Release 2023.03.04

Created by: pukkandan

:ci skip all :ci run dl

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting that a **supported** site is broken
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <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 **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <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 **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <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 **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <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 **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <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 **2023.03.03** ([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 **2023.03.04** ([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 2023.03.03 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.03.04 [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: 2023.03.03, Current version: 2023.03.03
+        Latest version: 2023.03.04, Current version: 2023.03.04
-        yt-dlp is up to date (2023.03.03)
+        yt-dlp is up to date (2023.03.04)
         <more lines>
       render: shell

.github/workflows/publish.yml

@@ -55,12 +55,12 @@ jobs:
         run: |
           gh release create \
             --notes-file ARCHIVE_NOTES \
-            --title "Build ${{ inputs.version }}" \
+            --title "yt-dlp nightly ${{ inputs.version }}" \
             ${{ inputs.version }} \
             artifact/*
 
       - name: Prune old nightly release
-        if: inputs.nightly
+        if: inputs.nightly && !vars.ARCHIVE_REPO
         env:
           GH_TOKEN: ${{ github.token }}
         run: |
@@ -71,6 +71,7 @@ jobs:
       - name: Publish release${{ inputs.nightly && ' (nightly)' || '' }}
         env:
           GH_TOKEN: ${{ github.token }}
+        if: (inputs.nightly && !vars.ARCHIVE_REPO) || !inputs.nightly
         run: |
           gh release create \
             --notes-file ${{ inputs.nightly && 'PRE' || '' }}RELEASE_NOTES \

.github/workflows/release-nightly.yml

@@ -4,7 +4,7 @@ on:
     branches:
       - master
     paths:
-      - "**.py"
+      - "yt_dlp/**.py"
       - "!yt_dlp/version.py"
 concurrency:
   group: release-nightly

.github/workflows/release.yml

@@ -64,6 +64,7 @@ jobs:
 
       - name: Install Requirements
         run: |
+          sudo apt-get -y install pandoc man
           python -m pip install -U pip setuptools wheel twine
           python -m pip install -U -r requirements.txt
 
@@ -79,6 +80,7 @@ jobs:
         if: env.TWINE_PASSWORD != ''
         run: |
           rm -rf dist/*
+          make pypi-files
           python devscripts/set-variant.py pip -M "You installed yt-dlp with pip or using the wheel from PyPi; Use that to update"
           python setup.py sdist bdist_wheel
           twine upload dist/*

CONTRIBUTORS

@@ -406,3 +406,6 @@ rohieb
 sdht0
 seproDev
 Hill-98
+LXYan2333
+mushbite
+venkata-krishnas

Changelog.md

@@ -4,6 +4,45 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2023.03.04
+
+#### Extractor changes
+- bilibili
+    - [Fix for downloading wrong subtitles](https://github.com/yt-dlp/yt-dlp/commit/8a83baaf218ab89e6e7faa76b7c7be3a2ec19e3a) ([#6358](https://github.com/yt-dlp/yt-dlp/issues/6358)) by [LXYan2333](https://github.com/LXYan2333)
+- ESPNcricinfo
+    - [Handle new URL pattern](https://github.com/yt-dlp/yt-dlp/commit/640c934823fc2d1ec77ec932566078014058635f) ([#6321](https://github.com/yt-dlp/yt-dlp/issues/6321)) by [venkata-krishnas](https://github.com/venkata-krishnas)
+- lefigaro
+    - [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/eb8fd6d044e8926532772b72be0645c6b8ecb3aa) ([#6309](https://github.com/yt-dlp/yt-dlp/issues/6309)) by [elyse0](https://github.com/elyse0)
+- lumni
+    - [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1f8489cccbdc6e96027ef527b88717458f0900e8) ([#6302](https://github.com/yt-dlp/yt-dlp/issues/6302)) by [carusocr](https://github.com/carusocr)
+- Prankcast
+    - [Fix tags](https://github.com/yt-dlp/yt-dlp/commit/ed4cc4ea793314c50ae3f82e98248c1de1c25694) ([#6316](https://github.com/yt-dlp/yt-dlp/issues/6316)) by [columndeeply](https://github.com/columndeeply)
+- rutube
+    - [Extract chapters from description](https://github.com/yt-dlp/yt-dlp/commit/22ccd5420b3eb0782776071f12cccd1fedaa1fd0) ([#6345](https://github.com/yt-dlp/yt-dlp/issues/6345)) by [mushbite](https://github.com/mushbite)
+- SportDeutschland
+    - [Rewrite extractor](https://github.com/yt-dlp/yt-dlp/commit/45db357289b4e1eec09093c8bc5446520378f426) by [pukkandan](https://github.com/pukkandan)
+- telecaribe
+    - [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b40471282286bd2b09c485bf79afd271d229272c) ([#6311](https://github.com/yt-dlp/yt-dlp/issues/6311)) by [elyse0](https://github.com/elyse0)
+- tubetugraz
+    - [Support `--twofactor` (#6424)](https://github.com/yt-dlp/yt-dlp/commit/f44cb4e77bb9be8be291d02ab6f79dc0b4c0d4a1) ([#6427](https://github.com/yt-dlp/yt-dlp/issues/6427)) by [Ferdi265](https://github.com/Ferdi265)
+- tunein
+    - [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/46580ced56c90b559885aded6aa8f46f20a9cdce) ([#6310](https://github.com/yt-dlp/yt-dlp/issues/6310)) by [elyse0](https://github.com/elyse0)
+- twitch
+    - [Update for GraphQL API changes](https://github.com/yt-dlp/yt-dlp/commit/4a6272c6d1bff89969b67cd22b26ebe6d7e72279) ([#6318](https://github.com/yt-dlp/yt-dlp/issues/6318)) by [elyse0](https://github.com/elyse0)
+- twitter
+    - [Fix retweet extraction](https://github.com/yt-dlp/yt-dlp/commit/cf605226521e99c89fc8dff26a319025810e63a0) ([#6422](https://github.com/yt-dlp/yt-dlp/issues/6422)) by [selfisekai](https://github.com/selfisekai)
+- xvideos
+    - quickies: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/283a0b5bc511f3b350eead4488158f50c20ec526) ([#6414](https://github.com/yt-dlp/yt-dlp/issues/6414)) by [Yakabuff](https://github.com/Yakabuff)
+
+#### Misc. changes
+- build
+    - [Fix publishing to PyPI and homebrew](https://github.com/yt-dlp/yt-dlp/commit/55676fe498345a389a2539d8baaba958d6d61c3e) by [bashonly](https://github.com/bashonly)
+    - [Only archive if `vars.ARCHIVE_REPO` is set](https://github.com/yt-dlp/yt-dlp/commit/08ff6d59f97b5f5f0128f6bf6fbef56fd836cc52) by [Grub4K](https://github.com/Grub4K)
+- cleanup
+    - Miscellaneous: [392389b](https://github.com/yt-dlp/yt-dlp/commit/392389b7df7b818f794b231f14dc396d4875fbad) by [pukkandan](https://github.com/pukkandan)
+- devscripts
+    - `make_changelog`: [Stop at `Release ...` commit](https://github.com/yt-dlp/yt-dlp/commit/7accdd9845fe7ce9d0aa5a9d16faaa489c1294eb) by [pukkandan](https://github.com/pukkandan)
+
 ### 2023.03.03
 
 #### Important changes

README.md

@@ -192,9 +192,8 @@ For other third-party package managers, see [the wiki](https://github.com/yt-dlp
 <a id="update-channels"/>
 
 There are currently two release channels for binaries, `stable` and `nightly`.
-`stable` releases are what the program will update to by default, and have had many of their changes tested by users of the master branch.
+`stable` is the default channel, and many of its changes have been tested by users of the nightly channel.
-`nightly` releases are built after each push to the master branch, and will have the most recent fixes and additions, but also have the potential for bugs.
+The `nightly` channel has releases built after each push to the master branch, and will have the most recent fixes and additions, but also have more risk of regressions. They are available in [their own repo](https://github.com/yt-dlp/yt-dlp-nightly-builds/releases).
-The latest `nightly` is available as a [pre-release from this repository](https://github.com/yt-dlp/yt-dlp/releases/tag/nightly), and all `nightly` releases are [archived in their own repo](https://github.com/yt-dlp/yt-dlp-nightly-builds/releases).
 
 When using `--update`/`-U`, a release binary will only update to its current channel.
 This release channel can be changed by using the `--update-to` option. `--update-to` can also be used to upgrade or downgrade to specific tags from a channel.

devscripts/changelog_override.json

@@ -1,12 +1,12 @@
 [
     {
         "action": "add",
-        "when": "2023.02.17",
+        "when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
         "short": "[priority] **A new release type has been added!**\n    * [`nightly`](https://github.com/yt-dlp/yt-dlp/releases/tag/nightly) builds will be made after each push, containing the latest fixes (but also possibly bugs).\n    * When using `--update`/`-U`, a release binary will only update to its current channel (either `stable` or `nightly`).\n    * The `--update-to` option has been added allowing the user more control over program upgrades (or downgrades).\n    * `--update-to` can change the release channel (`stable`, `nightly`) and also upgrade or downgrade to specific tags.\n    * **Usage**: `--update-to CHANNEL`, `--update-to TAG`, `--update-to CHANNEL@TAG`"
     },
     {
         "action": "add",
-        "when": "2023.02.17",
+        "when": "776d1c3f0c9b00399896dd2e40e78e9a43218109",
         "short": "[priority] **YouTube throttling fixes!**"
     }
 ]

devscripts/make_changelog.py

@@ -1,19 +1,26 @@
 from __future__ import annotations
 
+# Allow direct execution
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 import enum
 import itertools
 import json
 import logging
 import re
-import subprocess
-import sys
 from collections import defaultdict
 from dataclasses import dataclass
 from functools import lru_cache
 from pathlib import Path
 
+from devscripts.utils import read_file, run_process, write_file
+
 BASE_URL = 'https://github.com'
 LOCATION_PATH = Path(__file__).parent
+HASH_LENGTH = 7
 
 logger = logging.getLogger(__name__)
 
@@ -82,7 +89,7 @@ class Commit:
         result = f'{self.short!r}'
 
         if self.hash:
-            result += f' ({self.hash[:7]})'
+            result += f' ({self.hash[:HASH_LENGTH]})'
 
         if self.authors:
             authors = ', '.join(self.authors)
@@ -208,7 +215,7 @@ class Changelog:
 
     def _format_message_link(self, message, hash):
         assert message or hash, 'Improperly defined commit message or override'
-        message = message if message else hash[:7]
+        message = message if message else hash[:HASH_LENGTH]
         return f'[{message}]({self.repo_url}/commit/{hash})' if hash else message
 
     def _format_issues(self, issues):
@@ -242,36 +249,11 @@ class CommitRange:
     FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert)\s+([\da-f]{40})')
     UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
 
-    def __init__(self, start, end, default_author=None) -> None:
+    def __init__(self, start, end, default_author=None):
-        self._start = start
+        self._start, self._end = start, end
-        self._end = end
         self._commits, self._fixes = self._get_commits_and_fixes(default_author)
         self._commits_added = []
 
-    @classmethod
-    def from_single(cls, commitish='HEAD', default_author=None):
-        start_commitish = cls.get_prev_tag(commitish)
-        end_commitish = cls.get_next_tag(commitish)
-        if start_commitish == end_commitish:
-            start_commitish = cls.get_prev_tag(f'{commitish}~')
-        logger.info(f'Determined range from {commitish!r}: {start_commitish}..{end_commitish}')
-        return cls(start_commitish, end_commitish, default_author)
-
-    @classmethod
-    def get_prev_tag(cls, commitish):
-        command = [cls.COMMAND, 'describe', '--tags', '--abbrev=0', '--exclude=*[^0-9.]*', commitish]
-        return subprocess.check_output(command, text=True).strip()
-
-    @classmethod
-    def get_next_tag(cls, commitish):
-        result = subprocess.run(
-            [cls.COMMAND, 'describe', '--contains', '--abbrev=0', commitish],
-            stdout=subprocess.PIPE, stderr=subprocess.DEVNULL, text=True)
-        if result.returncode:
-            return 'HEAD'
-
-        return result.stdout.partition('~')[0].strip()
-
     def __iter__(self):
         return iter(itertools.chain(self._commits.values(), self._commits_added))
 
@@ -286,20 +268,15 @@ class CommitRange:
 
         return commit in self._commits
 
-    def _is_ancestor(self, commitish):
-        return bool(subprocess.call(
-            [self.COMMAND, 'merge-base', '--is-ancestor', commitish, self._start]))
-
     def _get_commits_and_fixes(self, default_author):
-        result = subprocess.check_output([
+        result = run_process(
             self.COMMAND, 'log', f'--format=%H%n%s%n%b%n{self.COMMIT_SEPARATOR}',
-            f'{self._start}..{self._end}'], text=True)
+            f'{self._start}..{self._end}' if self._start else self._end).stdout
 
         commits = {}
         fixes = defaultdict(list)
         lines = iter(result.splitlines(False))
-        for line in lines:
+        for i, commit_hash in enumerate(lines):
-            commit_hash = line
             short = next(lines)
             skip = short.startswith('Release ') or short == '[version] update'
 
@@ -310,9 +287,12 @@ class CommitRange:
                     authors = sorted(map(str.strip, line[match.end():].split(',')), key=str.casefold)
 
             commit = Commit(commit_hash, short, authors)
-            if skip:
+            if skip and (self._start or not i):
                 logger.debug(f'Skipped commit: {commit}')
                 continue
+            elif skip:
+                logger.debug(f'Reached Release commit, breaking: {commit}')
+                break
 
             fix_match = self.FIXES_RE.search(commit.short)
             if fix_match:
@@ -323,12 +303,12 @@ class CommitRange:
 
         for commitish, fix_commits in fixes.items():
             if commitish in commits:
-                hashes = ', '.join(commit.hash[:7] for commit in fix_commits)
+                hashes = ', '.join(commit.hash[:HASH_LENGTH] for commit in fix_commits)
-                logger.info(f'Found fix(es) for {commitish[:7]}: {hashes}')
+                logger.info(f'Found fix(es) for {commitish[:HASH_LENGTH]}: {hashes}')
                 for fix_commit in fix_commits:
                     del commits[fix_commit.hash]
             else:
-                logger.debug(f'Commit with fixes not in changes: {commitish[:7]}')
+                logger.debug(f'Commit with fixes not in changes: {commitish[:HASH_LENGTH]}')
 
         return commits, fixes
 
@@ -419,11 +399,10 @@ class CommitRange:
 def get_new_contributors(contributors_path, commits):
     contributors = set()
     if contributors_path.exists():
-        with contributors_path.open() as file:
+        for line in read_file(contributors_path).splitlines():
-            for line in filter(None, map(str.strip, file)):
+            author, _, _ = line.strip().partition(' (')
-                author, _, _ = line.partition(' (')
+            authors = author.split('/')
-                authors = author.split('/')
+            contributors.update(map(str.casefold, authors))
-                contributors.update(map(str.casefold, authors))
 
     new_contributors = set()
     for commit in commits:
@@ -471,12 +450,11 @@ if __name__ == '__main__':
         datefmt='%Y-%m-%d %H-%M-%S', format='{asctime} | {levelname:<8} | {message}',
         level=logging.WARNING - 10 * args.verbosity, style='{', stream=sys.stderr)
 
-    commits = CommitRange.from_single(args.commitish, args.default_author)
+    commits = CommitRange(None, args.commitish, args.default_author)
 
     if not args.no_override:
         if args.override_path.exists():
-            with args.override_path.open() as file:
+            overrides = json.loads(read_file(args.override_path))
-                overrides = json.load(file)
             commits.apply_overrides(overrides)
         else:
             logger.warning(f'File {args.override_path.as_posix()} does not exist')
@@ -486,8 +464,7 @@ if __name__ == '__main__':
     new_contributors = get_new_contributors(args.contributors_path, commits)
     if new_contributors:
         if args.contributors:
-            with args.contributors_path.open('a') as file:
+            write_file(args.contributors_path, '\n'.join(new_contributors) + '\n', mode='a')
-                file.writelines(f'{contributor}\n' for contributor in new_contributors)
         logger.info(f'New contributors: {", ".join(new_contributors)}')
 
     print(Changelog(commits.groups(), args.repo))

devscripts/update-version.py

@@ -9,11 +9,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 import argparse
 import contextlib
-import subprocess
 import sys
 from datetime import datetime
 
-from devscripts.utils import read_version, write_file
+from devscripts.utils import read_version, run_process, write_file
 
 
 def get_new_version(version, revision):
@@ -32,7 +31,7 @@ def get_new_version(version, revision):
 
 def get_git_head():
     with contextlib.suppress(Exception):
-        return subprocess.check_output(['git', 'rev-parse', 'HEAD'], text=True).strip() or None
+        return run_process('git', 'rev-parse', 'HEAD').stdout.strip()
 
 
 VERSION_TEMPLATE = '''\

devscripts/utils.py

@@ -1,5 +1,6 @@
 import argparse
 import functools
+import subprocess
 
 
 def read_file(fname):
@@ -12,8 +13,8 @@ def write_file(fname, content, mode='w'):
         return f.write(content)
 
 
-# Get the version without importing the package
 def read_version(fname='yt_dlp/version.py'):
+    """Get the version without importing the package"""
     exec(compile(read_file(fname), fname, 'exec'))
     return locals()['__version__']
 
@@ -33,3 +34,13 @@ def get_filename_args(has_infile=False, default_outfile=None):
 
 def compose_functions(*functions):
     return lambda x: functools.reduce(lambda y, f: f(y), functions, x)
+
+
+def run_process(*args, **kwargs):
+    kwargs.setdefault('text', True)
+    kwargs.setdefault('check', True)
+    kwargs.setdefault('capture_output', True)
+    if kwargs['text']:
+        kwargs.setdefault('encoding', 'utf-8')
+        kwargs.setdefault('errors', 'replace')
+    return subprocess.run(args, **kwargs)

supportedsites.md

@@ -663,6 +663,8 @@
  - **Lecturio**: [*lecturio*](## "netrc machine")
  - **LecturioCourse**: [*lecturio*](## "netrc machine")
  - **LecturioDeCourse**: [*lecturio*](## "netrc machine")
+ - **LeFigaroVideoEmbed**
+ - **LeFigaroVideoSection**
  - **LEGO**
  - **Lemonde**
  - **Lenta**
@@ -696,6 +698,7 @@
  - **LoveHomePorn**
  - **LRTStream**
  - **LRTVOD**
+ - **Lumni**
  - **lynda**: [*lynda*](## "netrc machine") lynda.com videos
  - **lynda:course**: [*lynda*](## "netrc machine") lynda.com online courses
  - **m6**
@@ -1365,6 +1368,7 @@
  - **Tele13**
  - **Tele5**
  - **TeleBruxelles**
+ - **TelecaribePlay**
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **telegram:embed**
@@ -1440,10 +1444,9 @@
  - **TubiTv**: [*tubitv*](## "netrc machine")
  - **TubiTvShow**
  - **Tumblr**: [*tumblr*](## "netrc machine")
- - **tunein:clip**
+ - **TuneInPodcast**
- - **tunein:program**
+ - **TuneInPodcastEpisode**
- - **tunein:station**
+ - **TuneInStation**
- - **tunein:topic**
  - **TunePk**
  - **Turbo**
  - **tv.dfb.de**
@@ -1695,6 +1698,7 @@
  - **XTubeUser**: XTube user profile
  - **Xuite**: 隨意窩Xuite影音
  - **XVideos**
+ - **xvideos:quickies**
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **yahoo:gyao**

yt_dlp/YoutubeDL.py

@@ -3784,7 +3784,7 @@ class YoutubeDL:
         klass = type(self)
         write_debug(join_nonempty(
             f'{"yt-dlp" if REPOSITORY == "yt-dlp/yt-dlp" else REPOSITORY} version',
-            __version__ + {'stable': '', 'nightly': '*'}.get(CHANNEL, f' <{CHANNEL}>'),
+            f'{CHANNEL}@{__version__}',
             f'[{RELEASE_GIT_HEAD[:9]}]' if RELEASE_GIT_HEAD else '',
             '' if source == 'unknown' else f'({source})',
             '' if _IN_CLI else 'API' if klass == YoutubeDL else f'API:{self.__module__}.{klass.__qualname__}',

yt_dlp/extractor/_extractors.py

@@ -914,6 +914,10 @@ from .leeco import (
     LePlaylistIE,
     LetvCloudIE,
 )
+from .lefigaro import (
+    LeFigaroVideoEmbedIE,
+    LeFigaroVideoSectionIE,
+)
 from .lego import LEGOIE
 from .lemonde import LemondeIE
 from .lenta import LentaIE
@@ -962,6 +966,9 @@ from .lrt import (
     LRTVODIE,
     LRTStreamIE
 )
+from .lumni import (
+    LumniIE
+)
 from .lynda import (
     LyndaIE,
     LyndaCourseIE
@@ -1851,6 +1858,7 @@ from .ted import (
 from .tele5 import Tele5IE
 from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
+from .telecaribe import TelecaribePlayIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telegram import TelegramEmbedIE
@@ -1963,10 +1971,9 @@ from .tubitv import (
 )
 from .tumblr import TumblrIE
 from .tunein import (
-    TuneInClipIE,
     TuneInStationIE,
-    TuneInProgramIE,
+    TuneInPodcastIE,
-    TuneInTopicIE,
+    TuneInPodcastEpisodeIE,
     TuneInShortenerIE,
 )
 from .tunepk import TunePkIE
@@ -2315,7 +2322,10 @@ from .xnxx import XNXXIE
 from .xstream import XstreamIE
 from .xtube import XTubeUserIE, XTubeIE
 from .xuite import XuiteIE
-from .xvideos import XVideosIE
+from .xvideos import (
+    XVideosIE,
+    XVideosQuickiesIE
+)
 from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,

yt_dlp/extractor/bilibili.py

@@ -81,7 +81,7 @@ class BilibiliBaseIE(InfoExtractor):
                          f'{line["content"]}\n\n')
         return srt_data
 
-    def _get_subtitles(self, video_id, initial_state, cid):
+    def _get_subtitles(self, video_id, aid, cid):
         subtitles = {
             'danmaku': [{
                 'ext': 'xml',
@@ -89,7 +89,8 @@ class BilibiliBaseIE(InfoExtractor):
             }]
         }
 
-        for s in traverse_obj(initial_state, ('videoData', 'subtitle', 'list')) or []:
+        video_info_json = self._download_json(f'https://api.bilibili.com/x/player/v2?aid={aid}&cid={cid}', video_id)
+        for s in traverse_obj(video_info_json, ('data', 'subtitle', 'subtitles', ...)):
             subtitles.setdefault(s['lan'], []).append({
                 'ext': 'srt',
                 'data': self.json2srt(self._download_json(s['subtitle_url'], video_id))
@@ -331,7 +332,7 @@ class BiliBiliIE(BilibiliBaseIE):
             'timestamp': traverse_obj(initial_state, ('videoData', 'pubdate')),
             'duration': float_or_none(play_info.get('timelength'), scale=1000),
             'chapters': self._get_chapters(aid, cid),
-            'subtitles': self.extract_subtitles(video_id, initial_state, cid),
+            'subtitles': self.extract_subtitles(video_id, aid, cid),
             '__post_extractor': self.extract_comments(aid),
             'http_headers': {'Referer': url},
         }

yt_dlp/extractor/common.py

@@ -3649,6 +3649,38 @@ class InfoExtractor:
                 or urllib.parse.unquote(os.path.splitext(url_basename(url))[0])
                 or default)
 
+    def _extract_chapters_helper(self, chapter_list, start_function, title_function, duration, strict=True):
+        if not duration:
+            return
+        chapter_list = [{
+            'start_time': start_function(chapter),
+            'title': title_function(chapter),
+        } for chapter in chapter_list or []]
+        if not strict:
+            chapter_list.sort(key=lambda c: c['start_time'] or 0)
+
+        chapters = [{'start_time': 0}]
+        for idx, chapter in enumerate(chapter_list):
+            if chapter['start_time'] is None:
+                self.report_warning(f'Incomplete chapter {idx}')
+            elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
+                chapters.append(chapter)
+            elif chapter not in chapters:
+                self.report_warning(
+                    f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
+        return chapters[1:]
+
+    def _extract_chapters_from_description(self, description, duration):
+        duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
+        sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
+        return self._extract_chapters_helper(
+            re.findall(sep_re % (duration_re, r'.+?'), description or ''),
+            start_function=lambda x: parse_duration(x[0]), title_function=lambda x: x[1],
+            duration=duration, strict=False) or self._extract_chapters_helper(
+            re.findall(sep_re % (r'.+?', duration_re), description or ''),
+            start_function=lambda x: parse_duration(x[1]), title_function=lambda x: x[0],
+            duration=duration, strict=False)
+
     @staticmethod
     def _availability(is_private=None, needs_premium=None, needs_subscription=None, needs_auth=None, is_unlisted=None):
         all_known = all(map(

yt_dlp/extractor/espn.py

@@ -240,7 +240,7 @@ class FiveThirtyEightIE(InfoExtractor):
 
 
 class ESPNCricInfoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?espncricinfo\.com/video/[^#$&?/]+-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?espncricinfo\.com/(?:cricket-)?videos?/[^#$&?/]+-(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.espncricinfo.com/video/finch-chasing-comes-with-risks-despite-world-cup-trend-1289135',
         'info_dict': {
@@ -252,6 +252,17 @@ class ESPNCricInfoIE(InfoExtractor):
             'duration': 96,
         },
         'params': {'skip_download': True}
+    }, {
+        'url': 'https://www.espncricinfo.com/cricket-videos/daryl-mitchell-mitchell-santner-is-one-of-the-best-white-ball-spinners-india-vs-new-zealand-1356225',
+        'info_dict': {
+            'id': '1356225',
+            'ext': 'mp4',
+            'description': '"Santner has done it for a long time for New Zealand - we\'re lucky to have him"',
+            'upload_date': '20230128',
+            'title': 'Mitchell: \'Santner is one of the best white-ball spinners at the moment\'',
+            'duration': 87,
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/lefigaro.py

@@ -0,0 +1,135 @@
+import json
+import math
+
+from .common import InfoExtractor
+from ..utils import (
+    InAdvancePagedList,
+    traverse_obj,
+)
+
+
+class LeFigaroVideoEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.lefigaro\.fr/embed/[^?#]+/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://video.lefigaro.fr/embed/figaro/video/les-francais-ne-veulent-ils-plus-travailler-suivez-en-direct-le-club-le-figaro-idees/',
+        'md5': 'e94de44cd80818084352fcf8de1ce82c',
+        'info_dict': {
+            'id': 'g9j7Eovo',
+            'title': 'Les Français ne veulent-ils plus travailler ? Retrouvez Le Club Le Figaro Idées',
+            'description': 'md5:862b8813148ba4bf10763a65a69dfe41',
+            'upload_date': '20230216',
+            'timestamp': 1676581615,
+            'duration': 3076,
+            'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://video.lefigaro.fr/embed/figaro/video/intelligence-artificielle-faut-il-sen-mefier/',
+        'md5': '0b3f10332b812034b3a3eda1ef877c5f',
+        'info_dict': {
+            'id': 'LeAgybyc',
+            'title': 'Intelligence artificielle : faut-il s’en méfier ?',
+            'description': 'md5:249d136e3e5934a67c8cb704f8abf4d2',
+            'upload_date': '20230124',
+            'timestamp': 1674584477,
+            'duration': 860,
+            'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
+            'ext': 'mp4',
+        },
+    }]
+
+    _WEBPAGE_TESTS = [{
+        'url': 'https://video.lefigaro.fr/figaro/video/suivez-en-direct-le-club-le-figaro-international-avec-philippe-gelie-9/',
+        'md5': '3972ddf2d5f8b98699f191687258e2f9',
+        'info_dict': {
+            'id': 'QChnbPYA',
+            'title': 'Où en est le couple franco-allemand ? Retrouvez Le Club Le Figaro International',
+            'description': 'md5:6f47235b7e7c93b366fd8ebfa10572ac',
+            'upload_date': '20230123',
+            'timestamp': 1674503575,
+            'duration': 3153,
+            'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
+            'age_limit': 0,
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://video.lefigaro.fr/figaro/video/la-philosophe-nathalie-sarthou-lajus-est-linvitee-du-figaro-live/',
+        'md5': '3ac0a0769546ee6be41ab52caea5d9a9',
+        'info_dict': {
+            'id': 'QJzqoNbf',
+            'title': 'La philosophe Nathalie Sarthou-Lajus est l’invitée du Figaro Live',
+            'description': 'md5:c586793bb72e726c83aa257f99a8c8c4',
+            'upload_date': '20230217',
+            'timestamp': 1676661986,
+            'duration': 1558,
+            'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
+            'age_limit': 0,
+            'ext': 'mp4',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        player_data = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['pageData']['playerData']
+
+        return self.url_result(
+            f'jwplatform:{player_data["videoId"]}', title=player_data.get('title'),
+            description=player_data.get('description'), thumbnail=player_data.get('poster'))
+
+
+class LeFigaroVideoSectionIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.lefigaro\.fr/figaro/(?P<id>[\w-]+)/?(?:[#?]|$)'
+
+    _TESTS = [{
+        'url': 'https://video.lefigaro.fr/figaro/le-club-le-figaro-idees/',
+        'info_dict': {
+            'id': 'le-club-le-figaro-idees',
+            'title': 'Le Club Le Figaro Idées',
+        },
+        'playlist_mincount': 14,
+    }, {
+        'url': 'https://video.lefigaro.fr/figaro/factu/',
+        'info_dict': {
+            'id': 'factu',
+            'title': 'Factu',
+        },
+        'playlist_mincount': 519,
+    }]
+
+    _PAGE_SIZE = 20
+
+    def _get_api_response(self, display_id, page_num, note=None):
+        return self._download_json(
+            'https://api-graphql.lefigaro.fr/graphql', display_id, note=note,
+            query={
+                'id': 'flive-website_UpdateListPage_1fb260f996bca2d78960805ac382544186b3225f5bedb43ad08b9b8abef79af6',
+                'variables': json.dumps({
+                    'slug': display_id,
+                    'videosLimit': self._PAGE_SIZE,
+                    'sort': 'DESC',
+                    'order': 'PUBLISHED_AT',
+                    'page': page_num,
+                }).encode(),
+            })
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        initial_response = self._get_api_response(display_id, page_num=1)['data']['playlist']
+
+        def page_func(page_num):
+            api_response = self._get_api_response(display_id, page_num + 1, note=f'Downloading page {page_num + 1}')
+
+            return [self.url_result(
+                video['embedUrl'], LeFigaroVideoEmbedIE, **traverse_obj(video, {
+                    'title': 'name',
+                    'description': 'description',
+                    'thumbnail': 'thumbnailUrl',
+                })) for video in api_response['data']['playlist']['jsonLd'][0]['itemListElement']]
+
+        entries = InAdvancePagedList(
+            page_func, math.ceil(initial_response['videoCount'] / self._PAGE_SIZE), self._PAGE_SIZE)
+
+        return self.playlist_result(entries, playlist_id=display_id, playlist_title=initial_response.get('title'))

yt_dlp/extractor/lumni.py

@@ -0,0 +1,24 @@
+from .common import InfoExtractor
+from .francetv import FranceTVIE
+
+
+class LumniIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lumni\.fr/video/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.lumni.fr/video/l-homme-et-son-environnement-dans-la-revolution-industrielle',
+        'md5': '960e8240c4f2c7a20854503a71e52f5e',
+        'info_dict': {
+            'id': 'd2b9a4e5-a526-495b-866c-ab72737e3645',
+            'ext': 'mp4',
+            'title': "L'homme et son environnement dans la révolution industrielle - L'ère de l'homme",
+            'thumbnail': 'https://assets.webservices.francetelevisions.fr/v1/assets/images/a7/17/9f/a7179f5f-63a5-4e11-8d4d-012ab942d905.jpg',
+            'duration': 230,
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._html_search_regex(
+            r'<div[^>]+data-factoryid\s*=\s*["\']([^"\']+)', webpage, 'video id')
+        return self.url_result(f'francetv:{video_id}', FranceTVIE, video_id)

yt_dlp/extractor/prankcast.py

@@ -18,7 +18,7 @@ class PrankCastIE(InfoExtractor):
             'cast': ['Devonanustart', 'Phonelosers'],
             'description': '',
             'categories': ['prank'],
-            'tags': ['prank call', 'prank'],
+            'tags': ['prank call', 'prank', 'live show'],
             'upload_date': '20220825'
         }
     }, {
@@ -35,7 +35,7 @@ class PrankCastIE(InfoExtractor):
             'cast': ['phonelosers'],
             'description': '',
             'categories': ['prank'],
-            'tags': ['prank call', 'prank'],
+            'tags': ['prank call', 'prank', 'live show'],
             'upload_date': '20221006'
         }
     }]
@@ -62,5 +62,5 @@ class PrankCastIE(InfoExtractor):
             'cast': list(filter(None, [uploader] + traverse_obj(guests_json, (..., 'name')))),
             'description': json_info.get('broadcast_description'),
             'categories': [json_info.get('broadcast_category')],
-            'tags': self._parse_json(json_info.get('broadcast_tags') or '{}', video_id)
+            'tags': try_call(lambda: json_info['broadcast_tags'].split(','))
         }

yt_dlp/extractor/rutube.py

@@ -25,8 +25,7 @@ class RutubeBaseIE(InfoExtractor):
             video_id, 'Downloading video JSON',
             'Unable to download video JSON', query=query)
 
-    @staticmethod
+    def _extract_info(self, video, video_id=None, require_title=True):
-    def _extract_info(video, video_id=None, require_title=True):
         title = video['title'] if require_title else video.get('title')
 
         age_limit = video.get('is_adult')
@@ -35,13 +34,15 @@ class RutubeBaseIE(InfoExtractor):
 
         uploader_id = try_get(video, lambda x: x['author']['id'])
         category = try_get(video, lambda x: x['category']['name'])
+        description = video.get('description')
+        duration = int_or_none(video.get('duration'))
 
         return {
             'id': video.get('id') or video_id if video_id else video['id'],
             'title': title,
-            'description': video.get('description'),
+            'description': description,
             'thumbnail': video.get('thumbnail_url'),
-            'duration': int_or_none(video.get('duration')),
+            'duration': duration,
             'uploader': try_get(video, lambda x: x['author']['name']),
             'uploader_id': compat_str(uploader_id) if uploader_id else None,
             'timestamp': unified_timestamp(video.get('created_ts')),
@@ -50,6 +51,7 @@ class RutubeBaseIE(InfoExtractor):
             'view_count': int_or_none(video.get('hits')),
             'comment_count': int_or_none(video.get('comments_count')),
             'is_live': bool_or_none(video.get('is_livestream')),
+            'chapters': self._extract_chapters_from_description(description, duration),
         }
 
     def _download_and_extract_info(self, video_id, query=None):
@@ -111,8 +113,9 @@ class RutubeIE(RutubeBaseIE):
             'view_count': int,
             'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
             'category': ['Новости и СМИ'],
-
+            'chapters': [],
         },
+        'expected_warnings': ['Unable to download f4m'],
     }, {
         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
         'only_matching': True,
@@ -142,7 +145,28 @@ class RutubeIE(RutubeBaseIE):
             'view_count': int,
             'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
             'category': ['Видеоигры'],
+            'chapters': [],
         },
+        'expected_warnings': ['Unable to download f4m'],
+    }, {
+        'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
+        'info_dict': {
+            'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
+            'ext': 'mp4',
+            'chapters': 'count:4',
+            'category': ['Бизнес и предпринимательство'],
+            'description': 'md5:252feac1305257d8c1bab215cedde75d',
+            'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
+            'duration': 782,
+            'age_limit': 0,
+            'uploader_id': '23491359',
+            'timestamp': 1677153329,
+            'view_count': int,
+            'upload_date': '20230223',
+            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
+            'uploader': 'Стас Быков',
+        },
+        'expected_warnings': ['Unable to download f4m'],
     }]
 
     @classmethod

yt_dlp/extractor/sportdeutschland.py

@@ -1,10 +1,9 @@
 from .common import InfoExtractor
-
 from ..utils import (
-    format_field,
+    join_nonempty,
+    strip_or_none,
     traverse_obj,
     unified_timestamp,
-    strip_or_none
 )
 
 
@@ -13,98 +12,131 @@ class SportDeutschlandIE(InfoExtractor):
     _TESTS = [{
         'url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
         'info_dict': {
-            'id': '983758e9-5829-454d-a3cf-eb27bccc3c94',
+            'id': '9839a5c7-0dbb-48a8-ab63-3b408adc7b54',
             'ext': 'mp4',
             'title': 'Buchholzer Formationswochenende 2023 - Samstag - 1. Bundesliga / Landesliga',
+            'display_id': 'blauweissbuchholztanzsport/buchholzer-formationswochenende-2023-samstag-1-bundesliga-landesliga',
             'description': 'md5:a288c794a5ee69e200d8f12982f81a87',
             'live_status': 'was_live',
             'channel': 'Blau-Weiss Buchholz Tanzsport',
             'channel_url': 'https://sportdeutschland.tv/blauweissbuchholztanzsport',
             'channel_id': '93ec33c9-48be-43b6-b404-e016b64fdfa3',
-            'display_id': '9839a5c7-0dbb-48a8-ab63-3b408adc7b54',
             'duration': 32447,
             'upload_date': '20230114',
-            'timestamp': 1673730018.0,
+            'timestamp': 1673733618,
         }
     }, {
         'url': 'https://sportdeutschland.tv/deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
         'info_dict': {
-            'id': '95b97d9a-04f6-4880-9039-182985c33943',
+            'id': '95c80c52-6b9a-4ae9-9197-984145adfced',
             'ext': 'mp4',
             'title': 'BWF Tour: 1. Runde Feld 1 - YONEX GAINWARD German Open 2022',
+            'display_id': 'deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
             'description': 'md5:2afb5996ceb9ac0b2ac81f563d3a883e',
             'live_status': 'was_live',
             'channel': 'Deutscher Badminton Verband',
             'channel_url': 'https://sportdeutschland.tv/deutscherbadmintonverband',
             'channel_id': '93ca5866-2551-49fc-8424-6db35af58920',
-            'display_id': '95c80c52-6b9a-4ae9-9197-984145adfced',
             'duration': 41097,
             'upload_date': '20220309',
             'timestamp': 1646860727.0,
         }
+    }, {
+        'url': 'https://sportdeutschland.tv/ggcbremen/formationswochenende-latein-2023',
+        'info_dict': {
+            'id': '9889785e-55b0-4d97-a72a-ce9a9f157cce',
+            'title': 'Formationswochenende Latein 2023 - Samstag',
+            'display_id': 'ggcbremen/formationswochenende-latein-2023',
+            'description': 'md5:6e4060d40ff6a8f8eeb471b51a8f08b2',
+            'live_status': 'was_live',
+            'channel': 'Grün-Gold-Club Bremen e.V.',
+            'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
+            'channel_url': 'https://sportdeutschland.tv/ggcbremen',
+        },
+        'playlist_count': 3,
+        'playlist': [{
+            'info_dict': {
+                'id': '988e1fea-9d44-4fab-8c72-3085fb667547',
+                'ext': 'mp4',
+                'channel_url': 'https://sportdeutschland.tv/ggcbremen',
+                'channel_id': '9888f04e-bb46-4c7f-be47-df960a4167bb',
+                'channel': 'Grün-Gold-Club Bremen e.V.',
+                'duration': 86,
+                'title': 'Formationswochenende Latein 2023 - Samstag Part 1',
+                'upload_date': '20230225',
+                'timestamp': 1677349909,
+                'live_status': 'was_live',
+            }
+        }]
+    }, {
+        'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
+        'info_dict': {
+            'id': '95d71b8a-370a-4b87-ad16-94680da18528',
+            'ext': 'mp4',
+            'title': r're:Gymnastik International - Tag 1 .+',
+            'display_id': 'dtb/gymnastik-international-tag-1',
+            'channel_id': '936ecef1-2f4a-4e08-be2f-68073cb7ecab',
+            'channel': 'Deutscher Turner-Bund',
+            'channel_url': 'https://sportdeutschland.tv/dtb',
+            'description': 'md5:07a885dde5838a6f0796ee21dc3b0c52',
+            'live_status': 'is_live',
+        },
+        'skip': 'live',
     }]
 
+    def _process_video(self, asset_id, video):
+        is_live = video['type'] == 'mux_live'
+        token = self._download_json(
+            f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
+            video['id'], query={'type': video['type'], 'playback_id': video['src']})['token']
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://stream.mux.com/{video["src"]}.m3u8?token={token}', video['id'], live=is_live)
+
+        return {
+            'is_live': is_live,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(video, {
+                'id': 'id',
+                'duration': ('duration', {lambda x: float(x) > 0 and float(x)}),
+                'timestamp': ('created_at', {unified_timestamp})
+            }),
+        }
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
         meta = self._download_json(
-            'https://api.sportdeutschland.tv/api/stateless/frontend/assets/' + display_id,
+            f'https://api.sportdeutschland.tv/api/stateless/frontend/assets/{display_id}',
             display_id, query={'access_token': 'true'})
 
-        asset_id = traverse_obj(meta, 'id', 'uuid')
-
         info = {
-            'id': asset_id,
+            'display_id': display_id,
-            'channel_url': format_field(meta, ('profile', 'slug'), 'https://sportdeutschland.tv/%s'),
             **traverse_obj(meta, {
+                'id': (('id', 'uuid'), ),
                 'title': (('title', 'name'), {strip_or_none}),
                 'description': 'description',
                 'channel': ('profile', 'name'),
                 'channel_id': ('profile', 'id'),
                 'is_live': 'currently_live',
-                'was_live': 'was_live'
+                'was_live': 'was_live',
+                'channel_url': ('profile', 'slug', {lambda x: f'https://sportdeutschland.tv/{x}'}),
             }, get_all=False)
         }
 
-        videos = meta.get('videos') or []
+        parts = traverse_obj(meta, (('livestream', ('videos', ...)), ))
+        entries = [{
+            'title': join_nonempty(info.get('title'), f'Part {i}', delim=' '),
+            **traverse_obj(info, {'channel': 'channel', 'channel_id': 'channel_id',
+                                  'channel_url': 'channel_url', 'was_live': 'was_live'}),
+            **self._process_video(info['id'], video),
+        } for i, video in enumerate(parts, 1)]
 
-        if len(videos) > 1:
+        return {
-            info.update({
+            '_type': 'multi_video',
-                '_type': 'multi_video',
+            **info,
-                'entries': self.processVideoOrStream(asset_id, video)
+            'entries': entries,
-            } for video in enumerate(videos) if video.get('formats'))
+        } if len(entries) > 1 else {
-
+            **info,
-        elif len(videos) == 1:
+            **entries[0],
-            info.update(
+            'title': info.get('title'),
-                self.processVideoOrStream(asset_id, videos[0])
-            )
-
-        livestream = meta.get('livestream')
-
-        if livestream is not None:
-            info.update(
-                self.processVideoOrStream(asset_id, livestream)
-            )
-
-        return info
-
-    def process_video_or_stream(self, asset_id, video):
-        video_id = video['id']
-        video_src = video['src']
-        video_type = video['type']
-
-        token = self._download_json(
-            f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
-            video_id, query={'type': video_type, 'playback_id': video_src})['token']
-        formats = self._extract_m3u8_formats(f'https://stream.mux.com/{video_src}.m3u8?token={token}', video_id)
-
-        video_data = {
-            'display_id': video_id,
-            'formats': formats,
         }
-        if video_type == 'mux_vod':
-            video_data.update({
-                'duration': video.get('duration'),
-                'timestamp': unified_timestamp(video.get('created_at'))
-            })
-
-        return video_data

yt_dlp/extractor/telecaribe.py

@@ -0,0 +1,77 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class TelecaribePlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?play\.telecaribe\.co/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.play.telecaribe.co/breicok',
+        'info_dict': {
+            'id': 'breicok',
+            'title': 'Breicok',
+        },
+        'playlist_count': 7,
+    }, {
+        'url': 'https://www.play.telecaribe.co/si-fue-gol-de-yepes',
+        'info_dict': {
+            'id': 'si-fue-gol-de-yepes',
+            'title': 'Sí Fue Gol de Yepes',
+        },
+        'playlist_count': 6,
+    }, {
+        'url': 'https://www.play.telecaribe.co/ciudad-futura',
+        'info_dict': {
+            'id': 'ciudad-futura',
+            'title': 'Ciudad Futura',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.play.telecaribe.co/live',
+        'info_dict': {
+            'id': 'live',
+            'title': r're:^Señal en vivo',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        }
+    }]
+
+    def _download_player_webpage(self, webpage, display_id):
+        page_id = self._search_regex(
+            (r'window.firstPageId\s*=\s*["\']([^"\']+)', r'<div[^>]+id\s*=\s*"pageBackground_([^"]+)'),
+            webpage, 'page_id')
+
+        props = self._download_json(self._search_regex(
+            rf'<link[^>]+href\s*=\s*"([^"]+)"[^>]+id\s*=\s*"features_{page_id}"',
+            webpage, 'json_props_url'), display_id)['props']['render']['compProps']
+
+        return self._download_webpage(traverse_obj(props, (..., 'url'))[-1], display_id)
+
+    def _get_clean_title(self, title):
+        return re.sub(r'\s*\|\s*Telecaribe\s*VOD', '', title or '').strip() or None
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player = self._download_player_webpage(webpage, display_id)
+
+        if display_id != 'live':
+            return self.playlist_from_matches(
+                re.findall(r'<a[^>]+href\s*=\s*"([^"]+\.mp4)', player), display_id,
+                self._get_clean_title(self._og_search_title(webpage)))
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            self._search_regex(r'(?:let|const|var)\s+source\s*=\s*["\']([^"\']+)', player, 'm3u8 url'),
+            display_id, 'mp4')
+
+        return {
+            'id': display_id,
+            'title': self._get_clean_title(self._og_search_title(webpage)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': True,
+        }

yt_dlp/extractor/tubetugraz.py

@@ -21,17 +21,36 @@ class TubeTuGrazBaseIE(InfoExtractor):
         if not urlh:
             return
 
-        urlh = self._request_webpage(
+        content, urlh = self._download_webpage_handle(
             urlh.geturl(), None, fatal=False, headers={'referer': urlh.geturl()},
-            note='logging in', errnote='unable to log in', data=urlencode_postdata({
+            note='logging in', errnote='unable to log in',
+            data=urlencode_postdata({
                 'lang': 'de',
                 '_eventId_proceed': '',
                 'j_username': username,
                 'j_password': password
             }))
+        if not urlh or urlh.geturl() == 'https://tube.tugraz.at/paella/ui/index.html':
+            return
 
-        if urlh and urlh.geturl() != 'https://tube.tugraz.at/paella/ui/index.html':
+        if not self._html_search_regex(
+                r'<p\b[^>]*>(Bitte geben Sie einen OTP-Wert ein:)</p>',
+                content, 'TFA prompt', default=None):
             self.report_warning('unable to login: incorrect password')
+            return
+
+        content, urlh = self._download_webpage_handle(
+            urlh.geturl(), None, fatal=False, headers={'referer': urlh.geturl()},
+            note='logging in with TFA', errnote='unable to log in with TFA',
+            data=urlencode_postdata({
+                'lang': 'de',
+                '_eventId_proceed': '',
+                'j_tokenNumber': self._get_tfa_info(),
+            }))
+        if not urlh or urlh.geturl() == 'https://tube.tugraz.at/paella/ui/index.html':
+            return
+
+        self.report_warning('unable to login: incorrect TFA code')
 
     def _extract_episode(self, episode_info):
         id = episode_info.get('id')

yt_dlp/extractor/tunein.py

@@ -1,149 +1,201 @@
-import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
-from ..compat import compat_urlparse
+    OnDemandPagedList,
+    determine_ext,
+    parse_iso8601,
+    traverse_obj,
+)
 
 
 class TuneInBaseIE(InfoExtractor):
-    _API_BASE_URL = 'http://tunein.com/tuner/tune/'
+    _VALID_URL_BASE = r'https?://(?:www\.)?tunein\.com'
 
-    def _real_extract(self, url):
+    def _extract_metadata(self, webpage, content_id):
-        content_id = self._match_id(url)
+        return self._search_json(r'window.INITIAL_STATE=', webpage, 'hydration', content_id, fatal=False)
-
-        content_info = self._download_json(
-            self._API_BASE_URL + self._API_URL_QUERY % content_id,
-            content_id, note='Downloading JSON metadata')
-
-        title = content_info['Title']
-        thumbnail = content_info.get('Logo')
-        location = content_info.get('Location')
-        streams_url = content_info.get('StreamUrl')
-        if not streams_url:
-            raise ExtractorError('No downloadable streams found', expected=True)
-        if not streams_url.startswith('http://'):
-            streams_url = compat_urlparse.urljoin(url, streams_url)
 
+    def _extract_formats_and_subtitles(self, content_id):
         streams = self._download_json(
-            streams_url, content_id, note='Downloading stream data',
+            f'https://opml.radiotime.com/Tune.ashx?render=json&formats=mp3,aac,ogg,flash,hls&id={content_id}',
-            transform_source=lambda s: re.sub(r'^\s*\((.*)\);\s*$', r'\1', s))['Streams']
+            content_id)['body']
 
-        is_live = None
+        formats, subtitles = [], {}
-        formats = []
         for stream in streams:
-            if stream.get('Type') == 'Live':
+            if stream.get('media_type') == 'hls':
-                is_live = True
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(stream['url'], content_id, fatal=False)
-            reliability = stream.get('Reliability')
+                formats.extend(fmts)
-            format_note = (
+                self._merge_subtitles(subs, target=subtitles)
-                'Reliability: %d%%' % reliability
+            elif determine_ext(stream['url']) == 'pls':
-                if reliability is not None else None)
+                playlist_content = self._download_webpage(stream['url'], content_id)
-            formats.append({
+                formats.append({
-                'preference': (
+                    'url': self._search_regex(r'File1=(.*)', playlist_content, 'url', fatal=False),
-                    0 if reliability is None or reliability > 90
+                    'abr': stream.get('bitrate'),
-                    else 1),
+                    'ext': stream.get('media_type'),
-                'abr': stream.get('Bandwidth'),
+                })
-                'ext': stream.get('MediaType').lower(),
+            else:
-                'acodec': stream.get('MediaType'),
+                formats.append({
-                'vcodec': 'none',
+                    'url': stream['url'],
-                'url': stream.get('Url'),
+                    'abr': stream.get('bitrate'),
-                'source_preference': reliability,
+                    'ext': stream.get('media_type'),
-                'format_note': format_note,
+                })
-            })
 
-        return {
+        return formats, subtitles
-            'id': content_id,
-            'title': title,
-            'formats': formats,
-            'thumbnail': thumbnail,
-            'location': location,
-            'is_live': is_live,
-        }
-
-
-class TuneInClipIE(TuneInBaseIE):
-    IE_NAME = 'tunein:clip'
-    _VALID_URL = r'https?://(?:www\.)?tunein\.com/station/.*?audioClipId\=(?P<id>\d+)'
-    _API_URL_QUERY = '?tuneType=AudioClip&audioclipId=%s'
-
-    _TESTS = [{
-        'url': 'http://tunein.com/station/?stationId=246119&audioClipId=816',
-        'md5': '99f00d772db70efc804385c6b47f4e77',
-        'info_dict': {
-            'id': '816',
-            'title': '32m',
-            'ext': 'mp3',
-        },
-    }]
 
 
 class TuneInStationIE(TuneInBaseIE):
-    IE_NAME = 'tunein:station'
+    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'(?:/radio/[^?#]+-|/embed/player/)(?P<id>s\d+)'
-    _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-s|station/.*?StationId=|embed/player/s)(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/s\d+)']
-    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/[pst]\d+)']
-    _API_URL_QUERY = '?tuneType=Station&stationId=%s'
-
-    @classmethod
-    def suitable(cls, url):
-        return False if TuneInClipIE.suitable(url) else super(TuneInStationIE, cls).suitable(url)
 
     _TESTS = [{
-        'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
+        'url': 'https://tunein.com/radio/Jazz24-885-s34682/',
         'info_dict': {
-            'id': '34682',
+            'id': 's34682',
-            'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
+            'title': 're:^Jazz24',
+            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
+            'thumbnail': 're:^https?://[^?&]+/s34682',
+            'location': 'Seattle-Tacoma, US',
             'ext': 'mp3',
-            'location': 'Tacoma, WA',
+            'live_status': 'is_live',
         },
         'params': {
-            'skip_download': True,  # live stream
+            'skip_download': True,
         },
     }, {
-        'url': 'http://tunein.com/embed/player/s6404/',
+        'url': 'https://tunein.com/embed/player/s6404/',
         'only_matching': True,
-    }]
+    }, {
-
+        'url': 'https://tunein.com/radio/BBC-Radio-1-988-s24939/',
-
-class TuneInProgramIE(TuneInBaseIE):
-    IE_NAME = 'tunein:program'
-    _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:radio/.*?-p|program/.*?ProgramId=|embed/player/p)(?P<id>\d+)'
-    _API_URL_QUERY = '?tuneType=Program&programId=%s'
-
-    _TESTS = [{
-        'url': 'http://tunein.com/radio/Jazz-24-p2506/',
         'info_dict': {
-            'id': '2506',
+            'id': 's24939',
-            'title': 'Jazz 24 on 91.3 WUKY-HD3',
+            'title': 're:^BBC Radio 1',
+            'description': 'md5:f3f75f7423398d87119043c26e7bfb84',
+            'thumbnail': 're:^https?://[^?&]+/s24939',
+            'location': 'London, UK',
             'ext': 'mp3',
-            'location': 'Lexington, KY',
+            'live_status': 'is_live',
         },
         'params': {
-            'skip_download': True,  # live stream
+            'skip_download': True,
         },
-    }, {
-        'url': 'http://tunein.com/embed/player/p191660/',
-        'only_matching': True,
     }]
 
+    def _real_extract(self, url):
+        station_id = self._match_id(url)
 
-class TuneInTopicIE(TuneInBaseIE):
+        webpage = self._download_webpage(url, station_id)
-    IE_NAME = 'tunein:topic'
+        metadata = self._extract_metadata(webpage, station_id)
-    _VALID_URL = r'https?://(?:www\.)?tunein\.com/(?:topic/.*?TopicId=|embed/player/t)(?P<id>\d+)'
+
-    _API_URL_QUERY = '?tuneType=Topic&topicId=%s'
+        formats, subtitles = self._extract_formats_and_subtitles(station_id)
+        return {
+            'id': station_id,
+            'title': traverse_obj(metadata, ('profiles', station_id, 'title')),
+            'description': traverse_obj(metadata, ('profiles', station_id, 'description')),
+            'thumbnail': traverse_obj(metadata, ('profiles', station_id, 'image')),
+            'timestamp': parse_iso8601(
+                traverse_obj(metadata, ('profiles', station_id, 'actions', 'play', 'publishTime'))),
+            'location': traverse_obj(
+                metadata, ('profiles', station_id, 'metadata', 'properties', 'location', 'displayName'),
+                ('profiles', station_id, 'properties', 'location', 'displayName')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': traverse_obj(metadata, ('profiles', station_id, 'actions', 'play', 'isLive')),
+        }
+
+
+class TuneInPodcastIE(TuneInBaseIE):
+    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'/(?:podcasts/[^?#]+-|embed/player/)(?P<id>p\d+)/?(?:#|$)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>(?:https?://)?tunein\.com/embed/player/p\d+)']
 
     _TESTS = [{
-        'url': 'http://tunein.com/topic/?TopicId=101830576',
+        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019',
-        'md5': 'c31a39e6f988d188252eae7af0ef09c9',
         'info_dict': {
-            'id': '101830576',
+            'id': 'p1153019',
-            'title': 'Votez pour moi du 29 octobre 2015 (29/10/15)',
+            'title': 'Lex Fridman Podcast',
-            'ext': 'mp3',
+            'description': 'md5:bedc4e5f1c94f7dec6e4317b5654b00d',
-            'location': 'Belgium',
         },
+        'playlist_mincount': 200,
     }, {
-        'url': 'http://tunein.com/embed/player/t101830576/',
+        'url': 'https://tunein.com/embed/player/p191660/',
-        'only_matching': True,
+        'only_matching': True
+    }, {
+        'url': 'https://tunein.com/podcasts/World-News/BBC-News-p14/',
+        'info_dict': {
+            'id': 'p14',
+            'title': 'BBC News',
+            'description': 'md5:1218e575eeaff75f48ed978261fa2068',
+        },
+        'playlist_mincount': 200,
     }]
 
+    _PAGE_SIZE = 30
+
+    def _real_extract(self, url):
+        podcast_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, podcast_id, fatal=False)
+        metadata = self._extract_metadata(webpage, podcast_id)
+
+        def page_func(page_num):
+            api_response = self._download_json(
+                f'https://api.tunein.com/profiles/{podcast_id}/contents', podcast_id,
+                note=f'Downloading page {page_num + 1}', query={
+                    'filter': 't:free',
+                    'offset': page_num * self._PAGE_SIZE,
+                    'limit': self._PAGE_SIZE,
+                })
+
+            return [
+                self.url_result(
+                    f'https://tunein.com/podcasts/{podcast_id}?topicId={episode["GuideId"][1:]}',
+                    TuneInPodcastEpisodeIE, title=episode.get('Title'))
+                for episode in api_response['Items']]
+
+        entries = OnDemandPagedList(page_func, self._PAGE_SIZE)
+        return self.playlist_result(
+            entries, playlist_id=podcast_id, title=traverse_obj(metadata, ('profiles', podcast_id, 'title')),
+            description=traverse_obj(metadata, ('profiles', podcast_id, 'description')))
+
+
+class TuneInPodcastEpisodeIE(TuneInBaseIE):
+    _VALID_URL = TuneInBaseIE._VALID_URL_BASE + r'/podcasts/(?:[^?&]+-)?(?P<podcast_id>p\d+)/?\?topicId=(?P<id>\w\d+)'
+
+    _TESTS = [{
+        'url': 'https://tunein.com/podcasts/Technology-Podcasts/Artificial-Intelligence-p1153019/?topicId=236404354',
+        'info_dict': {
+            'id': 't236404354',
+            'title': '#351 \u2013 MrBeast: Future of YouTube, Twitter, TikTok, and Instagram',
+            'description': 'md5:e1734db6f525e472c0c290d124a2ad77',
+            'thumbnail': 're:^https?://[^?&]+/p1153019',
+            'timestamp': 1673458571,
+            'upload_date': '20230111',
+            'series_id': 'p1153019',
+            'series': 'Lex Fridman Podcast',
+            'ext': 'mp3',
+        },
+    }]
+
+    def _real_extract(self, url):
+        podcast_id, episode_id = self._match_valid_url(url).group('podcast_id', 'id')
+        episode_id = f't{episode_id}'
+
+        webpage = self._download_webpage(url, episode_id)
+        metadata = self._extract_metadata(webpage, episode_id)
+
+        formats, subtitles = self._extract_formats_and_subtitles(episode_id)
+        return {
+            'id': episode_id,
+            'title': traverse_obj(metadata, ('profiles', episode_id, 'title')),
+            'description': traverse_obj(metadata, ('profiles', episode_id, 'description')),
+            'thumbnail': traverse_obj(metadata, ('profiles', episode_id, 'image')),
+            'timestamp': parse_iso8601(
+                traverse_obj(metadata, ('profiles', episode_id, 'actions', 'play', 'publishTime'))),
+            'series_id': podcast_id,
+            'series': traverse_obj(metadata, ('profiles', podcast_id, 'title')),
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
 
 class TuneInShortenerIE(InfoExtractor):
     IE_NAME = 'tunein:shortener'
@@ -154,10 +206,13 @@ class TuneInShortenerIE(InfoExtractor):
         # test redirection
         'url': 'http://tun.in/ser7s',
         'info_dict': {
-            'id': '34682',
+            'id': 's34682',
-            'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
+            'title': 're:^Jazz24',
+            'description': 'md5:d6d0b89063fd68d529fa7058ee98619b',
+            'thumbnail': 're:^https?://[^?&]+/s34682',
+            'location': 'Seattle-Tacoma, US',
             'ext': 'mp3',
-            'location': 'Tacoma, WA',
+            'live_status': 'is_live',
         },
         'params': {
             'skip_download': True,  # live stream
@@ -169,6 +224,11 @@ class TuneInShortenerIE(InfoExtractor):
         # The server doesn't support HEAD requests
         urlh = self._request_webpage(
             url, redirect_id, note='Downloading redirect page')
+
         url = urlh.geturl()
+        url_parsed = urllib.parse.urlparse(url)
+        if url_parsed.port == 443:
+            url = url_parsed._replace(netloc=url_parsed.hostname).geturl()
+
         self.to_screen('Following redirect: %s' % url)
         return self.url_result(url)

yt_dlp/extractor/twitch.py

@@ -48,12 +48,12 @@ class TwitchBaseIE(InfoExtractor):
         'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
         'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
         'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
-        'ChannelCollectionsContent': '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84',
+        'ChannelCollectionsContent': '447aec6a0cc1e8d0a8d7732d47eb0762c336a2294fdb009e9c9d854e49d484b9',
-        'StreamMetadata': '1c719a40e481453e5c48d9bb585d971b8b372f8ebb105b17076722264dfa5b3e',
+        'StreamMetadata': 'a647c2a13599e5991e175155f798ca7f1ecddde73f7f341f39009c14dbf59962',
         'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
         'VideoAccessToken_Clip': '36b89d2507fce29e5ca551df756d27c1cfe079e2609642b4390aa4c35796eb11',
         'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
-        'VideoMetadata': '226edb3e692509f727fd56821f5653c05740242c82b0388883e0c0e75dcbf687',
+        'VideoMetadata': '49b5b8f268cdeb259d75b58dcb0c1a748e3b575003448a2333dc5cdafd49adad',
         'VideoPlayer_ChapterSelectButtonVideo': '8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41',
         'VideoPlayer_VODSeekbarPreviewVideo': '07e99e4d56c5a7c67117a154777b0baf85a5ffefa393b213f4bc712ccaf85dd6',
     }
@@ -380,13 +380,14 @@ class TwitchVodIE(TwitchBaseIE):
             }],
             'Downloading stream metadata GraphQL')
 
-        video = traverse_obj(data, (0, 'data', 'video'))
+        video = traverse_obj(data, (..., 'data', 'video'), get_all=False)
-        video['moments'] = traverse_obj(data, (1, 'data', 'video', 'moments', 'edges', ..., 'node'))
-        video['storyboard'] = traverse_obj(data, (2, 'data', 'video', 'seekPreviewsURL'), expected_type=url_or_none)
-
         if video is None:
-            raise ExtractorError(
+            raise ExtractorError(f'Video {item_id} does not exist', expected=True)
-                'Video %s does not exist' % item_id, expected=True)
+
+        video['moments'] = traverse_obj(data, (..., 'data', 'video', 'moments', 'edges', ..., 'node'))
+        video['storyboard'] = traverse_obj(
+            data, (..., 'data', 'video', 'seekPreviewsURL', {url_or_none}), get_all=False)
+
         return video
 
     def _extract_info(self, info):
@@ -854,6 +855,13 @@ class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
             'title': 'spamfish - Collections',
         },
         'playlist_mincount': 3,
+    }, {
+        'url': 'https://www.twitch.tv/monstercat/videos?filter=collections',
+        'info_dict': {
+            'id': 'monstercat',
+            'title': 'monstercat - Collections',
+        },
+        'playlist_mincount': 13,
     }]
 
     _OPERATION_NAME = 'ChannelCollectionsContent'
@@ -922,6 +930,7 @@ class TwitchStreamIE(TwitchBaseIE):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': 'User does not exist',
     }, {
         'url': 'http://www.twitch.tv/miracle_doto#profile-0',
         'only_matching': True,
@@ -934,6 +943,25 @@ class TwitchStreamIE(TwitchBaseIE):
     }, {
         'url': 'https://m.twitch.tv/food',
         'only_matching': True,
+    }, {
+        'url': 'https://www.twitch.tv/monstercat',
+        'info_dict': {
+            'id': '40500071752',
+            'display_id': 'monstercat',
+            'title': 're:Monstercat',
+            'description': 'md5:0945ad625e615bc8f0469396537d87d9',
+            'is_live': True,
+            'timestamp': 1677107190,
+            'upload_date': '20230222',
+            'uploader': 'Monstercat',
+            'uploader_id': 'monstercat',
+            'live_status': 'is_live',
+            'thumbnail': 're:https://.*.jpg',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
     }]
 
     @classmethod

yt_dlp/extractor/twitter.py

@@ -838,6 +838,28 @@ class TwitterIE(TwitterBaseIE):
             'timestamp': 1670306984.0,
         },
         'params': {'extractor_args': {'twitter': {'force_graphql': ['']}}},
+    }, {
+        # url to retweet id
+        'url': 'https://twitter.com/liberdalau/status/1623739803874349067',
+        'info_dict': {
+            'id': '1623274794488659969',
+            'display_id': '1623739803874349067',
+            'ext': 'mp4',
+            'title': 'Johnny Bullets - Me after going viral to over 30million people:    Whoopsie-daisy',
+            'description': 'md5:e873616a4a8fe0f93e71872678a672f3',
+            'uploader': 'Johnny Bullets',
+            'uploader_id': 'Johnnybull3ts',
+            'uploader_url': 'https://twitter.com/Johnnybull3ts',
+            'age_limit': 0,
+            'tags': [],
+            'duration': 8.033,
+            'timestamp': 1675853859.0,
+            'upload_date': '20230208',
+            'thumbnail': r're:https://pbs\.twimg\.com/ext_tw_video_thumb/.+',
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+        },
     }, {
         # onion route
         'url': 'https://twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid.onion/TwitterBlue/status/1484226494708662273',
@@ -949,13 +971,13 @@ class TwitterIE(TwitterBaseIE):
             status = self._graphql_to_legacy(result, twid)
 
         else:
-            status = self._call_api(f'statuses/show/{twid}.json', twid, {
+            status = traverse_obj(self._call_api(f'statuses/show/{twid}.json', twid, {
                 'cards_platform': 'Web-12',
                 'include_cards': 1,
                 'include_reply_count': 1,
                 'include_user_entities': 0,
                 'tweet_mode': 'extended',
-            })
+            }), 'retweeted_status', None)
 
         title = description = status['full_text'].replace('\n', ' ')
         # strip  'https -_t.co_BJYgOjSeGA' junk from filenames

yt_dlp/extractor/xvideos.py

@@ -157,3 +157,24 @@ class XVideosIE(InfoExtractor):
             'thumbnails': thumbnails,
             'age_limit': 18,
         }
+
+
+class XVideosQuickiesIE(InfoExtractor):
+    IE_NAME = 'xvideos:quickies'
+    _VALID_URL = r'https?://(?P<domain>(?:[^/]+\.)?xvideos2?\.com)/amateur-channels/[^#]+#quickies/a/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.xvideos.com/amateur-channels/wifeluna#quickies/a/47258683',
+        'md5': '16e322a93282667f1963915568f782c1',
+        'info_dict': {
+            'id': '47258683',
+            'ext': 'mp4',
+            'title': 'Verification video',
+            'age_limit': 18,
+            'duration': 16,
+            'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
+        }
+    }]
+
+    def _real_extract(self, url):
+        domain, id_ = self._match_valid_url(url).group('domain', 'id')
+        return self.url_result(f'https://{domain}/video{id_}/_', XVideosIE, id_)

yt_dlp/extractor/youtube.py

@@ -3205,11 +3205,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
             ), expected_type=list)
 
-        return self._extract_chapters(
+        return self._extract_chapters_helper(
             chapter_list,
-            chapter_time=lambda chapter: float_or_none(
+            start_function=lambda chapter: float_or_none(
                 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
-            chapter_title=lambda chapter: traverse_obj(
+            title_function=lambda chapter: traverse_obj(
                 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
             duration=duration)
 
@@ -3222,42 +3222,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         chapter_title = lambda chapter: self._get_text(chapter, 'title')
 
         return next(filter(None, (
-            self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
+            self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
-                                   chapter_time, chapter_title, duration)
+                                          chapter_time, chapter_title, duration)
             for contents in content_list)), [])
 
-    def _extract_chapters_from_description(self, description, duration):
-        duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
-        sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
-        return self._extract_chapters(
-            re.findall(sep_re % (duration_re, r'.+?'), description or ''),
-            chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
-            duration=duration, strict=False) or self._extract_chapters(
-            re.findall(sep_re % (r'.+?', duration_re), description or ''),
-            chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
-            duration=duration, strict=False)
-
-    def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
-        if not duration:
-            return
-        chapter_list = [{
-            'start_time': chapter_time(chapter),
-            'title': chapter_title(chapter),
-        } for chapter in chapter_list or []]
-        if not strict:
-            chapter_list.sort(key=lambda c: c['start_time'] or 0)
-
-        chapters = [{'start_time': 0}]
-        for idx, chapter in enumerate(chapter_list):
-            if chapter['start_time'] is None:
-                self.report_warning(f'Incomplete chapter {idx}')
-            elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
-                chapters.append(chapter)
-            elif chapter not in chapters:
-                self.report_warning(
-                    f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}"')
-        return chapters[1:]
-
     def _extract_comment(self, comment_renderer, parent=None):
         comment_id = comment_renderer.get('commentId')
         if not comment_id:
@@ -3749,10 +3717,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'filesize': int_or_none(fmt.get('contentLength')),
                 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
                 'format_note': join_nonempty(
-                    '%s%s' % (audio_track.get('displayName') or '',
+                    join_nonempty(audio_track.get('displayName'),
-                              ' (default)' if language_preference > 0 else ''),
+                                  language_preference > 0 and ' (default)', delim=''),
                     fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
-                    'DRC' if fmt.get('isDrc') else None,
+                    fmt.get('isDrc') and 'DRC',
                     try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
                     try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
                     throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),

yt_dlp/update.py

@@ -29,13 +29,13 @@ UPDATE_SOURCES = {
     'stable': 'yt-dlp/yt-dlp',
     'nightly': 'yt-dlp/yt-dlp-nightly-builds',
 }
+REPOSITORY = UPDATE_SOURCES['stable']
 
 _VERSION_RE = re.compile(r'(\d+\.)*\d+')
 
 API_BASE_URL = 'https://api.github.com/repos'
 
 # Backwards compatibility variables for the current channel
-REPOSITORY = UPDATE_SOURCES[CHANNEL]
 API_URL = f'{API_BASE_URL}/{REPOSITORY}/releases'
 
 

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2023.03.03'
+__version__ = '2023.03.04'
 
-RELEASE_GIT_HEAD = '93449642815a6973a4b09b289982ca7e1f961b5f'
+RELEASE_GIT_HEAD = '392389b7df7b818f794b231f14dc396d4875fbad'
 
 VARIANT = None