark.parametrize('reply_code', [
         Socks4CD.REQUEST_REJECTED_OR_FAILED,
         Socks4CD.REQUEST_REJECTED_CANNOT_CONNECT_TO_IDENTD,
@@ -323,7 +320,7 @@ class TestSocks4Proxy:
                 with pytest.raises(ProxyError):
                     ctx.socks_info_request(rh)
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_ipv6_socks4_proxy(self, handler, ctx):
         with ctx.socks_server(Socks4ProxyHandler, bind_ip='::1') as server_address:
             with handler(proxies={'all': f'socks4://{server_address}'}) as rh:
@@ -332,7 +329,7 @@ class TestSocks4Proxy:
                 assert response['ipv4_address'] == '127.0.0.1'
                 assert response['version'] == 4
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_timeout(self, handler, ctx):
         with ctx.socks_server(Socks4ProxyHandler, sleep=2) as server_address:
             with handler(proxies={'all': f'socks4://{server_address}'}, timeout=0.5) as rh:
@@ -342,7 +339,7 @@ class TestSocks4Proxy:
 
 class TestSocks5Proxy:
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5_no_auth(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}) as rh:
@@ -350,7 +347,7 @@ class TestSocks5Proxy:
                 assert response['auth_methods'] == [0x0]
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5_user_pass(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler, auth=('test', 'testpass')) as server_address:
             with handler() as rh:
@@ -363,7 +360,7 @@ class TestSocks5Proxy:
                 assert response['auth_methods'] == [Socks5Auth.AUTH_NONE, Socks5Auth.AUTH_USER_PASS]
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5_ipv4_target(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}) as rh:
@@ -371,7 +368,7 @@ class TestSocks5Proxy:
                 assert response['ipv4_address'] == '127.0.0.1'
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5_domain_target(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}) as rh:
@@ -379,7 +376,7 @@ class TestSocks5Proxy:
                 assert (response['ipv4_address'] == '127.0.0.1') != (response['ipv6_address'] == '::1')
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5h_domain_target(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5h://{server_address}'}) as rh:
@@ -388,7 +385,7 @@ class TestSocks5Proxy:
                 assert response['domain_address'] == 'localhost'
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5h_ip_target(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5h://{server_address}'}) as rh:
@@ -397,7 +394,7 @@ class TestSocks5Proxy:
                 assert response['domain_address'] is None
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_socks5_ipv6_destination(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}) as rh:
@@ -405,7 +402,7 @@ class TestSocks5Proxy:
                 assert response['ipv6_address'] == '::1'
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_ipv6_socks5_proxy(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler, bind_ip='::1') as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}) as rh:
@@ -416,7 +413,7 @@ class TestSocks5Proxy:
 
     # XXX: is there any feasible way of testing IPv6 source addresses?
     # Same would go for non-proxy source_address test...
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_ipv4_client_source_address(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler) as server_address:
             source_address = f'127.0.0.{random.randint(5, 255)}'
@@ -425,7 +422,7 @@ class TestSocks5Proxy:
                 assert response['client_address'][0] == source_address
                 assert response['version'] == 5
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     @pytest.mark.parametrize('reply_code', [
         Socks5Reply.GENERAL_FAILURE,
         Socks5Reply.CONNECTION_NOT_ALLOWED,
@@ -442,7 +439,7 @@ class TestSocks5Proxy:
                 with pytest.raises(ProxyError):
                     ctx.socks_info_request(rh)
 
-    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('CurlCFFI', 'http')], indirect=True)
+    @pytest.mark.parametrize('handler,ctx', [('Urllib', 'http'), ('Requests', 'http'), ('CurlCFFI', 'http')], indirect=True)
     def test_timeout(self, handler, ctx):
         with ctx.socks_server(Socks5ProxyHandler, sleep=2) as server_address:
             with handler(proxies={'all': f'socks5://{server_address}'}, timeout=1) as rh:

yt_dlp/YoutubeDL.py

@@ -4097,6 +4097,12 @@ class YoutubeDL:
                     new_req.extensions.pop('impersonate')
                     return _urlopen(new_req)
                 raise
+                """
+                TODO
+                                if 'unsupported proxy type: "https"' in ue.msg.lower():
+                    raise RequestError(
+                        'To use an HTTPS proxy for this request, one of the following dependencies needs to be installed: requests')
+                """
             except SSLError as e:
                 if 'UNSAFE_LEGACY_RENEGOTIATION_DISABLED' in str(e):
                     raise RequestError('UNSAFE_LEGACY_RENEGOTIATION_DISABLED: Try using --legacy-server-connect', cause=e) from e
@@ -4141,6 +4147,8 @@ class YoutubeDL:
                 }),
             ))
         director.preferences.update(preferences or [])
+        if 'prefer-legacy-http-handler' in self.params['compat_opts']:
+            director.preferences.add(lambda rh, _: 500 if rh.RH_KEY == 'Urllib' else 0)
         return director
 
     def encode(self, s):
@@ -4263,7 +4271,7 @@ class YoutubeDL:
         return ret
 
     def _write_thumbnails(self, label, info_dict, filename, thumb_filename_base=None):
-        ''' Write thumbnails to file and return list of (thumb_filename, final_thumb_filename) '''
+        ''' Write thumbnails to file and return list of (thumb_filename, final_thumb_filename); or None if error '''
         write_all = self.params.get('write_all_thumbnails', False)
         thumbnails, ret = [], []
         if write_all or self.params.get('writethumbnail', False):
@@ -4279,6 +4287,9 @@ class YoutubeDL:
             self.write_debug(f'Skipping writing {label} thumbnail')
             return ret
 
+        if not self._ensure_dir_exists(filename):
+            return None
+
         for idx, t in list(enumerate(thumbnails))[::-1]:
             thumb_ext = (f'{t["id"]}.' if multiple else '') + determine_ext(t['url'], 'jpg')
             thumb_display_id = f'{label} thumbnail {t["id"]}'

yt_dlp/__pyinstaller/hook-yt_dlp.py

@@ -21,7 +21,9 @@ def get_hidden_imports():
     yield from ('yt_dlp.compat._legacy', 'yt_dlp.compat._deprecated')
     yield from ('yt_dlp.utils._legacy', 'yt_dlp.utils._deprecated')
     yield pycryptodome_module()
-    yield from collect_submodules('websockets')
+    # Only `websockets` is required, others are collected just in case
+    for module in ('websockets', 'requests', 'urllib3'):
+        yield from collect_submodules(module)
     # These are auto-detected, but explicitly add them just in case
     yield from ('mutagen', 'brotli', 'certifi', 'curl_cffi')
 

yt_dlp/dependencies/__init__.py

@@ -58,6 +58,16 @@ except (ImportError, SyntaxError):
     # See https://github.com/yt-dlp/yt-dlp/issues/2633
     websockets = None
 
+try:
+    import urllib3
+except ImportError:
+    urllib3 = None
+
+try:
+    import requests
+except ImportError:
+    requests = None
+
 try:
     import xattr  # xattr or pyxattr
 except ImportError:

yt_dlp/extractor/_extractors.py

@@ -896,6 +896,10 @@ from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .joj import JojIE
 from .jstream import JStreamIE
+from .jtbc import (
+    JTBCIE,
+    JTBCProgramIE,
+)
 from .jwplatform import JWPlatformIE
 from .kakao import KakaoIE
 from .kaltura import KalturaIE
@@ -1053,6 +1057,7 @@ from .markiza import (
 from .massengeschmacktv import MassengeschmackTVIE
 from .masters import MastersIE
 from .matchtv import MatchTVIE
+from .mbn import MBNIE
 from .mdr import MDRIE
 from .medaltv import MedalTVIE
 from .mediaite import MediaiteIE

yt_dlp/extractor/banbye.py

@@ -31,7 +31,7 @@ class BanByeBaseIE(InfoExtractor):
 
 
 class BanByeIE(BanByeBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?watch/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
         'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
@@ -120,7 +120,7 @@ class BanByeIE(BanByeBaseIE):
 
 
 class BanByeChannelIE(BanByeBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?channel/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?channel/(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://banbye.com/channel/ch_wrealu24',
         'info_dict': {

yt_dlp/extractor/breitbart.py

@@ -2,7 +2,7 @@ from .common import InfoExtractor
 
 
 class BreitBartIE(InfoExtractor):
-    _VALID_URL = r'https?:\/\/(?:www\.)breitbart.com/videos/v/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?breitbart\.com/videos/v/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.breitbart.com/videos/v/5cOz1yup/?pl=Ij6NDOji',
         'md5': '0aa6d1d6e183ac5ca09207fe49f17ade',

yt_dlp/extractor/craftsy.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class CraftsyIE(InfoExtractor):
-    _VALID_URL = r'https?://www.craftsy.com/class/(?P<id>[a-z0-9_-]+)/'
+    _VALID_URL = r'https?://www\.craftsy\.com/class/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://www.craftsy.com/class/the-midnight-quilt-show-season-5/',
         'info_dict': {

yt_dlp/extractor/cybrary.py

@@ -45,7 +45,7 @@ class CybraryBaseIE(InfoExtractor):
 
 
 class CybraryIE(CybraryBaseIE):
-    _VALID_URL = r'https?://app.cybrary.it/immersive/(?P<enrollment>[0-9]+)/activity/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://app\.cybrary\.it/immersive/(?P<enrollment>[0-9]+)/activity/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://app.cybrary.it/immersive/12487950/activity/63102',
         'md5': '9ae12d37e555cb2ed554223a71a701d0',
@@ -110,7 +110,7 @@ class CybraryIE(CybraryBaseIE):
 
 
 class CybraryCourseIE(CybraryBaseIE):
-    _VALID_URL = r'https://app.cybrary.it/browse/course/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'https://app\.cybrary\.it/browse/course/(?P<id>[\w-]+)/?(?:$|[#?])'
     _TESTS = [{
         'url': 'https://app.cybrary.it/browse/course/az-500-microsoft-azure-security-technologies',
         'info_dict': {

yt_dlp/extractor/fifa.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class FifaIE(InfoExtractor):
-    _VALID_URL = r'https?://www.fifa.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
+    _VALID_URL = r'https?://www\.fifa\.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
         'info_dict': {

yt_dlp/extractor/filmmodu.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none
 
 
 class FilmmoduIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?filmmodu.org/(?P<id>[^/]+-(?:turkce-dublaj-izle|altyazili-izle))'
+    _VALID_URL = r'https?://(?:www\.)?filmmodu\.org/(?P<id>[^/]+-(?:turkce-dublaj-izle|altyazili-izle))'
     _TESTS = [{
         'url': 'https://www.filmmodu.org/f9-altyazili-izle',
         'md5': 'aeefd955c2a508a5bdaa3bcec8eeb0d4',

yt_dlp/extractor/itprotv.py

@@ -31,7 +31,7 @@ class ITProTVBaseIE(InfoExtractor):
 
 
 class ITProTVIE(ITProTVBaseIE):
-    _VALID_URL = r'https://app.itpro.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
+    _VALID_URL = r'https://app\.itpro\.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://app.itpro.tv/course/guided-tour/introductionitprotv',
         'md5': 'bca4a28c2667fd1a63052e71a94bb88c',
@@ -102,7 +102,7 @@ class ITProTVIE(ITProTVBaseIE):
 
 
 class ITProTVCourseIE(ITProTVBaseIE):
-    _VALID_URL = r'https?://app.itpro.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
     _TESTS = [
         {
             'url': 'https://app.itpro.tv/course/guided-tour',

yt_dlp/extractor/jable.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class JableIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jable.tv/videos/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://jable.tv/videos/pppd-812/',
         'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
@@ -64,7 +64,7 @@ class JableIE(InfoExtractor):
 
 
 class JablePlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jable.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://jable.tv/models/kaede-karen/',
         'info_dict': {

yt_dlp/extractor/jtbc.py

@@ -0,0 +1,156 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class JTBCIE(InfoExtractor):
+    IE_DESC = 'jtbc.co.kr'
+    _VALID_URL = r'''(?x)
+        https?://(?:
+            vod\.jtbc\.co\.kr/player/(?:program|clip)
+            |tv\.jtbc\.co\.kr/(?:replay|trailer|clip)/pr\d+/pm\d+
+        )/(?P<id>(?:ep|vo)\d+)'''
+    _GEO_COUNTRIES = ['KR']
+
+    _TESTS = [{
+        'url': 'https://tv.jtbc.co.kr/replay/pr10011629/pm10067930/ep20216321/view',
+        'md5': 'e6ade71d8c8685bbfd6e6ce4167c6a6c',
+        'info_dict': {
+            'id': 'VO10721192',
+            'display_id': 'ep20216321',
+            'ext': 'mp4',
+            'title': '힘쎈여자 강남순 2회 다시보기',
+            'description': 'md5:043c1d9019100ce271dba09995dbd1e2',
+            'duration': 3770.0,
+            'release_date': '20231008',
+            'age_limit': 15,
+            'thumbnail': 'https://fs.jtbc.co.kr//joydata/CP00000001/prog/drama/stronggirlnamsoon/img/20231008_163541_522_1.jpg',
+            'series': '힘쎈여자 강남순',
+        },
+    }, {
+        'url': 'https://vod.jtbc.co.kr/player/program/ep20216733',
+        'md5': '217a6d190f115a75e4bda0ceaa4cd7f4',
+        'info_dict': {
+            'id': 'VO10721429',
+            'display_id': 'ep20216733',
+            'ext': 'mp4',
+            'title': '헬로 마이 닥터 친절한 진료실 149회 다시보기',
+            'description': 'md5:1d70788a982dd5de26874a92fcffddb8',
+            'duration': 2720.0,
+            'release_date': '20231009',
+            'age_limit': 15,
+            'thumbnail': 'https://fs.jtbc.co.kr//joydata/CP00000001/prog/culture/hellomydoctor/img/20231009_095002_528_1.jpg',
+            'series': '헬로 마이 닥터 친절한 진료실',
+        },
+    }, {
+        'url': 'https://vod.jtbc.co.kr/player/clip/vo10721270',
+        'md5': '05782e2dc22a9c548aebefe62ae4328a',
+        'info_dict': {
+            'id': 'VO10721270',
+            'display_id': 'vo10721270',
+            'ext': 'mp4',
+            'title': '뭉쳐야 찬다3 2회 예고편 - A매치로 향하는 마지막 관문💥',
+            'description': 'md5:d48b51a8655c84843b4ed8d0c39aae68',
+            'duration': 46.0,
+            'release_date': '20231015',
+            'age_limit': 15,
+            'thumbnail': 'https://fs.jtbc.co.kr//joydata/CP00000001/prog/enter/soccer3/img/20231008_210957_775_1.jpg',
+            'series': '뭉쳐야 찬다3',
+        },
+    }, {
+        'url': 'https://tv.jtbc.co.kr/trailer/pr10010392/pm10032526/vo10720912/view',
+        'md5': '367d480eb3ef54a9cd7a4b4d69c4b32d',
+        'info_dict': {
+            'id': 'VO10720912',
+            'display_id': 'vo10720912',
+            'ext': 'mp4',
+            'title': '아는 형님 404회 예고편 | 10월 14일(토) 저녁 8시 50분 방송!',
+            'description': 'md5:2743bb1079ceb85bb00060f2ad8f0280',
+            'duration': 148.0,
+            'release_date': '20231014',
+            'age_limit': 15,
+            'thumbnail': 'https://fs.jtbc.co.kr//joydata/CP00000001/prog/enter/jtbcbros/img/20231006_230023_802_1.jpg',
+            'series': '아는 형님',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        if display_id.startswith('vo'):
+            video_id = display_id.upper()
+        else:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'data-vod="(VO\d+)"', webpage, 'vod id')
+
+        playback_data = self._download_json(
+            f'https://api.jtbc.co.kr/vod/{video_id}', video_id, note='Downloading VOD playback data')
+
+        subtitles = {}
+        for sub in traverse_obj(playback_data, ('tracks', lambda _, v: v['file'])):
+            subtitles.setdefault(sub.get('label', 'und'), []).append({'url': sub['file']})
+
+        formats = []
+        for stream_url in traverse_obj(playback_data, ('sources', 'HLS', ..., 'file', {url_or_none})):
+            stream_url = re.sub(r'/playlist(?:_pd\d+)?\.m3u8', '/index.m3u8', stream_url)
+            formats.extend(self._extract_m3u8_formats(stream_url, video_id, fatal=False))
+
+        metadata = self._download_json(
+            'https://now-api.jtbc.co.kr/v1/vod/detail', video_id,
+            note='Downloading mobile details', fatal=False, query={'vodFileId': video_id})
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            **traverse_obj(metadata, ('vodDetail', {
+                'title': 'vodTitleView',
+                'series': 'programTitle',
+                'age_limit': ('watchAge', {int_or_none}),
+                'release_date': ('broadcastDate', {lambda x: re.match(r'\d{8}', x.replace('.', ''))}, 0),
+                'description': 'episodeContents',
+                'thumbnail': ('imgFileUrl', {url_or_none}),
+            })),
+            'duration': parse_duration(playback_data.get('playTime')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class JTBCProgramIE(InfoExtractor):
+    IE_NAME = 'JTBC:program'
+    _VALID_URL = r'https?://(?:vod\.jtbc\.co\.kr/program|tv\.jtbc\.co\.kr/replay)/(?P<id>pr\d+)/(?:replay|pm\d+)/?(?:$|[?#])'
+
+    _TESTS = [{
+        'url': 'https://tv.jtbc.co.kr/replay/pr10010392/pm10032710',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'pr10010392',
+        },
+        'playlist_count': 398,
+    }, {
+        'url': 'https://vod.jtbc.co.kr/program/pr10011491/replay',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'pr10011491',
+        },
+        'playlist_count': 59,
+    }]
+
+    def _real_extract(self, url):
+        program_id = self._match_id(url)
+
+        vod_list = self._download_json(
+            'https://now-api.jtbc.co.kr/v1/vodClip/programHome/programReplayVodList', program_id,
+            note='Downloading program replay list', query={
+                'programId': program_id,
+                'rowCount': '10000',
+            })
+
+        entries = [self.url_result(f'https://vod.jtbc.co.kr/player/program/{video_id}', JTBCIE, video_id)
+                   for video_id in traverse_obj(vod_list, ('programReplayVodList', ..., 'episodeId'))]
+        return self.playlist_result(entries, program_id)

yt_dlp/extractor/kommunetv.py

@@ -3,7 +3,7 @@ from ..utils import update_url
 
 
 class KommunetvIE(InfoExtractor):
-    _VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
+    _VALID_URL = r'https://\w+\.kommunetv\.no/archive/(?P<id>\w+)'
     _TEST = {
         'url': 'https://oslo.kommunetv.no/archive/921',
         'md5': '5f102be308ee759be1e12b63d5da4bbc',

yt_dlp/extractor/mainstreaming.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class MainStreamingIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn\.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
     _EMBED_REGEX = [rf'<iframe[^>]+?src=["\']?(?P<url>{_VALID_URL})["\']?']
     IE_DESC = 'MainStreaming Player'
 

yt_dlp/extractor/mbn.py

@@ -0,0 +1,89 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class MBNIE(InfoExtractor):
+    IE_DESC = 'mbn.co.kr (매일방송)'
+    _VALID_URL = r'https?://(?:www\.)?mbn\.co\.kr/vod/programContents/preview(?:list)?/\d+/\d+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://mbn.co.kr/vod/programContents/previewlist/861/5433/1276155',
+        'md5': '85e1694e5b247c04d1386b7e3c90fd76',
+        'info_dict': {
+            'id': '1276155',
+            'ext': 'mp4',
+            'title': '결국 사로잡힌 권유리, 그녀를 목숨 걸고 구하려는 정일우!',
+            'duration': 3891,
+            'release_date': '20210703',
+            'thumbnail': 'http://img.vod.mbn.co.kr/mbnvod2img/861/2021/07/03/20210703230811_20_861_1276155_360_7_0.jpg',
+            'series': '보쌈 - 운명을 훔치다',
+            'episode': 'Episode 19',
+            'episode_number': 19,
+        },
+    }, {
+        'url': 'https://www.mbn.co.kr/vod/programContents/previewlist/835/5294/1084744',
+        'md5': 'fc65d3aac85e85e0b5056f4ef99cde4a',
+        'info_dict': {
+            'id': '1084744',
+            'ext': 'mp4',
+            'title': '김정은♥최원영, 제자리를 찾은 위험한 부부! ＂결혼은 투쟁이면서, 어려운 방식이야..＂',
+            'duration': 93,
+            'release_date': '20201124',
+            'thumbnail': 'http://img.vod.mbn.co.kr/mbnvod2img/835/2020/11/25/20201125000221_21_835_1084744_360_7_0.jpg',
+            'series': '나의 위험한 아내',
+        },
+    }, {
+        'url': 'https://www.mbn.co.kr/vod/programContents/preview/952/6088/1054797?next=1',
+        'md5': 'c711103c72aeac8323a5cf1751f10097',
+        'info_dict': {
+            'id': '1054797',
+            'ext': 'mp4',
+            'title': '[2차 티저] MBN 주말 미니시리즈 <완벽한 결혼의 정석> l 그녀에게 주어진 두 번째 인생',
+            'duration': 65,
+            'release_date': '20231028',
+            'thumbnail': 'http://img.vod.mbn.co.kr/vod2/952/2023/09/11/20230911130223_22_952_1054797_1080_7.jpg',
+            'series': '완벽한 결혼의 정석',
+        },
+    }]
+
+    def _real_extract(self, url):
+        content_id = self._match_id(url)
+        webpage = self._download_webpage(url, content_id)
+
+        content_cls_cd = self._search_regex(
+            r'"\?content_cls_cd=(\d+)&', webpage, 'content cls cd', fatal=False) or '20'
+        media_info = self._download_json(
+            'https://www.mbn.co.kr/player/mbnVodPlayer_2020.mbn', content_id,
+            note='Fetching playback data', query={
+                'content_cls_cd': content_cls_cd,
+                'content_id': content_id,
+                'relay_type': '1',
+            })
+
+        formats = []
+        for stream_url in traverse_obj(media_info, ('movie_list', ..., 'url', {url_or_none})):
+            stream_url = re.sub(r'/(?:chunk|play)list(?:_pd\d+)?\.m3u8', '/manifest.m3u8', stream_url)
+            final_url = url_or_none(self._download_webpage(
+                f'https://www.mbn.co.kr/player/mbnStreamAuth_new_vod.mbn?vod_url={stream_url}',
+                content_id, note='Fetching authenticated m3u8 url'))
+
+            formats.extend(self._extract_m3u8_formats(final_url, content_id, fatal=False))
+
+        return {
+            'id': content_id,
+            **traverse_obj(media_info, {
+                'title': ('movie_title', {str}),
+                'duration': ('play_sec', {int_or_none}),
+                'release_date': ('bcast_date', {lambda x: x.replace('.', '')}, {unified_strdate}),
+                'thumbnail': ('movie_start_Img', {url_or_none}),
+                'series': ('prog_nm', {str}),
+                'episode_number': ('ad_contentnumber', {int_or_none}),
+            }),
+            'formats': formats,
+        }

yt_dlp/extractor/mediaite.py

@@ -2,7 +2,7 @@ from .common import InfoExtractor
 
 
 class MediaiteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mediaite.com(?!/category)(?:/[\w-]+){2}'
+    _VALID_URL = r'https?://(?:www\.)?mediaite\.com(?!/category)(?:/[\w-]+){2}'
     _TESTS = [{
         'url': 'https://www.mediaite.com/sports/bill-burr-roasts-nfl-for-promoting-black-lives-matter-while-scheduling-more-games-after-all-the-sht-they-know-about-cte/',
         'info_dict': {

yt_dlp/extractor/mocha.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none, traverse_obj
 
 
 class MochaVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://video.mocha.com.vn/(?P<video_slug>[\w-]+)'
+    _VALID_URL = r'https?://video\.mocha\.com\.vn/(?P<video_slug>[\w-]+)'
     _TESTS = [{
         'url': 'http://video.mocha.com.vn/chuyen-meo-gia-su-tu-thong-diep-cuoc-song-v18694039',
         'info_dict': {

yt_dlp/extractor/nfl.py

@@ -247,7 +247,7 @@ class NFLArticleIE(NFLBaseIE):
 
 class NFLPlusReplayIE(NFLBaseIE):
     IE_NAME = 'nfl.com:plus:replay'
-    _VALID_URL = r'https?://(?:www\.)?nfl.com/plus/games/(?P<slug>[\w-]+)(?:/(?P<id>\d+))?'
+    _VALID_URL = r'https?://(?:www\.)?nfl\.com/plus/games/(?P<slug>[\w-]+)(?:/(?P<id>\d+))?'
     _TESTS = [{
         'url': 'https://www.nfl.com/plus/games/giants-at-vikings-2022-post-1/1572108',
         'info_dict': {
@@ -342,7 +342,7 @@ class NFLPlusReplayIE(NFLBaseIE):
 
 class NFLPlusEpisodeIE(NFLBaseIE):
     IE_NAME = 'nfl.com:plus:episode'
-    _VALID_URL = r'https?://(?:www\.)?nfl.com/plus/episodes/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?nfl\.com/plus/episodes/(?P<id>[\w-]+)'
     _TESTS = [{
         'note': 'Subscription required',
         'url': 'https://www.nfl.com/plus/episodes/kurt-s-qb-insider-conference-championships',

yt_dlp/extractor/novaplay.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none, parse_duration, parse_iso8601
 
 
 class NovaPlayIE(InfoExtractor):
-    _VALID_URL = r'https://play.nova\.bg/video/.*/(?P<id>\d+)'
+    _VALID_URL = r'https://play\.nova\.bg/video/[^?#]+/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'https://play.nova.bg/video/ochakvaite/season-0/ochakvaite-2022-07-22-sybudi-se-sat/606627',

yt_dlp/extractor/nubilesporn.py

@@ -19,7 +19,7 @@ from ..utils import (
 class NubilesPornIE(InfoExtractor):
     _NETRC_MACHINE = 'nubiles-porn'
     _VALID_URL = r'''(?x)
-        https://members.nubiles-porn.com/video/watch/(?P<id>\d+)
+        https://members\.nubiles-porn\.com/video/watch/(?P<id>\d+)
         (?:/(?P<display_id>[\w\-]+-s(?P<season>\d+)e(?P<episode>\d+)))?
     '''
 

yt_dlp/extractor/oftv.py

@@ -4,7 +4,7 @@ from ..utils import traverse_obj
 
 
 class OfTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?of.tv/video/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?of\.tv/video/(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://of.tv/video/627d7d95b353db0001dadd1a',
         'md5': 'cb9cd5db3bb9ee0d32bfd7e373d6ef0a',
@@ -34,7 +34,7 @@ class OfTVIE(InfoExtractor):
 
 
 class OfTVPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?of.tv/creators/(?P<id>[a-zA-Z0-9-]+)/.?'
+    _VALID_URL = r'https?://(?:www\.)?of\.tv/creators/(?P<id>[a-zA-Z0-9-]+)/?(?:$|[?#])'
     _TESTS = [{
         'url': 'https://of.tv/creators/this-is-fire/',
         'playlist_count': 8,

yt_dlp/extractor/radiko.py

@@ -154,7 +154,7 @@ class RadikoBaseIE(InfoExtractor):
                     sf['preference'] = -100
                     sf['format_note'] = 'not preferred'
                 if not is_onair and timefree_int == 1 and time_to_skip:
-                    sf['downloader_options'] = {'ffmpeg_args': ['-ss', time_to_skip]}
+                    sf['downloader_options'] = {'ffmpeg_args': ['-ss', str(time_to_skip)]}
             formats.extend(subformats)
 
         return formats

yt_dlp/extractor/sina.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class SinaIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:.*?\.)?video\.sina\.com\.cn/
+    _VALID_URL = r'''(?x)https?://(?:[^/?#]+\.)?video\.sina\.com\.cn/
                         (?:
                             (?:view/|.*\#)(?P<id>\d+)|
                             .+?/(?P<pseudo_id>[^/?#]+)(?:\.s?html)|

yt_dlp/extractor/twitter.py

@@ -1741,7 +1741,7 @@ class TwitterSpacesIE(TwitterBaseIE):
 
 class TwitterShortenerIE(TwitterBaseIE):
     IE_NAME = 'twitter:shortener'
-    _VALID_URL = r'https?://t.co/(?P<id>[^?]+)|tco:(?P<eid>[^?]+)'
+    _VALID_URL = r'https?://t\.co/(?P<id>[^?#]+)|tco:(?P<eid>[^?#]+)'
     _BASE_URL = 'https://t.co/'
 
     def _real_extract(self, url):

yt_dlp/extractor/utreon.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class UtreonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?utreon.com/v/(?P<id>[a-zA-Z0-9_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?utreon\.com/v/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://utreon.com/v/z_I7ikQbuDw',
         'info_dict': {

yt_dlp/extractor/vk.py

@@ -97,12 +97,12 @@ class VKIE(VKBaseIE):
                         (?:
                             (?:
                                 (?:(?:m|new)\.)?vk\.com/video_|
-                                (?:www\.)?daxab.com/
+                                (?:www\.)?daxab\.com/
                             )
                             ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
                             (?:
                                 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
-                                (?:www\.)?daxab.com/embed/
+                                (?:www\.)?daxab\.com/embed/
                             )
                             (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
                         )

yt_dlp/extractor/weverse.py

@@ -182,7 +182,7 @@ class WeverseBaseIE(InfoExtractor):
 
 
 class WeverseIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/live/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/live/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/live/0-107323480',
         'md5': '1fa849f00181eef9100d3c8254c47979',
@@ -344,7 +344,7 @@ class WeverseIE(WeverseBaseIE):
 
 
 class WeverseMediaIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/media/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/media/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/media/4-116372884',
         'md5': '8efc9cfd61b2f25209eb1a5326314d28',
@@ -420,7 +420,7 @@ class WeverseMediaIE(WeverseBaseIE):
 
 
 class WeverseMomentIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/moment/(?P<uid>[\da-f]+)/post/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/moment/(?P<uid>[\da-f]+)/post/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/secretnumber/moment/66a07e164b56a696ee71c99315ffe27b/post/1-117229444',
         'md5': '87733ac19a54081b7dfc2442036d282b',
@@ -516,7 +516,7 @@ class WeverseTabBaseIE(WeverseBaseIE):
 
 
 class WeverseLiveTabIE(WeverseTabBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/live/?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/live/?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/live/',
         'playlist_mincount': 55,
@@ -534,7 +534,7 @@ class WeverseLiveTabIE(WeverseTabBaseIE):
 
 
 class WeverseMediaTabIE(WeverseTabBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/media(?:/|/all|/new)?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/media(?:/|/all|/new)?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/media/',
         'playlist_mincount': 231,
@@ -558,7 +558,7 @@ class WeverseMediaTabIE(WeverseTabBaseIE):
 
 
 class WeverseLiveIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/purplekiss',
         'info_dict': {

yt_dlp/extractor/wimtv.py

@@ -11,7 +11,7 @@ class WimTVIE(InfoExtractor):
     _player = None
     _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
     _VALID_URL = r'''(?x:
-        https?://platform.wim.tv/
+        https?://platform\.wim\.tv/
         (?:
             (?:embed/)?\?
             |\#/webtv/.+?/

yt_dlp/extractor/xhamster.py

@@ -24,7 +24,7 @@ class XHamsterIE(InfoExtractor):
     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:.+?\.)?%s/
+                        (?:[^/?#]+\.)?%s/
                         (?:
                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
@@ -372,7 +372,7 @@ class XHamsterIE(InfoExtractor):
 
 
 class XHamsterEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
+    _VALID_URL = r'https?://(?:[^/?#]+\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1']
     _TEST = {
         'url': 'http://xhamster.com/xembed.php?video=3328539',

yt_dlp/extractor/youtube.py

@@ -949,7 +949,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         main_rm = next(main_retries)
         # Manual retry loop for multiple RetryManagers
         # The proper RetryManager MUST be advanced after an error
-        # and it's result MUST be checked if the manager is non fatal
+        # and its result MUST be checked if the manager is non fatal
         while True:
             try:
                 response = self._call_api(

yt_dlp/extractor/zoom.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class ZoomIE(InfoExtractor):
     IE_NAME = 'zoom'
-    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?P<type>play|share)/(?P<id>[A-Za-z0-9_.-]+)'
+    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom\.us/)rec(?:ording)?/(?P<type>play|share)/(?P<id>[\w.-]+)'
     _TESTS = [{
         'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
         'md5': 'ab445e8c911fddc4f9adc842c2c5d434',

yt_dlp/networking/__init__.py

@@ -13,10 +13,18 @@ from .common import (
 # isort: split
 # TODO: all request handlers should be safely imported
 from . import _urllib
+from ..utils import bug_reports_message
+
+try:
+    from . import _requests
+except ImportError:
+    pass
+except Exception as e:
+    warnings.warn(f'Failed to import "requests" request handler: {e}' + bug_reports_message())
 
 try:
     from . import _curlcffi  # noqa: F401
 except ImportError:
     pass
 except Exception as e:
-    warnings.warn(f'Failed to import curl_cffi handler: {e}')
+    warnings.warn(f'Failed to import "curl_cffi" request handler: {e}' + bug_reports_message())

yt_dlp/networking/_curlcffi.py

@@ -37,19 +37,29 @@ class CurlCFFIResponseReader(io.IOBase):
         return True
 
     def read(self, size=None):
-        if self._eof:
+        try:
-            return b''
+            while not self._eof and (size is None or len(self._buffer) < size):
+                chunk = next(self._response.iter_content(), None)
+                if chunk is None:
+                    self._eof = True
+                    break
+                self._buffer += chunk
 
-        while size is None or len(self._buffer) < size:
+            if size is None:
-            chunk = next(self._response.iter_content(), None)
+                data = self._buffer
-            if chunk is None:
+                self._buffer = b''
-                self._eof = True
+            else:
-                break
+                data = self._buffer[:size]
-            self._buffer += chunk
+                self._buffer = self._buffer[size:]
 
-        data = self._buffer[:size]
+            # "free" the curl instance if the response is fully read.
-        self._buffer = self._buffer[size:]
+            # curl_cffi doesn't do this automatically and only allows one open response per thread
-        return data
+            if self._eof and len(self._buffer) == 0:
+                self.close()
+            return data
+        except Exception:
+            self.close()
+            raise
 
     def close(self):
         self._response.close()

yt_dlp/networking/_helper.py

@@ -11,7 +11,7 @@ import urllib.request
 
 from .exceptions import RequestError, UnsupportedRequest
 from ..dependencies import certifi
-from ..socks import ProxyType
+from ..socks import ProxyType, sockssocket
 from ..utils import format_field, traverse_obj
 
 if typing.TYPE_CHECKING:
@@ -224,6 +224,24 @@ def _socket_connect(ip_addr, timeout, source_address):
         raise
 
 
+def create_socks_proxy_socket(dest_addr, proxy_args, proxy_ip_addr, timeout, source_address):
+    af, socktype, proto, canonname, sa = proxy_ip_addr
+    sock = sockssocket(af, socktype, proto)
+    try:
+        connect_proxy_args = proxy_args.copy()
+        connect_proxy_args.update({'addr': sa[0], 'port': sa[1]})
+        sock.setproxy(**connect_proxy_args)
+        if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:  # noqa: E721
+            sock.settimeout(timeout)
+        if source_address:
+            sock.bind(source_address)
+        sock.connect(dest_addr)
+        return sock
+    except socket.error:
+        sock.close()
+        raise
+
+
 def create_connection(
     address,
     timeout=socket._GLOBAL_DEFAULT_TIMEOUT,

yt_dlp/networking/_requests.py

@@ -0,0 +1,397 @@
+import contextlib
+import functools
+import http.client
+import logging
+import re
+import socket
+import warnings
+
+from ..dependencies import brotli, requests, urllib3
+from ..utils import bug_reports_message, int_or_none, variadic
+
+if requests is None:
+    raise ImportError('requests module is not installed')
+
+if urllib3 is None:
+    raise ImportError('urllib3 module is not installed')
+
+urllib3_version = tuple(int_or_none(x, default=0) for x in urllib3.__version__.split('.'))
+
+if urllib3_version < (1, 26, 17):
+    raise ImportError('Only urllib3 >= 1.26.17 is supported')
+
+if requests.__build__ < 0x023100:
+    raise ImportError('Only requests >= 2.31.0 is supported')
+
+import requests.adapters
+import requests.utils
+import urllib3.connection
+import urllib3.exceptions
+
+from ._helper import (
+    InstanceStoreMixin,
+    add_accept_encoding_header,
+    create_connection,
+    create_socks_proxy_socket,
+    get_redirect_method,
+    make_socks_proxy_opts,
+    select_proxy,
+)
+from .common import (
+    Features,
+    RequestHandler,
+    Response,
+    register_preference,
+    register_rh,
+)
+from .exceptions import (
+    CertificateVerifyError,
+    HTTPError,
+    IncompleteRead,
+    ProxyError,
+    RequestError,
+    SSLError,
+    TransportError,
+)
+from ..socks import ProxyError as SocksProxyError
+
+SUPPORTED_ENCODINGS = [
+    'gzip', 'deflate'
+]
+
+if brotli is not None:
+    SUPPORTED_ENCODINGS.append('br')
+
+"""
+Override urllib3's behavior to not convert lower-case percent-encoded characters
+to upper-case during url normalization process.
+
+RFC3986 defines that the lower or upper case percent-encoded hexidecimal characters are equivalent
+and normalizers should convert them to uppercase for consistency [1].
+
+However, some sites may have an incorrect implementation where they provide
+a percent-encoded url that is then compared case-sensitively.[2]
+
+While this is a very rare case, since urllib does not do this normalization step, it
+is best to avoid it in requests too for compatability reasons.
+
+1: https://tools.ietf.org/html/rfc3986#section-2.1
+2: https://github.com/streamlink/streamlink/pull/4003
+"""
+
+
+class Urllib3PercentREOverride:
+    def __init__(self, r: re.Pattern):
+        self.re = r
+
+    # pass through all other attribute calls to the original re
+    def __getattr__(self, item):
+        return self.re.__getattribute__(item)
+
+    def subn(self, repl, string, *args, **kwargs):
+        return string, self.re.subn(repl, string, *args, **kwargs)[1]
+
+
+# urllib3 >= 1.25.8 uses subn:
+# https://github.com/urllib3/urllib3/commit/a2697e7c6b275f05879b60f593c5854a816489f0
+import urllib3.util.url  # noqa: E305
+
+if hasattr(urllib3.util.url, 'PERCENT_RE'):
+    urllib3.util.url.PERCENT_RE = Urllib3PercentREOverride(urllib3.util.url.PERCENT_RE)
+elif hasattr(urllib3.util.url, '_PERCENT_RE'):  # urllib3 >= 2.0.0
+    urllib3.util.url._PERCENT_RE = Urllib3PercentREOverride(urllib3.util.url._PERCENT_RE)
+else:
+    warnings.warn('Failed to patch PERCENT_RE in urllib3 (does the attribute exist?)' + bug_reports_message())
+
+"""
+Workaround for issue in urllib.util.ssl_.py: ssl_wrap_context does not pass
+server_hostname to SSLContext.wrap_socket if server_hostname is an IP,
+however this is an issue because we set check_hostname to True in our SSLContext.
+
+Monkey-patching IS_SECURETRANSPORT forces ssl_wrap_context to pass server_hostname regardless.
+
+This has been fixed in urllib3 2.0+.
+See: https://github.com/urllib3/urllib3/issues/517
+"""
+
+if urllib3_version < (2, 0, 0):
+    with contextlib.suppress():
+        urllib3.util.IS_SECURETRANSPORT = urllib3.util.ssl_.IS_SECURETRANSPORT = True
+
+
+# Requests will not automatically handle no_proxy by default
+# due to buggy no_proxy handling with proxy dict [1].
+# 1. https://github.com/psf/requests/issues/5000
+requests.adapters.select_proxy = select_proxy
+
+
+class RequestsResponseAdapter(Response):
+    def __init__(self, res: requests.models.Response):
+        super().__init__(
+            fp=res.raw, headers=res.headers, url=res.url,
+            status=res.status_code, reason=res.reason)
+
+        self._requests_response = res
+
+    def read(self, amt: int = None):
+        try:
+            # Interact with urllib3 response directly.
+            return self.fp.read(amt, decode_content=True)
+
+        # See urllib3.response.HTTPResponse.read() for exceptions raised on read
+        except urllib3.exceptions.SSLError as e:
+            raise SSLError(cause=e) from e
+
+        except urllib3.exceptions.ProtocolError as e:
+            # IncompleteRead is always contained within ProtocolError
+            # See urllib3.response.HTTPResponse._error_catcher()
+            ir_err = next(
+                (err for err in (e.__context__, e.__cause__, *variadic(e.args))
+                 if isinstance(err, http.client.IncompleteRead)), None)
+            if ir_err is not None:
+                # `urllib3.exceptions.IncompleteRead` is subclass of `http.client.IncompleteRead`
+                # but uses an `int` for its `partial` property.
+                partial = ir_err.partial if isinstance(ir_err.partial, int) else len(ir_err.partial)
+                raise IncompleteRead(partial=partial, expected=ir_err.expected) from e
+            raise TransportError(cause=e) from e
+
+        except urllib3.exceptions.HTTPError as e:
+            # catch-all for any other urllib3 response exceptions
+            raise TransportError(cause=e) from e
+
+
+class RequestsHTTPAdapter(requests.adapters.HTTPAdapter):
+    def __init__(self, ssl_context=None, proxy_ssl_context=None, source_address=None, **kwargs):
+        self._pm_args = {}
+        if ssl_context:
+            self._pm_args['ssl_context'] = ssl_context
+        if source_address:
+            self._pm_args['source_address'] = (source_address, 0)
+        self._proxy_ssl_context = proxy_ssl_context or ssl_context
+        super().__init__(**kwargs)
+
+    def init_poolmanager(self, *args, **kwargs):
+        return super().init_poolmanager(*args, **kwargs, **self._pm_args)
+
+    def proxy_manager_for(self, proxy, **proxy_kwargs):
+        extra_kwargs = {}
+        if not proxy.lower().startswith('socks') and self._proxy_ssl_context:
+            extra_kwargs['proxy_ssl_context'] = self._proxy_ssl_context
+        return super().proxy_manager_for(proxy, **proxy_kwargs, **self._pm_args, **extra_kwargs)
+
+    def cert_verify(*args, **kwargs):
+        # lean on SSLContext for cert verification
+        pass
+
+
+class RequestsSession(requests.sessions.Session):
+    """
+    Ensure unified redirect method handling with our urllib redirect handler.
+    """
+    def rebuild_method(self, prepared_request, response):
+        new_method = get_redirect_method(prepared_request.method, response.status_code)
+
+        # HACK: requests removes headers/body on redirect unless code was a 307/308.
+        if new_method == prepared_request.method:
+            response._real_status_code = response.status_code
+            response.status_code = 308
+
+        prepared_request.method = new_method
+
+    def rebuild_auth(self, prepared_request, response):
+        # HACK: undo status code change from rebuild_method, if applicable.
+        # rebuild_auth runs after requests would remove headers/body based on status code
+        if hasattr(response, '_real_status_code'):
+            response.status_code = response._real_status_code
+            del response._real_status_code
+        return super().rebuild_auth(prepared_request, response)
+
+
+class Urllib3LoggingFilter(logging.Filter):
+
+    def filter(self, record):
+        # Ignore HTTP request messages since HTTPConnection prints those
+        if record.msg == '%s://%s:%s "%s %s %s" %s %s':
+            return False
+        return True
+
+
+class Urllib3LoggingHandler(logging.Handler):
+    """Redirect urllib3 logs to our logger"""
+    def __init__(self, logger, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self._logger = logger
+
+    def emit(self, record):
+        try:
+            msg = self.format(record)
+            if record.levelno >= logging.ERROR:
+                self._logger.error(msg)
+            else:
+                self._logger.stdout(msg)
+
+        except Exception:
+            self.handleError(record)
+
+
+@register_rh
+class RequestsRH(RequestHandler, InstanceStoreMixin):
+
+    """Requests RequestHandler
+    https://github.com/psf/requests
+    """
+    _SUPPORTED_URL_SCHEMES = ('http', 'https')
+    _SUPPORTED_ENCODINGS = tuple(SUPPORTED_ENCODINGS)
+    _SUPPORTED_PROXY_SCHEMES = ('http', 'https', 'socks4', 'socks4a', 'socks5', 'socks5h')
+    _SUPPORTED_FEATURES = (Features.NO_PROXY, Features.ALL_PROXY)
+    RH_NAME = 'requests'
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        # Forward urllib3 debug messages to our logger
+        logger = logging.getLogger('urllib3')
+        handler = Urllib3LoggingHandler(logger=self._logger)
+        handler.setFormatter(logging.Formatter('requests: %(message)s'))
+        handler.addFilter(Urllib3LoggingFilter())
+        logger.addHandler(handler)
+        logger.setLevel(logging.WARNING)
+
+        if self.verbose:
+            # Setting this globally is not ideal, but is easier than hacking with urllib3.
+            # It could technically be problematic for scripts embedding yt-dlp.
+            # However, it is unlikely debug traffic is used in that context in a way this will cause problems.
+            urllib3.connection.HTTPConnection.debuglevel = 1
+            logger.setLevel(logging.DEBUG)
+        # this is expected if we are using --no-check-certificate
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+    def close(self):
+        self._clear_instances()
+
+    def _check_extensions(self, extensions):
+        super()._check_extensions(extensions)
+        extensions.pop('cookiejar', None)
+        extensions.pop('timeout', None)
+
+    def _create_instance(self, cookiejar):
+        session = RequestsSession()
+        http_adapter = RequestsHTTPAdapter(
+            ssl_context=self._make_sslcontext(),
+            source_address=self.source_address,
+            max_retries=urllib3.util.retry.Retry(False),
+        )
+        session.adapters.clear()
+        session.headers = requests.models.CaseInsensitiveDict({'Connection': 'keep-alive'})
+        session.mount('https://', http_adapter)
+        session.mount('http://', http_adapter)
+        session.cookies = cookiejar
+        session.trust_env = False  # no need, we already load proxies from env
+        return session
+
+    def _send(self, request):
+
+        headers = self._merge_headers(request.headers)
+        add_accept_encoding_header(headers, SUPPORTED_ENCODINGS)
+
+        max_redirects_exceeded = False
+
+        session = self._get_instance(
+            cookiejar=request.extensions.get('cookiejar') or self.cookiejar)
+
+        try:
+            requests_res = session.request(
+                method=request.method,
+                url=request.url,
+                data=request.data,
+                headers=headers,
+                timeout=float(request.extensions.get('timeout') or self.timeout),
+                proxies=request.proxies or self.proxies,
+                allow_redirects=True,
+                stream=True
+            )
+
+        except requests.exceptions.TooManyRedirects as e:
+            max_redirects_exceeded = True
+            requests_res = e.response
+
+        except requests.exceptions.SSLError as e:
+            if 'CERTIFICATE_VERIFY_FAILED' in str(e):
+                raise CertificateVerifyError(cause=e) from e
+            raise SSLError(cause=e) from e
+
+        except requests.exceptions.ProxyError as e:
+            raise ProxyError(cause=e) from e
+
+        except (requests.exceptions.ConnectionError, requests.exceptions.Timeout) as e:
+            raise TransportError(cause=e) from e
+
+        except urllib3.exceptions.HTTPError as e:
+            # Catch any urllib3 exceptions that may leak through
+            raise TransportError(cause=e) from e
+
+        except requests.exceptions.RequestException as e:
+            # Miscellaneous Requests exceptions. May not necessary be network related e.g. InvalidURL
+            raise RequestError(cause=e) from e
+
+        res = RequestsResponseAdapter(requests_res)
+
+        if not 200 <= res.status < 300:
+            raise HTTPError(res, redirect_loop=max_redirects_exceeded)
+
+        return res
+
+
+@register_preference(RequestsRH)
+def requests_preference(rh, request):
+    return 100
+
+
+# Use our socks proxy implementation with requests to avoid an extra dependency.
+class SocksHTTPConnection(urllib3.connection.HTTPConnection):
+    def __init__(self, _socks_options, *args, **kwargs):  # must use _socks_options to pass PoolKey checks
+        self._proxy_args = _socks_options
+        super().__init__(*args, **kwargs)
+
+    def _new_conn(self):
+        try:
+            return create_connection(
+                address=(self._proxy_args['addr'], self._proxy_args['port']),
+                timeout=self.timeout,
+                source_address=self.source_address,
+                _create_socket_func=functools.partial(
+                    create_socks_proxy_socket, (self.host, self.port), self._proxy_args))
+        except (socket.timeout, TimeoutError) as e:
+            raise urllib3.exceptions.ConnectTimeoutError(
+                self, f'Connection to {self.host} timed out. (connect timeout={self.timeout})') from e
+        except SocksProxyError as e:
+            raise urllib3.exceptions.ProxyError(str(e), e) from e
+        except (OSError, socket.error) as e:
+            raise urllib3.exceptions.NewConnectionError(
+                self, f'Failed to establish a new connection: {e}') from e
+
+
+class SocksHTTPSConnection(SocksHTTPConnection, urllib3.connection.HTTPSConnection):
+    pass
+
+
+class SocksHTTPConnectionPool(urllib3.HTTPConnectionPool):
+    ConnectionCls = SocksHTTPConnection
+
+
+class SocksHTTPSConnectionPool(urllib3.HTTPSConnectionPool):
+    ConnectionCls = SocksHTTPSConnection
+
+
+class SocksProxyManager(urllib3.PoolManager):
+
+    def __init__(self, socks_proxy, username=None, password=None, num_pools=10, headers=None, **connection_pool_kw):
+        connection_pool_kw['_socks_options'] = make_socks_proxy_opts(socks_proxy)
+        super().__init__(num_pools, headers, **connection_pool_kw)
+        self.pool_classes_by_scheme = {
+            'http': SocksHTTPConnectionPool,
+            'https': SocksHTTPSConnectionPool
+        }
+
+
+requests.adapters.SOCKSProxyManager = SocksProxyManager

yt_dlp/networking/_urllib.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 import functools
 import http.client
 import io
-import socket
 import ssl
 import urllib.error
 import urllib.parse
@@ -24,6 +23,7 @@ from ._helper import (
     InstanceStoreMixin,
     add_accept_encoding_header,
     create_connection,
+    create_socks_proxy_socket,
     get_redirect_method,
     make_socks_proxy_opts,
     select_proxy,
@@ -40,7 +40,6 @@ from .exceptions import (
 )
 from ..dependencies import brotli
 from ..socks import ProxyError as SocksProxyError
-from ..socks import sockssocket
 from ..utils import update_url_query
 from ..utils.networking import normalize_url
 
@@ -190,25 +189,12 @@ def make_socks_conn_class(base_class, socks_proxy):
         _create_connection = create_connection
 
         def connect(self):
-            def sock_socket_connect(ip_addr, timeout, source_address):
-                af, socktype, proto, canonname, sa = ip_addr
-                sock = sockssocket(af, socktype, proto)
-                try:
-                    connect_proxy_args = proxy_args.copy()
-                    connect_proxy_args.update({'addr': sa[0], 'port': sa[1]})
-                    sock.setproxy(**connect_proxy_args)
-                    if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:  # noqa: E721
-                        sock.settimeout(timeout)
-                    if source_address:
-                        sock.bind(source_address)
-                    sock.connect((self.host, self.port))
-                    return sock
-                except socket.error:
-                    sock.close()
-                    raise
             self.sock = create_connection(
-                (proxy_args['addr'], proxy_args['port']), timeout=self.timeout,
+                (proxy_args['addr'], proxy_args['port']),
-                source_address=self.source_address, _create_socket_func=sock_socket_connect)
+                timeout=self.timeout,
+                source_address=self.source_address,
+                _create_socket_func=functools.partial(
+                    create_socks_proxy_socket, (self.host, self.port), proxy_args))
             if isinstance(self, http.client.HTTPSConnection):
                 self.sock = self._context.wrap_socket(self.sock, server_hostname=self.host)
 

yt_dlp/networking/exceptions.py

@@ -75,7 +75,7 @@ class HTTPError(RequestError):
 
 
 class IncompleteRead(TransportError):
-    def __init__(self, partial: int, expected: int = None, **kwargs):
+    def __init__(self, partial: int, expected: int | None = None, **kwargs):
         self.partial = partial
         self.expected = expected
         msg = f'{partial} bytes read'

yt_dlp/options.py

@@ -471,11 +471,12 @@ def create_parser():
                 'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
                 'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
                 'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
+                'prefer-legacy-http-handler'
             }, 'aliases': {
                 'youtube-dl': ['all', '-multistreams', '-playlist-match-filter'],
                 'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter'],
                 '2021': ['2022', 'no-certifi', 'filename-sanitization', 'no-youtube-prefer-utc-upload-date'],
-                '2022': ['no-external-downloader-progress', 'playlist-match-filter'],
+                '2022': ['no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler'],
             }
         }, help=(
             'Options that can help keep compatibility with youtube-dl or youtube-dlc '
@@ -732,7 +733,7 @@ def create_parser():
     authentication.add_option(
         '--video-password',
         dest='videopassword', metavar='PASSWORD',
-        help='Video password (vimeo, youku)')
+        help='Video-specific password')
     authentication.add_option(
         '--ap-mso',
         dest='ap_mso', metavar='MSO',

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2023.10.07'
+__version__ = '2023.10.13'
 
-RELEASE_GIT_HEAD = '377e85a1797db9e98b78b38203ed9d4ded229991'
+RELEASE_GIT_HEAD = 'b634ba742d8f38ce9ecfa0546485728b0c6c59d1'
 
 VARIANT = None