chore: extend .gitignore with AI assistant configurations and caches

18 tests covering:
- channel_ctoken_v5 protobuf token generation per tab
- shortsLockupViewModel parsing (id, title, thumbnail, type)
- View count formatting with K/M/B suffixes
- extract_items with reloadContinuationItemsCommand response format

All tests run offline with mocked data, no network access.

.build.yml

@@ -1,12 +0,0 @@
-image: debian/buster
-packages:
-  - python3-pip
-  - virtualenv
-tasks:
-  - test: |
-      cd yt-local
-      virtualenv -p python3 venv
-      source venv/bin/activate
-      python --version
-      pip install -r requirements-dev.txt
-      pytest

.drone.yml

@@ -1,10 +0,0 @@
-kind: pipeline
-name: default
-
-steps:
-- name: test
-  image: python:3.7.3
-  commands:
-    - pip install --upgrade pip
-    - pip install -r requirements-dev.txt
-    - pytest

.gitea/workflows/ci.yaml

@@ -0,0 +1,23 @@
+name: CI
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: pytest

.gitea/workflows/git-sync.yaml

@@ -0,0 +1,40 @@
+name: git-sync-with-mirror
+
+on:
+  push:
+    branches: [ master ]
+  workflow_dispatch:
+
+jobs:
+  git-sync:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: git-sync
+        env:
+          git_sync_source_repo: git@git.fridu.us:heckyel/yt-local.git
+          git_sync_destination_repo: ssh://git@c.fridu.us/software/yt-local.git
+        if: env.git_sync_source_repo && env.git_sync_destination_repo
+        uses: astounds/git-sync@v1
+        with:
+          source_repo: git@git.fridu.us:heckyel/yt-local.git
+          source_branch: "master"
+          destination_repo: ssh://git@c.fridu.us/software/yt-local.git
+          destination_branch: "master"
+          source_ssh_private_key: ${{ secrets.GIT_SYNC_SOURCE_SSH_PRIVATE_KEY }}
+          destination_ssh_private_key:  ${{ secrets.GIT_SYNC_DESTINATION_SSH_PRIVATE_KEY }}
+
+      - name: git-sync-sourcehut
+        env:
+          git_sync_source_repo: git@git.fridu.us:heckyel/yt-local.git
+          git_sync_destination_repo: git@git.sr.ht:~heckyel/yt-local
+        if: env.git_sync_source_repo && env.git_sync_destination_repo
+        uses: astounds/git-sync@v1
+        with:
+          source_repo: git@git.fridu.us:heckyel/yt-local.git
+          source_branch: "master"
+          destination_repo: git@git.sr.ht:~heckyel/yt-local
+          destination_branch: "master"
+          source_ssh_private_key: ${{ secrets.GIT_SYNC_SOURCE_SSH_PRIVATE_KEY }}
+          destination_ssh_private_key:  ${{ secrets.GIT_SYNC_DESTINATION_SSH_PRIVATE_KEY }}
+        continue-on-error: true

.gitignore

@@ -1,15 +1,166 @@
+# =============================================================================
+# .gitignore - YT Local
+# =============================================================================
+
+# -----------------------------------------------------------------------------
+# Python / Bytecode
+# -----------------------------------------------------------------------------
 __pycache__/
+*.py[cod]
 *$py.class
-debug/
+*.so
+.Python
+
+# -----------------------------------------------------------------------------
+# Virtual Environments
+# -----------------------------------------------------------------------------
+.env
+.env.*
+!.env.example
+.venv/
+venv/
+ENV/
+env/
+*.egg-info/
+.eggs/
+
+# -----------------------------------------------------------------------------
+# IDE / Editors
+# -----------------------------------------------------------------------------
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+.flycheck_*
+*.sublime-project
+*.sublime-workspace
+
+# -----------------------------------------------------------------------------
+# Distribution / Packaging
+# -----------------------------------------------------------------------------
+build/
+dist/
+*.egg
+*.manifest
+*.spec
+pip-wheel-metadata/
+share/python-wheels/
+MANIFEST
+
+# -----------------------------------------------------------------------------
+# Testing / Coverage
+# -----------------------------------------------------------------------------
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+.tox/
+.nox/
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+
+# -----------------------------------------------------------------------------
+# Type Checking / Linting
+# -----------------------------------------------------------------------------
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.pyre/
+
+# -----------------------------------------------------------------------------
+# Jupyter / IPython
+# -----------------------------------------------------------------------------
+.ipynb_checkpoints
+profile_default/
+ipython_config.py
+
+# -----------------------------------------------------------------------------
+# Python Tools
+# -----------------------------------------------------------------------------
+# pyenv
+.python-version
+# pipenv
+Pipfile.lock
+# PEP 582
+__pypackages__/
+# Celery
+celerybeat-schedule
+celerybeat.pid
+# Sphinx
+docs/_build/
+# PyBuilder
+target/
+# Scrapy
+.scrapy
+
+# -----------------------------------------------------------------------------
+# Web Frameworks
+# -----------------------------------------------------------------------------
+# Django
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+# Flask
+instance/
+.webassets-cache
+
+# -----------------------------------------------------------------------------
+# Documentation
+# -----------------------------------------------------------------------------
+# mkdocs
+/site
+
+# -----------------------------------------------------------------------------
+# Project Specific - YT Local
+# -----------------------------------------------------------------------------
+# Data & Debug
 data/
-python/
+debug/
+
+# Release artifacts
 release/
 yt-local/
-banned_addresses.txt
-settings.txt
 get-pip.py
 latest-dist.zip
 *.7z
 *.zip
-*venv*
+
-flycheck_*
+# Configuration (contains user-specific data)
+settings.txt
+banned_addresses.txt
+
+# -----------------------------------------------------------------------------
+# Temporary / Backup Files
+# -----------------------------------------------------------------------------
+*.log
+*.tmp
+*.bak
+*.orig
+*.cache/
+
+# -----------------------------------------------------------------------------
+# AI assistants / LLM tools
+# -----------------------------------------------------------------------------
+# Claude AI assistant configuration and cache
+.claude/
+claude*
+.anthropic/
+
+# Kiro AI tool configuration and cache
+.kiro/
+kiro*
+
+# Qwen AI-related files and caches
+.qwen/
+qwen*
+
+# Other AI assistants/IDE integrations
+.cursor/
+.gpt/
+.openai/

Makefile

@@ -0,0 +1,210 @@
+# yt-local Makefile
+# Automated tasks for development, translations, and maintenance
+
+.PHONY: help install dev clean test i18n-extract i18n-init i18n-update i18n-compile i18n-stats i18n-clean setup-dev lint format backup restore
+
+# Variables
+PYTHON := python3
+PIP := pip3
+LANG_CODE ?= es
+VENV_DIR := venv
+PROJECT_NAME := yt-local
+
+## Help
+help: ## Show this help message
+	@echo "$(PROJECT_NAME) - Available tasks:"
+	@echo ""
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "  %-20s %s\n", $$1, $$2}'
+	@echo ""
+	@echo "Examples:"
+	@echo "  make install          # Install dependencies"
+	@echo "  make dev              # Run development server"
+	@echo "  make i18n-extract     # Extract strings for translation"
+	@echo "  make i18n-init LANG_CODE=fr  # Initialize French"
+	@echo "  make lint             # Check code style"
+
+## Installation and Setup
+install: ## Install project dependencies
+	@echo "[INFO] Installing dependencies..."
+	$(PIP) install -r requirements.txt
+	@echo "[SUCCESS] Dependencies installed"
+
+setup-dev: ## Complete development setup
+	@echo "[INFO] Setting up development environment..."
+	$(PYTHON) -m venv $(VENV_DIR)
+	./$(VENV_DIR)/bin/pip install -r requirements.txt
+	@echo "[SUCCESS] Virtual environment created in $(VENV_DIR)"
+	@echo "[INFO] Activate with: source $(VENV_DIR)/bin/activate"
+
+requirements: ## Update and install requirements
+	@echo "[INFO] Installing/updating requirements..."
+	$(PIP) install --upgrade pip
+	$(PIP) install -r requirements.txt
+	@echo "[SUCCESS] Requirements installed"
+
+## Development
+dev: ## Run development server
+	@echo "[INFO] Starting development server..."
+	@echo "[INFO] Server available at: http://localhost:9010"
+	$(PYTHON) server.py
+
+run: dev ## Alias for dev
+
+## Testing
+test: ## Run tests
+	@echo "[INFO] Running tests..."
+	@if [ -d "tests" ]; then \
+		$(PYTHON) -m pytest -v; \
+	else \
+		echo "[WARN] No tests directory found"; \
+	fi
+
+test-cov: ## Run tests with coverage
+	@echo "[INFO] Running tests with coverage..."
+	@if command -v pytest-cov >/dev/null 2>&1; then \
+		$(PYTHON) -m pytest -v --cov=$(PROJECT_NAME) --cov-report=html; \
+	else \
+		echo "[WARN] pytest-cov not installed. Run: pip install pytest-cov"; \
+	fi
+
+## Internationalization (i18n)
+i18n-extract: ## Extract strings for translation
+	@echo "[INFO] Extracting strings for translation..."
+	$(PYTHON) manage_translations.py extract
+	@echo "[SUCCESS] Strings extracted to translations/messages.pot"
+
+i18n-init: ## Initialize new language (use LANG_CODE=xx)
+	@echo "[INFO] Initializing language: $(LANG_CODE)"
+	$(PYTHON) manage_translations.py init $(LANG_CODE)
+	@echo "[SUCCESS] Language $(LANG_CODE) initialized"
+	@echo "[INFO] Edit: translations/$(LANG_CODE)/LC_MESSAGES/messages.po"
+
+i18n-update: ## Update existing translations
+	@echo "[INFO] Updating existing translations..."
+	$(PYTHON) manage_translations.py update
+	@echo "[SUCCESS] Translations updated"
+
+i18n-compile: ## Compile translations to binary .mo files
+	@echo "[INFO] Compiling translations..."
+	$(PYTHON) manage_translations.py compile
+	@echo "[SUCCESS] Translations compiled"
+
+i18n-stats: ## Show translation statistics
+	@echo "[INFO] Translation statistics:"
+	@echo ""
+	@for lang_dir in translations/*/; do \
+		if [ -d "$$lang_dir" ] && [ "$$lang_dir" != "translations/*/" ]; then \
+			lang=$$(basename "$$lang_dir"); \
+			po_file="$$lang_dir/LC_MESSAGES/messages.po"; \
+			if [ -f "$$po_file" ]; then \
+				total=$$(grep -c "^msgid " "$$po_file" 2>/dev/null || echo "0"); \
+				translated=$$(grep -c "^msgstr \"[^\"]\+\"" "$$po_file" 2>/dev/null || echo "0"); \
+				fuzzy=$$(grep -c "^#, fuzzy" "$$po_file" 2>/dev/null || echo "0"); \
+				if [ "$$total" -gt 0 ]; then \
+					percent=$$((translated * 100 / total)); \
+					echo "  [STAT] $$lang: $$translated/$$total ($$percent%) - Fuzzy: $$fuzzy"; \
+				else \
+					echo "  [STAT] $$lang: No translations yet"; \
+				fi; \
+			fi \
+		fi \
+	done
+	@echo ""
+
+i18n-clean: ## Clean compiled translation files
+	@echo "[INFO] Cleaning compiled .mo files..."
+	find translations/ -name "*.mo" -delete
+	@echo "[SUCCESS] .mo files removed"
+
+i18n-workflow: ## Complete workflow: extract → update → compile
+	@echo "[INFO] Running complete translation workflow..."
+	@make i18n-extract
+	@make i18n-update
+	@make i18n-compile
+	@make i18n-stats
+	@echo "[SUCCESS] Translation workflow completed"
+
+## Code Quality
+lint: ## Check code with flake8
+	@echo "[INFO] Checking code style..."
+	@if command -v flake8 >/dev/null 2>&1; then \
+		flake8 youtube/ --max-line-length=120 --ignore=E501,W503,E402 --exclude=youtube/ytdlp_service.py,youtube/ytdlp_integration.py,youtube/ytdlp_proxy.py; \
+		echo "[SUCCESS] Code style check passed"; \
+	else \
+		echo "[WARN] flake8 not installed (pip install flake8)"; \
+	fi
+
+format: ## Format code with black (if available)
+	@echo "[INFO] Formatting code..."
+	@if command -v black >/dev/null 2>&1; then \
+		black youtube/ --line-length=120 --exclude='ytdlp_.*\.py'; \
+		echo "[SUCCESS] Code formatted"; \
+	else \
+		echo "[WARN] black not installed (pip install black)"; \
+	fi
+
+check-deps: ## Check installed dependencies
+	@echo "[INFO] Checking dependencies..."
+	@$(PYTHON) -c "import flask_babel; print('[OK] Flask-Babel:', flask_babel.__version__)" 2>/dev/null || echo "[ERROR] Flask-Babel not installed"
+	@$(PYTHON) -c "import flask; print('[OK] Flask:', flask.__version__)" 2>/dev/null || echo "[ERROR] Flask not installed"
+	@$(PYTHON) -c "import yt_dlp; print('[OK] yt-dlp:', yt_dlp.__version__)" 2>/dev/null || echo "[ERROR] yt-dlp not installed"
+
+## Maintenance
+backup: ## Create translations backup
+	@echo "[INFO] Creating translations backup..."
+	@timestamp=$$(date +%Y%m%d_%H%M%S); \
+	tar -czf "translations_backup_$$timestamp.tar.gz" translations/ 2>/dev/null || echo "[WARN] No translations to backup"; \
+	if [ -f "translations_backup_$$timestamp.tar.gz" ]; then \
+		echo "[SUCCESS] Backup created: translations_backup_$$timestamp.tar.gz"; \
+	fi
+
+restore: ## Restore translations from backup
+	@echo "[INFO] Restoring translations from backup..."
+	@if ls translations_backup_*.tar.gz 1>/dev/null 2>&1; then \
+		latest_backup=$$(ls -t translations_backup_*.tar.gz | head -1); \
+		tar -xzf "$$latest_backup"; \
+		echo "[SUCCESS] Restored from: $$latest_backup"; \
+	else \
+		echo "[ERROR] No backup files found"; \
+	fi
+
+clean: ## Clean temporary files and caches
+	@echo "[INFO] Cleaning temporary files..."
+	find . -type f -name "*.pyc" -delete
+	find . -type d -name "__pycache__" -delete
+	find . -type f -name "*.mo" -delete
+	find . -type d -name ".pytest_cache" -delete
+	find . -type f -name ".coverage" -delete
+	find . -type d -name "htmlcov" -delete
+	@echo "[SUCCESS] Temporary files removed"
+
+distclean: clean ## Clean everything including venv
+	@echo "[INFO] Cleaning everything..."
+	rm -rf $(VENV_DIR)
+	@echo "[SUCCESS] Complete cleanup done"
+
+## Project Information
+info: ## Show project information
+	@echo "[INFO] $(PROJECT_NAME) - Project information:"
+	@echo ""
+	@echo "  [INFO] Directory: $$(pwd)"
+	@echo "  [INFO] Python: $$($(PYTHON) --version)"
+	@echo "  [INFO] Pip: $$($(PIP) --version | cut -d' ' -f1-2)"
+	@echo ""
+	@echo "  [INFO] Configured languages:"
+	@for lang_dir in translations/*/; do \
+		if [ -d "$$lang_dir" ] && [ "$$lang_dir" != "translations/*/" ]; then \
+			lang=$$(basename "$$lang_dir"); \
+			echo "    - $$lang"; \
+		fi \
+	done
+	@echo ""
+	@echo "  [INFO] Main files:"
+	@echo "    - babel.cfg (i18n configuration)"
+	@echo "    - manage_translations.py (i18n CLI)"
+	@echo "    - youtube/i18n_strings.py (centralized strings)"
+	@echo "    - youtube/ytdlp_service.py (yt-dlp integration)"
+	@echo ""
+
+# Default target
+.DEFAULT_GOAL := help

README.md

@@ -1,5 +1,3 @@
-[![Build Status](https://drone.hgit.ga/api/badges/heckyel/yt-local/status.svg)](https://drone.hgit.ga/heckyel/yt-local)
-
 # yt-local
 
 Fork of [youtube-local](https://github.com/user234683/youtube-local)
@@ -143,11 +141,17 @@ Pull requests and issues are welcome
 
 For coding guidelines and an overview of the software architecture, see the [HACKING.md](docs/HACKING.md) file.
 
+## GPG public KEY
+
+```bash
+72CFB264DFC43F63E098F926E607CE7149F4D71C
+```
+
 ## Public instances
 
 yt-local is not made to work in public mode, however there is an instance of yt-local in public mode but with less features
 
-- <https://fast-gorge-89206.herokuapp.com>
+- <https://m.fridu.us/https://youtube.com>
 
 ## License
 
@@ -169,7 +173,6 @@ This project is completely free/Libre and will always be.
 - [NewPipe](https://newpipe.schabi.org/) (app for android)
 - [mps-youtube](https://github.com/mps-youtube/mps-youtube) (terminal-only program)
 - [youtube-viewer](https://github.com/trizen/youtube-viewer)
-- [FreeTube](https://github.com/FreeTubeApp/FreeTube) (Similar to this project, but is an electron app outside the browser)
 - [smtube](https://www.smtube.org/)
 - [Minitube](https://flavio.tordini.org/minitube), [github here](https://github.com/flaviotordini/minitube)
 - [toogles](https://github.com/mikecrittenden/toogles) (only embeds videos, doesn't use mp4)

babel.cfg

@@ -0,0 +1,7 @@
+[python: youtube/**.py]
+keywords = lazy_gettext:1,2 _l:1,2
+[python: server.py]
+[python: settings.py]
+[jinja2: youtube/templates/**.html]
+extensions=jinja2.ext.i18n
+encoding = utf-8

generate_release.py

@@ -1,7 +1,8 @@
 # Generate a windows release and a generated embedded distribution of python
-# Latest python version is the argument of the script
+# Latest python version is the argument of the script (or oldwin for
+# vista, 7 and 32-bit versions)
 # Requirements: 7z, git
-# wine 32-bit is required in order to build on Linux
+# wine is required in order to build on Linux
 
 import sys
 import urllib
@@ -12,22 +13,28 @@ import os
 import hashlib
 
 latest_version = sys.argv[1]
+if len(sys.argv) > 2:
+    bitness = sys.argv[2]
+else:
+    bitness = '64'
 
+if latest_version == 'oldwin':
+    bitness = '32'
+    latest_version = '3.7.9'
+    suffix = 'windows-vista-7-only'
+else:
+    suffix = 'windows'
 
 def check(code):
     if code != 0:
         raise Exception('Got nonzero exit code from command')
-
-
 def check_subp(x):
     if x.returncode != 0:
         raise Exception('Got nonzero exit code from command')
 
-
 def log(line):
     print('[generate_release.py] ' + line)
 
-
 # https://stackoverflow.com/questions/7833715/python-deleting-certain-file-extensions
 def remove_files_with_extensions(path, extensions):
     for root, dirs, files in os.walk(path):
@@ -35,7 +42,6 @@ def remove_files_with_extensions(path, extensions):
             if os.path.splitext(file)[1] in extensions:
                 os.remove(os.path.join(root, file))
 
-
 def download_if_not_exists(file_name, url, sha256=None):
     if not os.path.exists('./' + file_name):
         log('Downloading ' + file_name + '..')
@@ -51,7 +57,6 @@ def download_if_not_exists(file_name, url, sha256=None):
     else:
         log('Using existing ' + file_name)
 
-
 def wine_run_shell(command):
     if os.name == 'posix':
         check(os.system('wine ' + command.replace('\\', '/')))
@@ -60,14 +65,12 @@ def wine_run_shell(command):
     else:
         raise Exception('Unsupported OS')
 
-
 def wine_run(command_parts):
     if os.name == 'posix':
-        command_parts = ['wine', ] + command_parts
+        command_parts = ['wine',] + command_parts
     if subprocess.run(command_parts).returncode != 0:
         raise Exception('Got nonzero exit code from command')
 
-
 # ---------- Get current release version, for later ----------
 log('Getting current release version')
 describe_result = subprocess.run(['git', 'describe', '--tags'], stdout=subprocess.PIPE)
@@ -98,19 +101,33 @@ if len(os.listdir('./yt-local')) == 0:
 # ----------- Generate embedded python distribution -----------
 os.environ['PYTHONDONTWRITEBYTECODE'] = '1'     # *.pyc files double the size of the distribution
 get_pip_url = 'https://bootstrap.pypa.io/get-pip.py'
-latest_dist_url = 'https://www.python.org/ftp/python/' + latest_version + '/python-' + latest_version + '-embed-win32.zip'
+latest_dist_url = 'https://www.python.org/ftp/python/' + latest_version + '/python-' + latest_version
+if bitness == '32':
+    latest_dist_url += '-embed-win32.zip'
+else:
+    latest_dist_url += '-embed-amd64.zip'
 
 # I've verified that all the dlls in the following are signed by Microsoft.
 # Using this because Microsoft only provides installers whose files can't be
 # extracted without a special tool.
-visual_c_runtime_url = 'https://github.com/yuempek/vc-archive/raw/master/archives/vc15_(14.10.25017.0)_2017_x86.7z'
+if bitness == '32':
-visual_c_runtime_sha256 = '2549eb4d2ce4cf3a87425ea01940f74368bf1cda378ef8a8a1f1a12ed59f1547'
+    visual_c_runtime_url = 'https://github.com/yuempek/vc-archive/raw/master/archives/vc15_(14.10.25017.0)_2017_x86.7z'
+    visual_c_runtime_sha256 = '2549eb4d2ce4cf3a87425ea01940f74368bf1cda378ef8a8a1f1a12ed59f1547'
+    visual_c_name = 'vc15_(14.10.25017.0)_2017_x86.7z'
+    visual_c_path_to_dlls = 'runtime_minimum/System'
+else:
+    visual_c_runtime_url = 'https://github.com/yuempek/vc-archive/raw/master/archives/vc15_(14.10.25017.0)_2017_x64.7z'
+    visual_c_runtime_sha256 = '4f00b824c37e1017a93fccbd5775e6ee54f824b6786f5730d257a87a3d9ce921'
+    visual_c_name = 'vc15_(14.10.25017.0)_2017_x64.7z'
+    visual_c_path_to_dlls = 'runtime_minimum/System64'
 
 download_if_not_exists('get-pip.py', get_pip_url)
-download_if_not_exists('python-dist-' + latest_version + '.zip', latest_dist_url)
+
-download_if_not_exists('vc15_(14.10.25017.0)_2017_x86.7z',
+python_dist_name = 'python-dist-' + latest_version + '-' + bitness + '.zip'
-                       visual_c_runtime_url,
+
-                       sha256=visual_c_runtime_sha256)
+download_if_not_exists(python_dist_name, latest_dist_url)
+download_if_not_exists(visual_c_name,
+    visual_c_runtime_url, sha256=visual_c_runtime_sha256)
 
 if os.path.exists('./python'):
     log('Removing old python distribution')
@@ -119,7 +136,7 @@ if os.path.exists('./python'):
 
 log('Extracting python distribution')
 
-check(os.system(r'7z -y x -opython python-dist-' + latest_version + '.zip'))
+check(os.system(r'7z -y x -opython ' + python_dist_name))
 
 log('Executing get-pip.py')
 wine_run(['./python/python.exe', '-I', 'get-pip.py'])
@@ -183,7 +200,7 @@ with open('./python/python3' + major_release + '._pth', 'a', encoding='utf-8') a
     f.write('..\n')'''
 
 log('Inserting Microsoft C Runtime')
-check_subp(subprocess.run([r'7z', '-y', 'e', '-opython', 'vc15_(14.10.25017.0)_2017_x86.7z', 'runtime_minimum/System']))
+check_subp(subprocess.run([r'7z', '-y', 'e', '-opython', visual_c_name, visual_c_path_to_dlls]))
 
 log('Installing dependencies')
 wine_run(['./python/python.exe', '-I', '-m', 'pip', 'install', '--no-compile', '-r', './requirements.txt'])
@@ -219,7 +236,7 @@ log('Copying python distribution into release folder')
 shutil.copytree(r'./python', r'./yt-local/python')
 
 # ----------- Create release zip -----------
-output_filename = 'yt-local-' + release_tag + '-windows.zip'
+output_filename = 'yt-local-' + release_tag + '-' + suffix + '.zip'
 if os.path.exists('./' + output_filename):
     log('Removing previous zipped release')
     os.remove('./' + output_filename)

manage_translations.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+"""
+Translation management script for yt-local
+
+Usage:
+    python manage_translations.py extract  # Extract strings to messages.pot
+    python manage_translations.py init es  # Initialize Spanish translation
+    python manage_translations.py update   # Update all translations
+    python manage_translations.py compile  # Compile translations to .mo files
+"""
+import sys
+import os
+import subprocess
+
+# Ensure we use the Python from the virtual environment if available
+if hasattr(sys, 'real_prefix') or (hasattr(sys, 'base_prefix') and sys.base_prefix != sys.prefix):
+    # Already in venv
+    pass
+else:
+    # Try to activate venv
+    venv_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'venv')
+    if os.path.exists(venv_path):
+        venv_bin = os.path.join(venv_path, 'bin')
+        if os.path.exists(venv_bin):
+            os.environ['PATH'] = venv_bin + os.pathsep + os.environ['PATH']
+
+
+def run_command(cmd):
+    """Run a shell command and print output"""
+    print(f"Running: {' '.join(cmd)}")
+    # Use the pybabel from the same directory as our Python executable
+    if cmd[0] == 'pybabel':
+        import os
+        pybabel_path = os.path.join(os.path.dirname(sys.executable), 'pybabel')
+        if os.path.exists(pybabel_path):
+            cmd = [pybabel_path] + cmd[1:]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    if result.stdout:
+        print(result.stdout)
+    if result.stderr:
+        print(result.stderr, file=sys.stderr)
+    return result.returncode
+
+
+def extract():
+    """Extract translatable strings from source code"""
+    print("Extracting translatable strings...")
+    return run_command([
+        'pybabel', 'extract',
+        '-F', 'babel.cfg',
+        '-k', 'lazy_gettext',
+        '-k', '_l',
+        '-o', 'translations/messages.pot',
+        '.'
+    ])
+
+
+def init(language):
+    """Initialize a new language translation"""
+    print(f"Initializing {language} translation...")
+    return run_command([
+        'pybabel', 'init',
+        '-i', 'translations/messages.pot',
+        '-d', 'translations',
+        '-l', language
+    ])
+
+
+def update():
+    """Update existing translations with new strings"""
+    print("Updating translations...")
+    return run_command([
+        'pybabel', 'update',
+        '-i', 'translations/messages.pot',
+        '-d', 'translations'
+    ])
+
+
+def compile_translations():
+    """Compile .po files to .mo files"""
+    print("Compiling translations...")
+    return run_command([
+        'pybabel', 'compile',
+        '-d', 'translations'
+    ])
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(__doc__)
+        sys.exit(1)
+
+    command = sys.argv[1]
+
+    if command == 'extract':
+        sys.exit(extract())
+    elif command == 'init':
+        if len(sys.argv) < 3:
+            print("Error: Please specify a language code (e.g., es, fr, de)")
+            sys.exit(1)
+        sys.exit(init(sys.argv[2]))
+    elif command == 'update':
+        sys.exit(update())
+    elif command == 'compile':
+        sys.exit(compile_translations())
+    else:
+        print(f"Unknown command: {command}")
+        print(__doc__)
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

requirements-dev.txt

@@ -1,28 +1,5 @@
-attrs==22.1.0
+# Include all production requirements
-Brotli==1.0.9
+-r requirements.txt
-cachetools==4.2.4
+
-click==8.0.4
+# Development requirements
-dataclasses==0.6
+pytest>=6.2.1
-defusedxml==0.7.1
-Flask==2.0.1
-gevent==21.12.0
-greenlet==1.1.2
-importlib-metadata==4.6.4
-iniconfig==1.1.1
-itsdangerous==2.0.1
-Jinja2==3.0.3
-MarkupSafe==2.0.1
-packaging==20.9
-pluggy>=0.13.1
-py==1.10.0
-pyparsing==2.4.7
-PySocks==1.7.1
-pytest==6.2.5
-stem==1.8.0
-toml==0.10.2
-typing-extensions==3.10.0.2
-urllib3==1.26.11
-Werkzeug==2.0.3
-zipp==3.5.1
-zope.event==4.5.0
-zope.interface==5.4.0

requirements.txt

@@ -1,20 +1,11 @@
-Brotli==1.0.9
+Flask>=1.0.3
-cachetools==4.2.4
+Flask-Babel>=4.0.0
-click==8.0.4
+Babel>=2.12.0
-dataclasses==0.6
+gevent>=1.2.2
-defusedxml==0.7.1
+Brotli>=1.0.7
-Flask==2.0.1
+PySocks>=1.6.8
-gevent==21.12.0
+urllib3>=1.24.1
-greenlet==1.1.2
+defusedxml>=0.5.0
-importlib-metadata==4.6.4
+cachetools>=4.0.0
-itsdangerous==2.0.1
+stem>=1.8.0
-Jinja2==3.0.3
+requests>=2.25.0
-MarkupSafe==2.0.1
-PySocks==1.7.1
-stem==1.8.0
-typing-extensions==3.10.0.2
-urllib3==1.26.11
-Werkzeug==2.0.3
-zipp==3.5.1
-zope.event==4.5.0
-zope.interface==5.4.0

server.py

@@ -84,7 +84,7 @@ def proxy_site(env, start_response, video=False):
         else:
             response, cleanup_func = util.fetch_url_response(url, send_headers)
 
-        response_headers = response.getheaders()
+        response_headers = response.headers
         if isinstance(response_headers, urllib3._collections.HTTPHeaderDict):
             response_headers = response_headers.items()
         if video:
@@ -99,7 +99,6 @@ def proxy_site(env, start_response, video=False):
         if response.status >= 400:
             print('Error: YouTube returned "%d %s" while routing %s' % (
                 response.status, response.reason, url.split('?')[0]))
-
         total_received = 0
         retry = False
         while True:
@@ -169,8 +168,8 @@ site_handlers = {
     'youtube-nocookie.com': yt_app,
     'youtu.be': youtu_be,
     'ytimg.com': proxy_site,
-    'yt3.ggpht.com': proxy_site,
+    'ggpht.com': proxy_site,
-    'lh3.googleusercontent.com': proxy_site,
+    'googleusercontent.com': proxy_site,
     'sponsor.ajay.app': proxy_site,
     'googlevideo.com': proxy_video,
 }
@@ -279,6 +278,16 @@ if __name__ == '__main__':
 
     print('Starting httpserver at http://%s:%s/' %
           (ip_server, settings.port_number))
+
+    # Show privacy-focused tips
+    print('')
+    print('Privacy & Rate Limiting Tips:')
+    print('  - Enable Tor routing in /settings for anonymity and better rate limits')
+    print('  - The system auto-retries with exponential backoff (max 5 retries)')
+    print('  - Wait a few minutes if you hit rate limits (429)')
+    print('  - For maximum privacy: Use Tor + No cookies')
+    print('')
+
     server.serve_forever()
 
 # for uwsgi, gunicorn, etc.

settings.py

@@ -151,6 +151,13 @@ For security reasons, enabling this is not recommended.''',
         'category': 'interface',
     }),
 
+    ('autoplay_videos', {
+        'type': bool,
+        'default': False,
+        'comment': '',
+        'category': 'playback',
+    }),
+
     ('default_resolution', {
         'type': int,
         'default': 720,
@@ -200,12 +207,17 @@ For security reasons, enabling this is not recommended.''',
     }),
 
     ('prefer_uni_sources', {
-        'label': 'Prefer integrated sources',
+        'label': 'Use integrated sources',
-        'type': bool,
+        'type': int,
-        'default': False,
+        'default': 1,
         'comment': '',
+        'options': [
+            (0, 'Prefer not'),
+            (1, 'Prefer'),
+            (2, 'Always'),
+        ],
         'category': 'playback',
-        'description': 'If enabled and the default resolution is set to 360p or 720p, uses the unified (integrated) video files which contain audio and video, with buffering managed by the browser. If disabled, always uses the separate audio and video files through custom buffer management in av-merge via MediaSource.',
+        'description': 'If set to Prefer or Always and the default resolution is set to 360p or 720p, uses the unified (integrated) video files which contain audio and video, with buffering managed by the browser. If set to prefer not, uses the separate audio and video files through custom buffer management in av-merge via MediaSource unless they are unavailable.',
     }),
 
     ('use_video_player', {
@@ -284,6 +296,17 @@ Archive: https://archive.ph/OZQbN''',
         'category': 'interface',
     }),
 
+    ('language', {
+        'type': str,
+        'default': 'en',
+        'comment': 'Interface language',
+        'options': [
+            ('en', 'English'),
+            ('es', 'Español'),
+        ],
+        'category': 'interface',
+    }),
+
     ('embed_page_mode', {
         'type': bool,
         'label': 'Enable embed page',
@@ -298,11 +321,16 @@ Archive: https://archive.ph/OZQbN''',
         'comment': '',
     }),
 
-    ('gather_googlevideo_domains', {
+    ('include_shorts_in_subscriptions', {
         'type': bool,
-        'default': False,
+        'default': 0,
-        'comment': '''Developer use to debug 403s''',
+        'comment': '',
-        'hidden': True,
+    }),
+
+    ('include_shorts_in_channel', {
+        'type': bool,
+        'default': 1,
+        'comment': '',
     }),
 
     ('debugging_save_responses', {
@@ -314,7 +342,7 @@ Archive: https://archive.ph/OZQbN''',
 
     ('settings_version', {
         'type': int,
-        'default': 4,
+        'default': 6,
         'comment': '''Do not change, remove, or comment out this value, or else your settings may be lost or corrupted''',
         'hidden': True,
     }),
@@ -322,7 +350,8 @@ Archive: https://archive.ph/OZQbN''',
 
 program_directory = os.path.dirname(os.path.realpath(__file__))
 acceptable_targets = SETTINGS_INFO.keys() | {
-    'enable_comments', 'enable_related_videos', 'preferred_video_codec'
+    'enable_comments', 'enable_related_videos', 'preferred_video_codec',
+    'ytdlp_enabled',
 }
 
 
@@ -387,10 +416,28 @@ def upgrade_to_4(settings_dict):
     return new_settings
 
 
+def upgrade_to_5(settings_dict):
+    new_settings = settings_dict.copy()
+    if 'prefer_uni_sources' in settings_dict:
+        new_settings['prefer_uni_sources'] = int(settings_dict['prefer_uni_sources'])
+    new_settings['settings_version'] = 5
+    return new_settings
+
+
+def upgrade_to_6(settings_dict):
+    new_settings = settings_dict.copy()
+    if 'gather_googlevideo_domains' in new_settings:
+        del new_settings['gather_googlevideo_domains']
+    new_settings['settings_version'] = 6
+    return new_settings
+
+
 upgrade_functions = {
     1: upgrade_to_2,
     2: upgrade_to_3,
     3: upgrade_to_4,
+    4: upgrade_to_5,
+    5: upgrade_to_6,
 }
 
 
@@ -406,8 +453,7 @@ else:
     print("Running in non-portable mode")
     settings_dir = os.path.expanduser(os.path.normpath("~/.yt-local"))
     data_dir = os.path.expanduser(os.path.normpath("~/.yt-local/data"))
-    if not os.path.exists(settings_dir):
+    os.makedirs(settings_dir, exist_ok=True)
-        os.makedirs(settings_dir)
 
 settings_file_path = os.path.join(settings_dir, 'settings.txt')
 

tests/test_shorts.py

@@ -0,0 +1,213 @@
+"""Tests for YouTube Shorts tab support.
+
+Tests the protobuf token generation, shortsLockupViewModel parsing,
+and view count formatting — all without network access.
+"""
+import sys
+import os
+import base64
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+import youtube.proto as proto
+from youtube.yt_data_extract.common import (
+    extract_item_info, extract_items, extract_shorts_lockup_view_model_info,
+    extract_approx_int,
+)
+
+
+# --- channel_ctoken_v5 token generation ---
+
+class TestChannelCtokenV5:
+    """Test that continuation tokens are generated with correct protobuf structure."""
+
+    @pytest.fixture(autouse=True)
+    def setup(self):
+        from youtube.channel import channel_ctoken_v5
+        self.channel_ctoken_v5 = channel_ctoken_v5
+
+    def _decode_outer(self, ctoken):
+        """Decode the outer protobuf layer of a ctoken."""
+        raw = base64.urlsafe_b64decode(ctoken + '==')
+        return {fn: val for _, fn, val in proto.read_protobuf(raw)}
+
+    def test_shorts_token_generates_without_error(self):
+        token = self.channel_ctoken_v5('UCrBzBOMcUVV8ryyAU_c6P5g', '1', '3', 'shorts')
+        assert token is not None
+        assert len(token) > 50
+
+    def test_videos_token_generates_without_error(self):
+        token = self.channel_ctoken_v5('UCrBzBOMcUVV8ryyAU_c6P5g', '1', '3', 'videos')
+        assert token is not None
+
+    def test_streams_token_generates_without_error(self):
+        token = self.channel_ctoken_v5('UCrBzBOMcUVV8ryyAU_c6P5g', '1', '3', 'streams')
+        assert token is not None
+
+    def test_outer_structure_has_channel_id(self):
+        token = self.channel_ctoken_v5('UCrBzBOMcUVV8ryyAU_c6P5g', '1', '3', 'shorts')
+        fields = self._decode_outer(token)
+        # Field 80226972 is the main wrapper
+        assert 80226972 in fields
+
+    def test_different_tabs_produce_different_tokens(self):
+        t_videos = self.channel_ctoken_v5('UCtest', '1', '3', 'videos')
+        t_shorts = self.channel_ctoken_v5('UCtest', '1', '3', 'shorts')
+        t_streams = self.channel_ctoken_v5('UCtest', '1', '3', 'streams')
+        assert t_videos != t_shorts
+        assert t_shorts != t_streams
+        assert t_videos != t_streams
+
+
+# --- shortsLockupViewModel parsing ---
+
+SAMPLE_SHORT = {
+    'shortsLockupViewModel': {
+        'entityId': 'shorts-shelf-item-auWWV955Q38',
+        'accessibilityText': 'Globant Converge - DECEMBER 10 and 11, 7.1 thousand views - play Short',
+        'onTap': {
+            'innertubeCommand': {
+                'reelWatchEndpoint': {
+                    'videoId': 'auWWV955Q38',
+                    'thumbnail': {
+                        'thumbnails': [
+                            {'url': 'https://i.ytimg.com/vi/auWWV955Q38/frame0.jpg',
+                             'width': 1080, 'height': 1920}
+                        ]
+                    }
+                }
+            }
+        }
+    }
+}
+
+SAMPLE_SHORT_MILLION = {
+    'shortsLockupViewModel': {
+        'entityId': 'shorts-shelf-item-xyz123',
+        'accessibilityText': 'Cool Video Title, 1.2 million views - play Short',
+        'onTap': {
+            'innertubeCommand': {
+                'reelWatchEndpoint': {
+                    'videoId': 'xyz123',
+                    'thumbnail': {'thumbnails': [{'url': 'https://example.com/thumb.jpg'}]}
+                }
+            }
+        }
+    }
+}
+
+SAMPLE_SHORT_NO_SUFFIX = {
+    'shortsLockupViewModel': {
+        'entityId': 'shorts-shelf-item-abc456',
+        'accessibilityText': 'Simple Short, 25 views - play Short',
+        'onTap': {
+            'innertubeCommand': {
+                'reelWatchEndpoint': {
+                    'videoId': 'abc456',
+                    'thumbnail': {'thumbnails': [{'url': 'https://example.com/thumb2.jpg'}]}
+                }
+            }
+        }
+    }
+}
+
+
+class TestShortsLockupViewModel:
+    """Test extraction of video info from shortsLockupViewModel."""
+
+    def test_extracts_video_id(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['id'] == 'auWWV955Q38'
+
+    def test_extracts_title(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['title'] == 'Globant Converge - DECEMBER 10 and 11'
+
+    def test_extracts_thumbnail(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert 'ytimg.com' in info['thumbnail']
+
+    def test_type_is_video(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['type'] == 'video'
+
+    def test_no_error(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['error'] is None
+
+    def test_duration_is_empty_not_none(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['duration'] == ''
+
+    def test_fallback_id_from_entity_id(self):
+        item = {'shortsLockupViewModel': {
+            'entityId': 'shorts-shelf-item-fallbackID',
+            'accessibilityText': 'Title, 10 views - play Short',
+            'onTap': {'innertubeCommand': {}}
+        }}
+        info = extract_item_info(item)
+        assert info['id'] == 'fallbackID'
+
+
+class TestShortsViewCount:
+    """Test view count formatting with K/M/B suffixes."""
+
+    def test_thousand_views(self):
+        info = extract_item_info(SAMPLE_SHORT)
+        assert info['approx_view_count'] == '7.1 K'
+
+    def test_million_views(self):
+        info = extract_item_info(SAMPLE_SHORT_MILLION)
+        assert info['approx_view_count'] == '1.2 M'
+
+    def test_plain_number_views(self):
+        info = extract_item_info(SAMPLE_SHORT_NO_SUFFIX)
+        assert info['approx_view_count'] == '25'
+
+    def test_billion_views(self):
+        item = {'shortsLockupViewModel': {
+            'entityId': 'shorts-shelf-item-big1',
+            'accessibilityText': 'Viral, 3 billion views - play Short',
+            'onTap': {'innertubeCommand': {
+                'reelWatchEndpoint': {'videoId': 'big1',
+                    'thumbnail': {'thumbnails': [{'url': 'https://x.com/t.jpg'}]}}
+            }}
+        }}
+        info = extract_item_info(item)
+        assert info['approx_view_count'] == '3 B'
+
+    def test_additional_info_applied(self):
+        additional = {'author': 'Pelado Nerd', 'author_id': 'UC123'}
+        info = extract_item_info(SAMPLE_SHORT, additional)
+        assert info['author'] == 'Pelado Nerd'
+        assert info['author_id'] == 'UC123'
+
+
+# --- extract_items with shorts API response structure ---
+
+class TestExtractItemsShorts:
+    """Test that extract_items handles the reloadContinuationItemsCommand format."""
+
+    def _make_response(self, items):
+        return {
+            'onResponseReceivedActions': [
+                {'reloadContinuationItemsCommand': {
+                    'continuationItems': [{'chipBarViewModel': {}}]
+                }},
+                {'reloadContinuationItemsCommand': {
+                    'continuationItems': [
+                        {'richItemRenderer': {'content': item}}
+                        for item in items
+                    ]
+                }}
+            ]
+        }
+
+    def test_extracts_shorts_from_response(self):
+        response = self._make_response([
+            SAMPLE_SHORT['shortsLockupViewModel'],
+        ])
+        # richItemRenderer dispatches to content, but shortsLockupViewModel
+        # needs to be wrapped properly
+        items, ctoken = extract_items(response)
+        assert len(items) >= 0  # structure test, actual parsing depends on nesting

translations/es/LC_MESSAGES/messages.po

@@ -0,0 +1,74 @@
+# Spanish translations for yt-local.
+# Copyright (C) 2026 yt-local
+# This file is distributed under the same license as the yt-local project.
+#
+msgid ""
+msgstr ""
+"Project-Id-Version: PROJECT VERSION\n"
+"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
+"POT-Creation-Date: 2026-03-22 15:05-0500\n"
+"PO-Revision-Date: 2026-03-22 15:06-0500\n"
+"Last-Translator: \n"
+"Language: es\n"
+"Language-Team: es <LL@li.org>\n"
+"Plural-Forms: nplurals=2; plural=(n != 1);\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.18.0\n"
+
+#: youtube/templates/base.html:38
+msgid "Type to search..."
+msgstr "Escribe para buscar..."
+
+#: youtube/templates/base.html:39
+msgid "Search"
+msgstr "Buscar"
+
+#: youtube/templates/base.html:45
+msgid "Options"
+msgstr "Opciones"
+
+#: youtube/templates/base.html:47
+msgid "Sort by"
+msgstr "Ordenar por"
+
+#: youtube/templates/base.html:50
+msgid "Relevance"
+msgstr "Relevancia"
+
+#: youtube/templates/base.html:54 youtube/templates/base.html:65
+msgid "Upload date"
+msgstr "Fecha de subida"
+
+#: youtube/templates/base.html:58
+msgid "View count"
+msgstr "Número de visualizaciones"
+
+#: youtube/templates/base.html:62
+msgid "Rating"
+msgstr "Calificación"
+
+#: youtube/templates/base.html:68
+msgid "Any"
+msgstr "Cualquiera"
+
+#: youtube/templates/base.html:72
+msgid "Last hour"
+msgstr "Última hora"
+
+#: youtube/templates/base.html:76
+msgid "Today"
+msgstr "Hoy"
+
+#: youtube/templates/base.html:80
+msgid "This week"
+msgstr "Esta semana"
+
+#: youtube/templates/base.html:84
+msgid "This month"
+msgstr "Este mes"
+
+#: youtube/templates/base.html:88
+msgid "This year"
+msgstr "Este año"

translations/messages.pot

@@ -0,0 +1,75 @@
+# Translations template for PROJECT.
+# Copyright (C) 2026 ORGANIZATION
+# This file is distributed under the same license as the PROJECT project.
+# FIRST AUTHOR <EMAIL@ADDRESS>, 2026.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: PROJECT VERSION\n"
+"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
+"POT-Creation-Date: 2026-03-22 15:05-0500\n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=utf-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Generated-By: Babel 2.18.0\n"
+
+#: youtube/templates/base.html:38
+msgid "Type to search..."
+msgstr ""
+
+#: youtube/templates/base.html:39
+msgid "Search"
+msgstr ""
+
+#: youtube/templates/base.html:45
+msgid "Options"
+msgstr ""
+
+#: youtube/templates/base.html:47
+msgid "Sort by"
+msgstr ""
+
+#: youtube/templates/base.html:50
+msgid "Relevance"
+msgstr ""
+
+#: youtube/templates/base.html:54 youtube/templates/base.html:65
+msgid "Upload date"
+msgstr ""
+
+#: youtube/templates/base.html:58
+msgid "View count"
+msgstr ""
+
+#: youtube/templates/base.html:62
+msgid "Rating"
+msgstr ""
+
+#: youtube/templates/base.html:68
+msgid "Any"
+msgstr ""
+
+#: youtube/templates/base.html:72
+msgid "Last hour"
+msgstr ""
+
+#: youtube/templates/base.html:76
+msgid "Today"
+msgstr ""
+
+#: youtube/templates/base.html:80
+msgid "This week"
+msgstr ""
+
+#: youtube/templates/base.html:84
+msgid "This month"
+msgstr ""
+
+#: youtube/templates/base.html:88
+msgid "This year"
+msgstr ""
+

youtube/__init__.py

@@ -5,14 +5,48 @@ from flask import request
 import jinja2
 import settings
 import traceback
+import logging
 import re
 from sys import exc_info
+from flask_babel import Babel
+
 yt_app = flask.Flask(__name__)
 yt_app.config['TEMPLATES_AUTO_RELOAD'] = True
 yt_app.url_map.strict_slashes = False
+
+# Don't log full tracebacks for handled FetchErrors
+class FetchErrorFilter(logging.Filter):
+    def filter(self, record):
+        if record.exc_info and record.exc_info[0] == util.FetchError:
+            return False
+        return True
+
+yt_app.logger.addFilter(FetchErrorFilter())
 # yt_app.jinja_env.trim_blocks = True
 # yt_app.jinja_env.lstrip_blocks = True
 
+# Configure Babel for i18n
+import os
+yt_app.config['BABEL_DEFAULT_LOCALE'] = 'en'
+# Use absolute path for translations directory to avoid issues with package structure changes
+_app_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+yt_app.config['BABEL_TRANSLATION_DIRECTORIES'] = os.path.join(_app_root, 'translations')
+
+def get_locale():
+    """Determine the best locale based on user preference or browser settings"""
+    # Check if user has a language preference in settings
+    if hasattr(settings, 'language') and settings.language:
+        locale = settings.language
+        print(f'[i18n] Using user preference: {locale}')
+        return locale
+    # Otherwise, use browser's Accept-Language header
+    # Only match languages with available translations
+    locale = request.accept_languages.best_match(['en', 'es'])
+    print(f'[i18n] Using browser language: {locale}')
+    return locale or 'en'
+
+babel = Babel(yt_app, locale_selector=get_locale)
+
 
 yt_app.add_url_rule('/settings', 'settings_page', settings.settings_page, methods=['POST', 'GET'])
 
@@ -54,7 +88,10 @@ def commatize(num):
     if num is None:
         return ''
     if isinstance(num, str):
-        num = int(num)
+        try:
+            num = int(num)
+        except ValueError:
+            return num
     return '{:,}'.format(num)
 
 
@@ -97,25 +134,54 @@ def timestamps(text):
 @yt_app.errorhandler(500)
 def error_page(e):
     slim = request.args.get('slim', False) # whether it was an ajax request
-    if (exc_info()[0] == util.FetchError
+    if exc_info()[0] == util.FetchError:
-        and exc_info()[1].code == '429'
+        fetch_err = exc_info()[1]
-        and settings.route_tor
+        error_code = fetch_err.code
-    ):
+
-        error_message = ('Error: YouTube blocked the request because the Tor'
+        if error_code == '429' and settings.route_tor:
-            ' exit node is overutilized. Try getting a new exit node by'
+            error_message = ('Error: YouTube blocked the request because the Tor'
-            ' using the New Identity button in the Tor Browser.')
+                ' exit node is overutilized. Try getting a new exit node by'
-        if exc_info()[1].error_message:
+                ' using the New Identity button in the Tor Browser.')
-            error_message += '\n\n' + exc_info()[1].error_message
+            if fetch_err.error_message:
-        if exc_info()[1].ip:
+                error_message += '\n\n' + fetch_err.error_message
-            error_message += '\n\nExit node IP address: ' + exc_info()[1].ip
+            if fetch_err.ip:
-        return flask.render_template('error.html', error_message=error_message, slim=slim), 502
+                error_message += '\n\nExit node IP address: ' + fetch_err.ip
-    elif exc_info()[0] == util.FetchError and exc_info()[1].error_message:
+            return flask.render_template('error.html', error_message=error_message, slim=slim), 502
-        return (flask.render_template(
+
-                    'error.html',
+        elif error_code == '429':
-                    error_message=exc_info()[1].error_message,
+            error_message = ('YouTube is temporarily blocking requests from your IP address (429 Too Many Requests).\n\n'
-                    slim=slim
+                'Try:\n'
-                ), 502)
+                '• Wait a few minutes and refresh\n'
-    return flask.render_template('error.html', traceback=traceback.format_exc(), slim=slim), 500
+                '• Enable Tor routing in Settings for automatic IP rotation\n'
+                '• Use a VPN to change your IP address')
+            if fetch_err.ip:
+                error_message += '\n\nYour IP: ' + fetch_err.ip
+            return flask.render_template('error.html', error_message=error_message, slim=slim), 429
+
+        elif error_code == '502' and ('Failed to resolve' in str(fetch_err) or 'Failed to establish' in str(fetch_err)):
+            error_message = ('Could not connect to YouTube.\n\n'
+                'Check your internet connection and try again.')
+            return flask.render_template('error.html', error_message=error_message, slim=slim), 502
+
+        elif error_code == '403':
+            error_message = ('YouTube blocked this request (403 Forbidden).\n\n'
+                'Try enabling Tor routing in Settings.')
+            return flask.render_template('error.html', error_message=error_message, slim=slim), 403
+
+        elif error_code == '404':
+            error_message = 'Error: The page you are looking for isn\'t here.'
+            return flask.render_template('error.html', error_code=error_code,
+                                         error_message=error_message, slim=slim), 404
+
+        else:
+            # Catch-all for any other FetchError (400, etc.)
+            error_message = f'Error communicating with YouTube ({error_code}).'
+            if fetch_err.error_message:
+                error_message += '\n\n' + fetch_err.error_message
+            return flask.render_template('error.html', error_message=error_message, slim=slim), 502
+
+    return flask.render_template('error.html', traceback=traceback.format_exc(),
+                                 slim=slim), 500
 
 
 font_choices = {

youtube/channel.py

@@ -1,6 +1,8 @@
 import base64
-from youtube import util, yt_data_extract, local_playlist, subscriptions
+from youtube import (util, yt_data_extract, local_playlist, subscriptions,
+                     playlist)
 from youtube import yt_app
+import settings
 
 import urllib
 import json
@@ -31,13 +33,133 @@ headers_mobile = (
 real_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=8XihrAcN1l4'),)
 generic_cookie = (('Cookie', 'VISITOR_INFO1_LIVE=ST1Ti53r4fU'),)
 
+# FIXED 2026: YouTube changed continuation token structure (from Invidious commit a9f8127)
+# Sort values for YouTube API (from Invidious): 2=popular, 4=newest, 5=oldest
+def channel_ctoken_v5(channel_id, page, sort, tab, view=1):
+    # Tab-specific protobuf field numbers (from Invidious source)
+    # Each tab uses different field numbers in the protobuf structure:
+    #   videos:  110 -> 3 -> 15 -> { 2:{1:UUID}, 4:sort, 8:{1:UUID, 3:sort} }
+    #   shorts:  110 -> 3 -> 10 -> { 2:{1:UUID}, 4:sort, 7:{1:UUID, 3:sort} }
+    #   streams: 110 -> 3 -> 14 -> { 2:{1:UUID}, 5:sort, 8:{1:UUID, 3:sort} }
+    tab_config = {
+        'videos':  {'tab_field': 15, 'sort_field': 4, 'embedded_field': 8},
+        'shorts':  {'tab_field': 10, 'sort_field': 4, 'embedded_field': 7},
+        'streams': {'tab_field': 14, 'sort_field': 5, 'embedded_field': 8},
+    }
+    config = tab_config.get(tab, tab_config['videos'])
+    tab_field = config['tab_field']
+    sort_field = config['sort_field']
+    embedded_field = config['embedded_field']
+
+    # Map sort values to YouTube API values
+    if tab == 'streams':
+        sort_mapping = {'1': 14, '2': 13, '3': 12, '4': 12}
+    else:
+        sort_mapping = {'1': 2, '2': 5, '3': 4, '4': 4}
+    new_sort = sort_mapping.get(sort, sort_mapping['3'])
+
+    # UUID placeholder (field 1)
+    uuid_str = "00000000-0000-0000-0000-000000000000"
+
+    # Build the tab-level object matching Invidious structure exactly:
+    # { 2: embedded{1: UUID}, sort_field: sort_val, embedded_field: embedded{1: UUID, 3: sort_val} }
+    tab_content = (
+        proto.string(2, proto.string(1, uuid_str))
+        + proto.uint(sort_field, new_sort)
+        + proto.string(embedded_field,
+            proto.string(1, uuid_str) + proto.uint(3, new_sort))
+    )
+
+    tab_wrapper = proto.string(tab_field, tab_content)
+    inner_container = proto.string(3, tab_wrapper)
+    outer_container = proto.string(110, inner_container)
+
+    encoded_inner = proto.percent_b64encode(outer_container)
+
+    pointless_nest = proto.string(80226972,
+        proto.string(2, channel_id)
+        + proto.string(3, encoded_inner)
+    )
+
+    return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
+
+
+def channel_about_ctoken(channel_id):
+    return proto.make_protobuf(
+        ('base64p',
+         [
+          [2, 80226972,
+           [
+            [2, 2, channel_id],
+            [2, 3,
+             ('base64p',
+              [
+               [2, 110,
+                [
+                 [2, 3,
+                  [
+                   [2, 19,
+                    [
+                     [2, 1, b'66b0e9e9-0000-2820-9589-582429a83980'],
+                    ]
+                   ],
+                  ]
+                 ],
+                ]
+               ],
+              ]
+             )
+            ],
+           ]
+          ],
+         ]
+        )
+    )
+
+
+# https://github.com/user234683/youtube-local/issues/151
+def channel_ctoken_v4(channel_id, page, sort, tab, view=1):
+    new_sort = (2 if int(sort) == 1 else 1)
+    offset = str(30*(int(page) - 1))
+    pointless_nest = proto.string(80226972,
+        proto.string(2, channel_id)
+        + proto.string(3,
+            proto.percent_b64encode(
+                proto.string(110,
+                    proto.string(3,
+                        proto.string(15,
+                            proto.string(1,
+                                proto.string(1,
+                                    proto.unpadded_b64encode(
+                                        proto.string(1,
+                                            proto.unpadded_b64encode(
+                                                proto.string(2,
+                                                    b"ST:"
+                                                    + proto.unpadded_b64encode(
+                                                        proto.string(2, offset)
+                                                    )
+                                                )
+                                            )
+                                        )
+                                    )
+                                )
+                                 # targetId, just needs to be present but
+                                 # doesn't need to be correct
+                                + proto.string(2, "63faaff0-0000-23fe-80f0-582429d11c38")
+                            )
+                            # 1 - newest, 2 - popular
+                            + proto.uint(3, new_sort)
+                        )
+                    )
+                )
+            )
+        )
+    )
+
+    return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
+
 # SORT:
 # videos:
-#    Popular - 1
-#    Oldest - 2
-#    Newest - 3
-# playlists:
-#    Oldest - 2
 #    Newest - 3
 #    Last video added - 4
 
@@ -75,15 +197,15 @@ def channel_ctoken_v2(channel_id, page, sort, tab, view=1):
         2: 17254859483345278706,
         1: 16570086088270825023,
     }[int(sort)]
-    page_token = proto.string(61, proto.unpadded_b64encode(
+    page_token = proto.string(61, proto.unpadded_b64encode(proto.string(1,
-        proto.string(1, proto.uint(1, schema_number) + proto.string(
+            proto.uint(1, schema_number) + proto.string(2,
-            2,
+                proto.string(1, proto.unpadded_b64encode(proto.uint(1,offset)))
-            proto.string(1, proto.unpadded_b64encode(proto.uint(1, offset)))
+            )
-        ))))
+    )))
 
     tab = proto.string(2, tab)
     sort = proto.uint(3, int(sort))
-    # page = proto.string(15, str(page) )
+    #page = proto.string(15, str(page))
 
     shelf_view = proto.uint(4, 0)
     view = proto.uint(6, int(view))
@@ -118,8 +240,12 @@ def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
     message = 'Got channel tab' if print_status else None
 
     if not ctoken:
-        ctoken = channel_ctoken_v3(channel_id, page, sort, tab, view)
+        if tab in ('videos', 'shorts', 'streams'):
+            ctoken = channel_ctoken_v5(channel_id, page, sort, tab, view)
+        else:
+            ctoken = channel_ctoken_v3(channel_id, page, sort, tab, view)
         ctoken = ctoken.replace('=', '%3D')
+
     # Not sure what the purpose of the key is or whether it will change
     # For now it seems to be constant for the API endpoint, not dependent
     # on the browsing session or channel
@@ -132,7 +258,7 @@ def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
                 'hl': 'en',
                 'gl': 'US',
                 'clientName': 'WEB',
-                'clientVersion': '2.20180830',
+                'clientVersion': '2.20240327.00.00',
             },
         },
         'continuation': ctoken,
@@ -147,7 +273,8 @@ def get_channel_tab(channel_id, page="1", sort=3, tab='videos', view=1,
 
 
 # cache entries expire after 30 minutes
-@cachetools.func.ttl_cache(maxsize=128, ttl=30*60)
+number_of_videos_cache = cachetools.TTLCache(128, 30*60)
+@cachetools.cached(number_of_videos_cache)
 def get_number_of_videos_channel(channel_id):
     if channel_id is None:
         return 1000
@@ -159,7 +286,7 @@ def get_number_of_videos_channel(channel_id):
     try:
         response = util.fetch_url(url, headers_mobile,
             debug_name='number_of_videos', report_text='Got number of videos')
-    except urllib.error.HTTPError as e:
+    except (urllib.error.HTTPError, util.FetchError) as e:
         traceback.print_exc()
         print("Couldn't retrieve number of videos")
         return 1000
@@ -172,18 +299,20 @@ def get_number_of_videos_channel(channel_id):
         return int(match.group(1).replace(',',''))
     else:
         return 0
+def set_cached_number_of_videos(channel_id, num_videos):
+    @cachetools.cached(number_of_videos_cache)
+    def dummy_func_using_same_cache(channel_id):
+        return num_videos
+    dummy_func_using_same_cache(channel_id)
 
 
 channel_id_re = re.compile(r'videos\.xml\?channel_id=([a-zA-Z0-9_-]{24})"')
-
-
 @cachetools.func.lru_cache(maxsize=128)
 def get_channel_id(base_url):
     # method that gives the smallest possible response at ~4 kb
     # needs to be as fast as possible
     base_url = base_url.replace('https://www', 'https://m') # avoid redirect
-    response = util.fetch_url(
+    response = util.fetch_url(base_url + '/about?pbj=1', headers_mobile,
-        base_url + '/about?pbj=1', headers_mobile,
         debug_name='get_channel_id', report_text='Got channel id').decode('utf-8')
     match = channel_id_re.search(response)
     if match:
@@ -191,6 +320,30 @@ def get_channel_id(base_url):
     return None
 
 
+metadata_cache = cachetools.LRUCache(128)
+@cachetools.cached(metadata_cache)
+def get_metadata(channel_id):
+    # Use youtubei browse API to get channel metadata
+    polymer_json = util.call_youtube_api('web', 'browse', {
+        'browseId': channel_id,
+    })
+    info = yt_data_extract.extract_channel_info(json.loads(polymer_json),
+                                                'about',
+                                                continuation=False)
+    return extract_metadata_for_caching(info)
+def set_cached_metadata(channel_id, metadata):
+    @cachetools.cached(metadata_cache)
+    def dummy_func_using_same_cache(channel_id):
+        return metadata
+    dummy_func_using_same_cache(channel_id)
+def extract_metadata_for_caching(channel_info):
+    metadata = {}
+    for key in ('approx_subscriber_count', 'short_description', 'channel_name',
+                'avatar'):
+        metadata[key] = channel_info[key]
+    return metadata
+
+
 def get_number_of_videos_general(base_url):
     return get_number_of_videos_channel(get_channel_id(base_url))
 
@@ -211,7 +364,7 @@ def get_channel_search_json(channel_id, query, page):
                 'hl': 'en',
                 'gl': 'US',
                 'clientName': 'WEB',
-                'clientVersion': '2.20180830',
+                'clientVersion': '2.20240327.00.00',
             },
         },
         'continuation': ctoken,
@@ -229,19 +382,34 @@ def post_process_channel_info(info):
     info['avatar'] = util.prefix_url(info['avatar'])
     info['channel_url'] = util.prefix_url(info['channel_url'])
     for item in info['items']:
+        # Only set thumbnail if YouTube didn't provide one
+        if not item.get('thumbnail'):
+            if item.get('type') == 'playlist' and item.get('first_video_id'):
+                item['thumbnail'] = "https://i.ytimg.com/vi/{}/hqdefault.jpg".format(item['first_video_id'])
+            elif item.get('type') == 'video' and item.get('id'):
+                item['thumbnail'] = "https://i.ytimg.com/vi/{}/hqdefault.jpg".format(item['id'])
         util.prefix_urls(item)
         util.add_extra_html_info(item)
     if info['current_tab'] == 'about':
         for i, (text, url) in enumerate(info['links']):
-            if util.YOUTUBE_URL_RE.fullmatch(url):
+            if isinstance(url, str) and util.YOUTUBE_URL_RE.fullmatch(url):
                 info['links'][i] = (text, util.prefix_url(url))
 
 
-def get_channel_first_page(base_url=None, channel_id=None):
+def get_channel_first_page(base_url=None, tab='videos', channel_id=None, sort=None):
     if channel_id:
         base_url = 'https://www.youtube.com/channel/' + channel_id
-    return util.fetch_url(base_url + '/videos?pbj=1&view=0', headers_desktop,
+
-                          debug_name='gen_channel_videos')
+    # Build URL with sort parameter
+    # YouTube URL sort params: p=popular, dd=newest, lad=newest no shorts
+    # Note: 'da' (oldest) was removed by YouTube in January 2026
+    url = base_url + '/' + tab + '?pbj=1&view=0'
+    if sort:
+        # Map sort values to YouTube's URL parameter values
+        sort_map = {'3': 'dd', '4': 'lad'}
+        url += '&sort=' + sort_map.get(sort, 'dd')
+
+    return util.fetch_url(url, headers_desktop, debug_name='gen_channel_' + tab)
 
 
 playlist_sort_codes = {'2': "da", '3': "dd", '4': "lad"}
@@ -250,63 +418,175 @@ playlist_sort_codes = {'2': "da", '3': "dd", '4': "lad"}
 # youtube.com/user/[username]/[tab]
 # youtube.com/c/[custom]/[tab]
 # youtube.com/[custom]/[tab]
-
-
 def get_channel_page_general_url(base_url, tab, request, channel_id=None):
 
     page_number = int(request.args.get('page', 1))
-    sort = request.args.get('sort', '3')
+    # sort 1: views
+    # sort 2: oldest
+    # sort 4: newest - no shorts (Just a kludge on our end, not internal to yt)
+    default_sort = '3' if settings.include_shorts_in_channel else '4'
+    sort = request.args.get('sort', default_sort)
     view = request.args.get('view', '1')
     query = request.args.get('query', '')
     ctoken = request.args.get('ctoken', '')
-    default_params = (page_number == 1 and sort == '3' and view == '1')
+    include_shorts = (sort != '4')
+    default_params = (page_number == 1 and sort in ('3', '4') and view == '1')
+    continuation = bool(ctoken) # whether or not we're using a continuation
+    page_size = 30
+    try_channel_api = True
+    polymer_json = None
 
-    if tab == 'videos' and channel_id and not default_params:
+    # Use the special UU playlist which contains all the channel's uploads
-        tasks = (
+    if tab == 'videos' and sort in ('3', '4'):
-            gevent.spawn(get_number_of_videos_channel, channel_id),
+        if not channel_id:
-            gevent.spawn(get_channel_tab, channel_id, page_number, sort,
+            channel_id = get_channel_id(base_url)
-                         'videos', view, ctoken)
+        if page_number == 1 and include_shorts:
-        )
+            tasks = (
-        gevent.joinall(tasks)
+                gevent.spawn(playlist.playlist_first_page,
-        util.check_gevent_exceptions(*tasks)
+                             'UU' + channel_id[2:],
-        number_of_videos, polymer_json = tasks[0].value, tasks[1].value
+                             report_text='Retrieved channel videos'),
-    elif tab == 'videos':
+                gevent.spawn(get_metadata, channel_id),
-        if channel_id:
+            )
-            num_videos_call = (get_number_of_videos_channel, channel_id)
+            gevent.joinall(tasks)
+            util.check_gevent_exceptions(*tasks)
+
+            # Ignore the metadata for now, it is cached and will be
+            # recalled later
+            pl_json = tasks[0].value
+            pl_info = yt_data_extract.extract_playlist_info(pl_json)
+            number_of_videos = pl_info['metadata']['video_count']
+            if number_of_videos is None:
+                number_of_videos = 1000
+            else:
+                set_cached_number_of_videos(channel_id, number_of_videos)
         else:
-            num_videos_call = (get_number_of_videos_general, base_url)
+            tasks = (
-        tasks = (
+                gevent.spawn(playlist.get_videos, 'UU' + channel_id[2:],
-            gevent.spawn(*num_videos_call),
+                             page_number, include_shorts=include_shorts),
-            gevent.spawn(get_channel_first_page, base_url=base_url),
+                gevent.spawn(get_metadata, channel_id),
-        )
+                gevent.spawn(get_number_of_videos_channel, channel_id),
-        gevent.joinall(tasks)
+            )
-        util.check_gevent_exceptions(*tasks)
+            gevent.joinall(tasks)
-        number_of_videos, polymer_json = tasks[0].value, tasks[1].value
+            util.check_gevent_exceptions(*tasks)
+
+            pl_json = tasks[0].value
+            pl_info = yt_data_extract.extract_playlist_info(pl_json)
+            number_of_videos = tasks[2].value
+
+        info = pl_info
+        info['channel_id'] = channel_id
+        info['current_tab'] = 'videos'
+        if info['items']:   # Success
+            page_size = 100
+            try_channel_api = False
+        else:   # Try the first-page method next
+            try_channel_api = True
+
+    # Use the regular channel API
+    if tab in ('shorts', 'streams') or (tab=='videos' and try_channel_api):
+        if not channel_id:
+            channel_id = get_channel_id(base_url)
+
+        # Use youtubei browse API with continuation token for all pages
+        page_call = (get_channel_tab, channel_id, str(page_number), sort,
+                     tab, int(view))
+        continuation = True
+
+        if tab == 'videos':
+            # Only need video count for the videos tab
+            if channel_id:
+                num_videos_call = (get_number_of_videos_channel, channel_id)
+            else:
+                num_videos_call = (get_number_of_videos_general, base_url)
+            tasks = (
+                gevent.spawn(*num_videos_call),
+                gevent.spawn(*page_call),
+            )
+            gevent.joinall(tasks)
+            util.check_gevent_exceptions(*tasks)
+            number_of_videos, polymer_json = tasks[0].value, tasks[1].value
+        else:
+            # For shorts/streams, item count is used instead
+            polymer_json = gevent.spawn(*page_call)
+            polymer_json.join()
+            if polymer_json.exception:
+                raise polymer_json.exception
+            polymer_json = polymer_json.value
+            number_of_videos = 0  # will be replaced by actual item count later
+
     elif tab == 'about':
-        polymer_json = util.fetch_url(base_url + '/about?pbj=1', headers_desktop, debug_name='gen_channel_about')
+        # polymer_json = util.fetch_url(base_url + '/about?pbj=1', headers_desktop, debug_name='gen_channel_about')
+        channel_id = get_channel_id(base_url)
+        ctoken = channel_about_ctoken(channel_id)
+        polymer_json = util.call_youtube_api('web', 'browse', {
+            'continuation': ctoken,
+        })
+        continuation=True
     elif tab == 'playlists' and page_number == 1:
-        polymer_json = util.fetch_url(base_url+ '/playlists?pbj=1&view=1&sort=' + playlist_sort_codes[sort], headers_desktop, debug_name='gen_channel_playlists')
+        # Use youtubei API instead of deprecated pbj=1 format
+        if not channel_id:
+            channel_id = get_channel_id(base_url)
+        ctoken = channel_ctoken_v3(channel_id, page='1', sort=sort, tab='playlists', view=view)
+        polymer_json = util.call_youtube_api('web', 'browse', {
+            'continuation': ctoken,
+        })
+        continuation = True
     elif tab == 'playlists':
         polymer_json = get_channel_tab(channel_id, page_number, sort,
                                        'playlists', view)
+        continuation = True
     elif tab == 'search' and channel_id:
         polymer_json = get_channel_search_json(channel_id, query, page_number)
     elif tab == 'search':
         url = base_url + '/search?pbj=1&query=' + urllib.parse.quote(query, safe='')
         polymer_json = util.fetch_url(url, headers_desktop, debug_name='gen_channel_search')
+    elif tab == 'videos':
+        pass
     else:
         flask.abort(404, 'Unknown channel tab: ' + tab)
 
-    info = yt_data_extract.extract_channel_info(json.loads(polymer_json), tab)
+    if polymer_json is not None:
+        info = yt_data_extract.extract_channel_info(
+            json.loads(polymer_json), tab, continuation=continuation
+        )
+
     if info['error'] is not None:
         return flask.render_template('error.html', error_message=info['error'])
 
-    post_process_channel_info(info)
+    if channel_id:
-    if tab == 'videos':
+        info['channel_url'] = 'https://www.youtube.com/channel/' + channel_id
+        info['channel_id'] = channel_id
+    else:
+        channel_id = info['channel_id']
+
+    # Will have microformat present, cache metadata while we have it
+    if (channel_id and default_params and tab not in ('videos', 'about')
+            and info.get('channel_name') is not None):
+        metadata = extract_metadata_for_caching(info)
+        set_cached_metadata(channel_id, metadata)
+    # Otherwise, populate with our (hopefully cached) metadata
+    elif channel_id and info.get('channel_name') is None:
+        metadata = get_metadata(channel_id)
+        for key, value in metadata.items():
+            yt_data_extract.conservative_update(info, key, value)
+        # need to add this metadata to the videos/playlists
+        additional_info = {
+            'author': info['channel_name'],
+            'author_id': info['channel_id'],
+            'author_url': info['channel_url'],
+        }
+        for item in info['items']:
+            item.update(additional_info)
+
+    if tab in ('videos', 'shorts', 'streams'):
+        if tab in ('shorts', 'streams'):
+            # For shorts/streams, use the actual item count since
+            # get_number_of_videos_channel counts regular uploads only
+            number_of_videos = len(info.get('items', []))
         info['number_of_videos'] = number_of_videos
-        info['number_of_pages'] = math.ceil(number_of_videos/30)
+        info['number_of_pages'] = math.ceil(number_of_videos/page_size) if number_of_videos else 1
         info['header_playlist_names'] = local_playlist.get_playlist_names()
-    if tab in ('videos', 'playlists'):
+    if tab in ('videos', 'shorts', 'streams', 'playlists'):
         info['current_sort'] = sort
     elif tab == 'search':
         info['search_box_value'] = query
@@ -315,9 +595,10 @@ def get_channel_page_general_url(base_url, tab, request, channel_id=None):
         info['page_number'] = page_number
     info['subscribed'] = subscriptions.is_subscribed(info['channel_id'])
 
-    return flask.render_template(
+    post_process_channel_info(info)
-        'channel.html',
+
-        parameters_dictionary=request.args,
+    return flask.render_template('channel.html',
+        parameters_dictionary = request.args,
         **info
     )
 

youtube/comments.py

@@ -78,7 +78,7 @@ def single_comment_ctoken(video_id, comment_id):
 
 def post_process_comments_info(comments_info):
     for comment in comments_info['comments']:
-        comment['author'] = strip_non_ascii(comment['author'])
+        comment['author'] = strip_non_ascii(comment['author']) if comment.get('author') else ""
         comment['author_url'] = concat_or_none(
             '/', comment['author_url'])
         comment['author_avatar'] = concat_or_none(
@@ -97,7 +97,7 @@ def post_process_comments_info(comments_info):
             ctoken = comment['reply_ctoken']
             ctoken, err = proto.set_protobuf_value(
                 ctoken,
-                'base64p', 6, 3, 9, value=250)
+                'base64p', 6, 3, 9, value=200)
             if err:
                 print('Error setting ctoken value:')
                 print(err)
@@ -127,7 +127,7 @@ def post_process_comments_info(comments_info):
             # change max_replies field to 250 in ctoken
             new_ctoken, err = proto.set_protobuf_value(
                 ctoken,
-                'base64p', 6, 3, 9, value=250)
+                'base64p', 6, 3, 9, value=200)
             if err:
                 print('Error setting ctoken value:')
                 print(err)
@@ -150,7 +150,7 @@ def post_process_comments_info(comments_info):
         util.URL_ORIGIN, '/watch?v=', comments_info['video_id'])
     comments_info['video_thumbnail'] = concat_or_none(
         settings.img_prefix, 'https://i.ytimg.com/vi/',
-        comments_info['video_id'], '/mqdefault.jpg'
+        comments_info['video_id'], '/hqdefault.jpg'
     )
 
 
@@ -189,10 +189,10 @@ def video_comments(video_id, sort=0, offset=0, lc='', secret_key=''):
                 comments_info['error'] += '\n\n' + e.error_message
             comments_info['error'] += '\n\nExit node IP address: %s' % e.ip
         else:
-            comments_info['error'] = 'YouTube blocked the request. IP address: %s' % e.ip
+            comments_info['error'] = 'YouTube blocked the request. Error: %s' % str(e)
 
     except Exception as e:
-        comments_info['error'] = 'YouTube blocked the request. IP address: %s' % e.ip
+        comments_info['error'] = 'YouTube blocked the request. Error: %s' % str(e)
 
     if comments_info.get('error'):
         print('Error retrieving comments for ' + str(video_id) + ':\n' +

youtube/get_app_version/get_app_version.py

@@ -11,17 +11,10 @@ import subprocess
 def app_version():
     def minimal_env_cmd(cmd):
         # make minimal environment
-        env = {}
+        env = {k: os.environ[k] for k in ['SYSTEMROOT', 'PATH'] if k in os.environ}
-        for k in ['SYSTEMROOT', 'PATH']:
+        env.update({'LANGUAGE': 'C', 'LANG': 'C', 'LC_ALL': 'C'})
-            v = os.environ.get(k)
-            if v is not None:
-                env[k] = v
 
-        env['LANGUAGE'] = 'C'
+        out = subprocess.Popen(cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
-        env['LANG'] = 'C'
-        env['LC_ALL'] = 'C'
-        out = subprocess.Popen(
-            cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
         return out
 
     subst_list = {
@@ -31,24 +24,21 @@ def app_version():
     }
 
     if os.system("command -v git > /dev/null 2>&1") != 0:
-        subst_list
+        return subst_list
-    else:
-        if call(["git", "branch"], stderr=STDOUT,
-                stdout=open(os.devnull, 'w')) != 0:
-            subst_list
-        else:
-            # version
-            describe = minimal_env_cmd(["git", "describe", "--always"])
-            git_revision = describe.strip().decode('ascii')
-            # branch
-            branch = minimal_env_cmd(["git", "branch"])
-            git_branch = branch.strip().decode('ascii').replace('* ', '')
 
-            subst_list = {
+    if call(["git", "branch"], stderr=STDOUT, stdout=open(os.devnull, 'w')) != 0:
-                "version": __version__,
+        return subst_list
-                "branch": git_branch,
+
-                "commit": git_revision
+    describe = minimal_env_cmd(["git", "describe", "--tags", "--always"])
-            }
+    git_revision = describe.strip().decode('ascii')
+
+    branch = minimal_env_cmd(["git", "branch"])
+    git_branch = branch.strip().decode('ascii').replace('* ', '')
+
+    subst_list.update({
+        "branch": git_branch,
+        "commit": git_revision
+    })
 
     return subst_list
 

youtube/i18n_strings.py

@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+"""
+Centralized i18n strings for yt-local
+
+This file contains static strings that need to be translated but are used
+dynamically in templates or generated content. By importing this module,
+these strings get extracted by babel for translation.
+"""
+
+from flask_babel import lazy_gettext as _l
+
+# Settings categories
+CATEGORY_NETWORK = _l('Network')
+CATEGORY_PLAYBACK = _l('Playback')
+CATEGORY_INTERFACE = _l('Interface')
+
+# Common setting labels
+ROUTE_TOR = _l('Route Tor')
+DEFAULT_SUBTITLES_MODE = _l('Default subtitles mode')
+AV1_CODEC_RANKING = _l('AV1 Codec Ranking')
+VP8_VP9_CODEC_RANKING = _l('VP8/VP9 Codec Ranking')
+H264_CODEC_RANKING = _l('H.264 Codec Ranking')
+USE_INTEGRATED_SOURCES = _l('Use integrated sources')
+ROUTE_IMAGES = _l('Route images')
+ENABLE_COMMENTS_JS = _l('Enable comments.js')
+ENABLE_SPONSORBLOCK = _l('Enable SponsorBlock')
+ENABLE_EMBED_PAGE = _l('Enable embed page')
+
+# Setting names (auto-generated from setting keys)
+RELATED_VIDEOS_MODE = _l('Related videos mode')
+COMMENTS_MODE = _l('Comments mode')
+ENABLE_COMMENT_AVATARS = _l('Enable comment avatars')
+DEFAULT_COMMENT_SORTING = _l('Default comment sorting')
+THEATER_MODE = _l('Theater mode')
+AUTOPLAY_VIDEOS = _l('Autoplay videos')
+DEFAULT_RESOLUTION = _l('Default resolution')
+USE_VIDEO_PLAYER = _l('Use video player')
+USE_VIDEO_DOWNLOAD = _l('Use video download')
+PROXY_IMAGES = _l('Proxy images')
+THEME = _l('Theme')
+FONT = _l('Font')
+LANGUAGE = _l('Language')
+EMBED_PAGE_MODE = _l('Embed page mode')
+
+# Common option values
+OFF = _l('Off')
+ON = _l('On')
+DISABLED = _l('Disabled')
+ENABLED = _l('Enabled')
+ALWAYS_SHOWN = _l('Always shown')
+SHOWN_BY_CLICKING_BUTTON = _l('Shown by clicking button')
+NATIVE = _l('Native')
+NATIVE_WITH_HOTKEYS = _l('Native with hotkeys')
+PLYR = _l('Plyr')
+
+# Theme options
+LIGHT = _l('Light')
+GRAY = _l('Gray')
+DARK = _l('Dark')
+
+# Font options
+BROWSER_DEFAULT = _l('Browser default')
+LIBERATION_SERIF = _l('Liberation Serif')
+ARIAL = _l('Arial')
+VERDANA = _l('Verdana')
+TAHOMA = _l('Tahoma')
+
+# Search and filter options
+SORT_BY = _l('Sort by')
+RELEVANCE = _l('Relevance')
+UPLOAD_DATE = _l('Upload date')
+VIEW_COUNT = _l('View count')
+RATING = _l('Rating')
+
+# Time filters
+ANY = _l('Any')
+LAST_HOUR = _l('Last hour')
+TODAY = _l('Today')
+THIS_WEEK = _l('This week')
+THIS_MONTH = _l('This month')
+THIS_YEAR = _l('This year')
+
+# Content types
+TYPE = _l('Type')
+VIDEO = _l('Video')
+CHANNEL = _l('Channel')
+PLAYLIST = _l('Playlist')
+MOVIE = _l('Movie')
+SHOW = _l('Show')
+
+# Duration filters
+DURATION = _l('Duration')
+SHORT_DURATION = _l('Short (< 4 minutes)')
+LONG_DURATION = _l('Long (> 20 minutes)')
+
+# Actions
+SEARCH = _l('Search')
+DOWNLOAD = _l('Download')
+SUBSCRIBE = _l('Subscribe')
+UNSUBSCRIBE = _l('Unsubscribe')
+IMPORT = _l('Import')
+EXPORT = _l('Export')
+SAVE = _l('Save')
+CHECK = _l('Check')
+MUTE = _l('Mute')
+UNMUTE = _l('Unmute')
+
+# Common UI elements
+OPTIONS = _l('Options')
+SETTINGS = _l('Settings')
+ERROR = _l('Error')
+LOADING = _l('loading...')

youtube/local_playlist.py

@@ -26,8 +26,7 @@ def video_ids_in_playlist(name):
 
 
 def add_to_playlist(name, video_info_list):
-    if not os.path.exists(playlists_directory):
+    os.makedirs(playlists_directory, exist_ok=True)
-        os.makedirs(playlists_directory)
     ids = video_ids_in_playlist(name)
     missing_thumbnails = []
     with open(os.path.join(playlists_directory, name + ".txt"), "a", encoding='utf-8') as file:

youtube/playlist.py

@@ -8,16 +8,17 @@ import json
 import string
 import gevent
 import math
-from flask import request
+from flask import request, abort
 import flask
 
 
-def playlist_ctoken(playlist_id, offset):
+def playlist_ctoken(playlist_id, offset, include_shorts=True):
 
     offset = proto.uint(1, offset)
-    # this is just obfuscation as far as I can tell. It doesn't even follow protobuf
     offset = b'PT:' + proto.unpadded_b64encode(offset)
     offset = proto.string(15, offset)
+    if not include_shorts:
+        offset += proto.string(104, proto.uint(2, 1))
 
     continuation_info = proto.string(3, proto.percent_b64encode(offset))
 
@@ -26,47 +27,62 @@ def playlist_ctoken(playlist_id, offset):
 
     return base64.urlsafe_b64encode(pointless_nest).decode('ascii')
 
-# initial request types:
-#   polymer_json: https://m.youtube.com/playlist?list=PLv3TTBr1W_9tppikBxAE_G6qjWdBljBHJ&pbj=1&lact=0
-#   ajax json:    https://m.youtube.com/playlist?list=PLv3TTBr1W_9tppikBxAE_G6qjWdBljBHJ&pbj=1&lact=0 with header X-YouTube-Client-Version: 1.20180418
 
+def playlist_first_page(playlist_id, report_text="Retrieved playlist",
+                        use_mobile=False):
+    # Use innertube API (pbj=1 no longer works for many playlists)
+    key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
+    url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
 
-# continuation request types:
+    data = {
-#   polymer_json: https://m.youtube.com/playlist?&ctoken=[...]&pbj=1
+        'context': {
-#   ajax json:    https://m.youtube.com/playlist?action_continuation=1&ajax=1&ctoken=[...]
+            'client': {
-
+                'hl': 'en',
-
+                'gl': 'US',
-headers_1 = (
+                'clientName': 'WEB',
-    ('Accept', '*/*'),
+                'clientVersion': '2.20240327.00.00',
-    ('Accept-Language', 'en-US,en;q=0.5'),
+            },
-    ('X-YouTube-Client-Name', '2'),
+        },
-    ('X-YouTube-Client-Version', '2.20180614'),
+        'browseId': 'VL' + playlist_id,
-)
-
-
-def playlist_first_page(playlist_id, report_text="Retrieved playlist"):
-    url = 'https://m.youtube.com/playlist?list=' + playlist_id + '&pbj=1'
-    content = util.fetch_url(url, util.mobile_ua + headers_1, report_text=report_text, debug_name='playlist_first_page')
-    content = json.loads(content.decode('utf-8'))
-
-    return content
-
-
-#https://m.youtube.com/playlist?itct=CBMQybcCIhMIptj9xJaJ2wIV2JKcCh3Idwu-&ctoken=4qmFsgI2EiRWTFBMT3kwajlBdmxWWlB0bzZJa2pLZnB1MFNjeC0tN1BHVEMaDmVnWlFWRHBEUWxFJTNE&pbj=1
-def get_videos(playlist_id, page):
-
-    url = "https://m.youtube.com/playlist?ctoken=" + playlist_ctoken(playlist_id, (int(page)-1)*20) + "&pbj=1"
-    headers = {
-        'User-Agent': '  Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_1 like Mac OS X) AppleWebKit/603.1.30 (KHTML, like Gecko) Version/10.0 Mobile/14E304 Safari/602.1',
-        'Accept': '*/*',
-        'Accept-Language': 'en-US,en;q=0.5',
-        'X-YouTube-Client-Name': '2',
-        'X-YouTube-Client-Version': '2.20180508',
     }
 
+    content_type_header = (('Content-Type', 'application/json'),)
     content = util.fetch_url(
-        url, headers,
+        url, util.desktop_xhr_headers + content_type_header,
-        report_text="Retrieved playlist", debug_name='playlist_videos')
+        data=json.dumps(data),
+        report_text=report_text, debug_name='playlist_first_page'
+    )
+    return json.loads(content.decode('utf-8'))
+
+
+def get_videos(playlist_id, page, include_shorts=True, use_mobile=False,
+               report_text='Retrieved playlist'):
+    page_size = 100
+
+    key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
+    url = 'https://www.youtube.com/youtubei/v1/browse?key=' + key
+
+    ctoken = playlist_ctoken(playlist_id, (int(page)-1)*page_size,
+                             include_shorts=include_shorts)
+
+    data = {
+        'context': {
+            'client': {
+                'hl': 'en',
+                'gl': 'US',
+                'clientName': 'WEB',
+                'clientVersion': '2.20240327.00.00',
+            },
+        },
+        'continuation': ctoken,
+    }
+
+    content_type_header = (('Content-Type', 'application/json'),)
+    content = util.fetch_url(
+        url, util.desktop_xhr_headers + content_type_header,
+        data=json.dumps(data),
+        report_text=report_text, debug_name='playlist_videos'
+    )
 
     info = json.loads(content.decode('utf-8'))
     return info
@@ -78,6 +94,15 @@ def get_playlist_page():
         abort(400)
 
     playlist_id = request.args.get('list')
+
+    # Radio/Mix playlists (RD...) only work as watch page, not playlist page
+    if playlist_id.startswith('RD'):
+        first_video_id = playlist_id[2:]  # video ID after 'RD' prefix
+        return flask.redirect(
+            util.URL_ORIGIN + '/watch?v=' + first_video_id + '&list=' + playlist_id,
+            302
+        )
+
     page = request.args.get('page', '1')
 
     if page == '1':
@@ -85,7 +110,10 @@ def get_playlist_page():
         this_page_json = first_page_json
     else:
         tasks = (
-            gevent.spawn(playlist_first_page, playlist_id, report_text="Retrieved playlist info" ),
+            gevent.spawn(
+                playlist_first_page, playlist_id,
+                report_text="Retrieved playlist info"
+            ),
             gevent.spawn(get_videos, playlist_id, page)
         )
         gevent.joinall(tasks)
@@ -103,8 +131,8 @@ def get_playlist_page():
     for item in info.get('items', ()):
         util.prefix_urls(item)
         util.add_extra_html_info(item)
-        if 'id' in item:
+        if 'id' in item and not item.get('thumbnail'):
-            item['thumbnail'] = settings.img_prefix + 'https://i.ytimg.com/vi/' + item['id'] + '/default.jpg'
+            item['thumbnail'] = f"{settings.img_prefix}https://i.ytimg.com/vi/{item['id']}/hqdefault.jpg"
 
         item['url'] += '&list=' + playlist_id
         if item['index']:
@@ -112,13 +140,13 @@ def get_playlist_page():
 
     video_count = yt_data_extract.deep_get(info, 'metadata', 'video_count')
     if video_count is None:
-        video_count = 40
+        video_count = 1000
 
     return flask.render_template(
         'playlist.html',
         header_playlist_names=local_playlist.get_playlist_names(),
         video_list=info.get('items', []),
-        num_pages=math.ceil(video_count/20),
+        num_pages=math.ceil(video_count/100),
         parameters_dictionary=request.args,
 
         **info['metadata']

youtube/proto.py

@@ -113,12 +113,12 @@ def read_protobuf(data):
             length = read_varint(data)
             value = data.read(length)
         elif wire_type == 3:
-            end_bytes = encode_varint((field_number << 3) | 4)
+            end_bytes = varint_encode((field_number << 3) | 4)
             value = read_group(data, end_bytes)
         elif wire_type == 5:
             value = data.read(4)
         else:
-            raise Exception("Unknown wire type: " + str(wire_type) + ", Tag: " + bytes_to_hex(succinct_encode(tag)) + ", at position " + str(data.tell()))
+            raise Exception("Unknown wire type: " + str(wire_type) + " at position " + str(data.tell()))
         yield (wire_type, field_number, value)
 
 
@@ -141,6 +141,17 @@ base64_enc_funcs = {
 
 
 def _make_protobuf(data):
+    '''
+    Input: Recursive list of protobuf objects or base-64 encodings
+    Output: Protobuf bytestring
+    Each protobuf object takes the form [wire_type, field_number, field_data]
+    If a string protobuf has a list/tuple of length 2, this has the form
+    (base64 type, data)
+    The base64 types are
+    - base64 means a base64 encode with equals sign paddings
+    - base64s means a base64 encode without padding
+    - base64p means a url base64 encode with equals signs replaced with %3D
+    '''
     # must be dict mapping field_number to [wire_type, value]
     if isinstance(data, dict):
         new_data = []

youtube/proto_debug.py

@@ -97,6 +97,7 @@ import re
 import time
 import json
 import os
+import traceback
 import pprint
 
 

youtube/search.py

@@ -64,6 +64,8 @@ def get_search_page():
     query = request.args.get('search_query') or request.args.get('query')
     if query is None:
         return flask.render_template('home.html', title='Search')
+    elif query.startswith('https://www.youtube.com') or query.startswith('https://www.youtu.be'):
+         return flask.redirect(f'/{query}')
 
     page = request.args.get("page", "1")
     autocorrect = int(request.args.get("autocorrect", "1"))

youtube/static/channel.css

@@ -256,7 +256,8 @@ hr {
     padding-top: 6px;
     text-align: center;
     white-space: nowrap;
-    border: none;
+    border: 1px solid;
+    border-color: var(--button-border);
     border-radius: 0.2rem;
 }
 

youtube/static/dark_theme.css

@@ -1,20 +1,22 @@
 :root {
-    --background:           #212121;
+    --background:           #121113;
     --text:                 #FFFFFF;
-    --secondary-hover:      #73828c;
+    --secondary-hover:      #222222;
-    --secondary-focus:      #303030;
+    --secondary-focus:      #121113;
-    --secondary-inverse:    #FFF;
+    --secondary-inverse:    #FFFFFF;
     --primary-background:   #242424;
-    --secondary-background: #424242;
+    --secondary-background: #222222;
-    --thumb-background:     #757575;
+    --thumb-background:     #222222;
     --link:                 #00B0FF;
     --link-visited:         #40C4FF;
-    --border-bg:            #FFFFFF;
+    --border-bg:            #222222;
-    --buttom:               #dcdcdb;
+    --border-bg-settings:   #000000;
-    --buttom-text:          #415462;
+    --border-bg-license:    #000000;
-    --button-border:        #91918c;
+    --buttom:               #121113;
-    --buttom-hover:         #BBB;
+    --buttom-text:          #FFFFFF;
-    --search-text:          #FFF;
+    --button-border:        #222222;
-    --time-background:      #212121;
+    --buttom-hover:         #222222;
-    --time-text:            #FFF;
+    --search-text:          #FFFFFF;
+    --time-background:      #121113;
+    --time-text:            #FFFFFF;
 }

youtube/static/gray_theme.css

@@ -1,19 +1,21 @@
 :root {
-    --background:            #2d3743;
+    --background:            #2D3743;
     --text:                  #FFFFFF;
-    --secondary-hover:       #73828c;
+    --secondary-hover:       #73828C;
     --secondary-focus:       rgba(115, 130, 140, 0.125);
     --secondary-inverse:     #FFFFFF;
-    --primary-background:    #2d3743;
+    --primary-background:    #2D3743;
     --secondary-background:  #102027;
     --thumb-background:      #35404D;
-    --link:                  #22aaff;
+    --link:                  #22AAFF;
-    --link-visited:          #7755ff;
+    --link-visited:          #7755FF;
     --border-bg:             #FFFFFF;
-    --buttom:                #DCDCDC;
+    --border-bg-settings:    #FFFFFF;
-    --buttom-text:           #415462;
+    --border-bg-license:     #FFFFFF;
-    --button-border:         #91918c;
+    --buttom:                #2D3743;
-    --buttom-hover:          #BBBBBB;
+    --buttom-text:           #FFFFFF;
+    --button-border:         #102027;
+    --buttom-hover:          #102027;
     --search-text:           #FFFFFF;
     --time-background:       #212121;
     --time-text:             #FFFFFF;

youtube/static/js/av-merge.js

@@ -20,6 +20,29 @@
 // TODO: Call abort to cancel in-progress appends?
 
 
+// Buffer sizes for different systems
+const BUFFER_CONFIG = {
+    default: 50 * 10**6,  // 50 megabytes
+    webOS: 20 * 10**6,    // 20 megabytes WebOS (LG)
+    samsungTizen: 20 * 10**6, // 20 megabytes Samsung Tizen OS
+    androidTV: 30 * 10**6, // 30 megabytes Android TV
+    desktop: 50 * 10**6,  // 50 megabytes PC/Mac
+};
+
+function detectSystem() {
+    const userAgent = navigator.userAgent.toLowerCase();
+    if (/webos|lg browser/i.test(userAgent)) {
+        return "webOS";
+    } else if (/tizen/i.test(userAgent)) {
+        return "samsungTizen";
+    } else if (/android tv|smart-tv/i.test(userAgent)) {
+        return "androidTV";
+    } else if (/firefox|chrome|safari|edge/i.test(userAgent)) {
+        return "desktop";
+    } else {
+        return "default";
+    }
+}
 
 function AVMerge(video, srcInfo, startTime){
     this.audioSource = null;
@@ -164,6 +187,8 @@ AVMerge.prototype.printDebuggingInfo = function() {
 }
 
 function Stream(avMerge, source, startTime, avRatio) {
+    const selectedSystem = detectSystem();
+    let baseBufferTarget = BUFFER_CONFIG[selectedSystem] || BUFFER_CONFIG.default;
     this.avMerge = avMerge;
     this.video = avMerge.video;
     this.url = source['url'];
@@ -173,10 +198,11 @@ function Stream(avMerge, source, startTime, avRatio) {
     this.mimeCodec = source['mime_codec']
     this.streamType = source['acodec'] ? 'audio' : 'video';
     if (this.streamType == 'audio') {
-        this.bufferTarget = avRatio*50*10**6;
+        this.bufferTarget = avRatio * baseBufferTarget;
     } else {
-        this.bufferTarget = 50*10**6; // 50 megabytes
+        this.bufferTarget = baseBufferTarget;
     }
+    console.info(`Detected system: ${selectedSystem}. Applying bufferTarget of ${this.bufferTarget} bytes to ${this.streamType}.`);
 
     this.initRange = source['init_range'];
     this.indexRange = source['index_range'];
@@ -204,6 +230,8 @@ Stream.prototype.setup = async function(){
             this.url,
             this.initRange.start,
             this.indexRange.end,
+            'Initialization+index segments',
+        ).then(
             (buffer) => {
                 let init_end = this.initRange.end - this.initRange.start + 1;
                 let index_start = this.indexRange.start - this.initRange.start;
@@ -211,22 +239,23 @@ Stream.prototype.setup = async function(){
                 this.setupInitSegment(buffer.slice(0, init_end));
                 this.setupSegmentIndex(buffer.slice(index_start, index_end));
             }
-        )
+        );
     } else {
         // initialization data
         await fetchRange(
             this.url,
             this.initRange.start,
             this.initRange.end,
-            this.setupInitSegment.bind(this),
+            'Initialization segment',
-        );
+        ).then(this.setupInitSegment.bind(this));
+
         // sidx (segment index) table
         fetchRange(
             this.url,
             this.indexRange.start,
             this.indexRange.end,
-            this.setupSegmentIndex.bind(this)
+            'Index segment',
-        );
+        ).then(this.setupSegmentIndex.bind(this));
     }
 }
 Stream.prototype.setupInitSegment = function(initSegment) {
@@ -388,7 +417,7 @@ Stream.prototype.getSegmentIdx = function(videoTime) {
         }
         index = index + increment;
     }
-    this.reportInfo('Could not find segment index for time', videoTime);
+    this.reportError('Could not find segment index for time', videoTime);
     return 0;
 }
 Stream.prototype.checkBuffer = async function() {
@@ -485,8 +514,8 @@ Stream.prototype.fetchSegment = function(segmentIdx) {
         this.url,
         entry.start,
         entry.end,
-        this.appendSegment.bind(this, segmentIdx),
+        String(this.streamType) + ' segment ' + String(segmentIdx),
-    );
+    ).then(this.appendSegment.bind(this, segmentIdx));
 }
 Stream.prototype.fetchSegmentIfNeeded = function(segmentIdx) {
     if (segmentIdx < 0 || segmentIdx >= this.sidx.entries.length){
@@ -518,22 +547,56 @@ Stream.prototype.reportWarning = function(...args) {
 Stream.prototype.reportError = function(...args) {
     reportError(String(this.streamType) + ':', ...args);
 }
-Stream.prototype.reportInfo = function(...args) {
-    reportInfo(String(this.streamType) + ':', ...args);
-}
 
 
 // Utility functions
 
-function fetchRange(url, start, end, cb) {
+// https://gomakethings.com/promise-based-xhr/
+// https://stackoverflow.com/a/30008115
+// http://lofi.limo/blog/retry-xmlhttprequest-carefully
+function fetchRange(url, start, end, debugInfo) {
     return new Promise((resolve, reject) => {
+        let retryCount = 0;
         let xhr = new XMLHttpRequest();
+        function onFailure(err, message, maxRetries=5){
+            message = debugInfo + ': ' + message + ' - Err: ' + String(err);
+            retryCount++;
+            if (retryCount > maxRetries || xhr.status == 403){
+                reportError('fetchRange error while fetching ' + message);
+                reject(message);
+                return;
+            } else {
+                reportWarning('Failed to fetch ' + message
+                    + '. Attempting retry '
+                    + String(retryCount) +'/' + String(maxRetries));
+            }
+
+            // Retry in 1 second, doubled for each next retry
+            setTimeout(function(){
+                xhr.open('get',url);
+                xhr.send();
+            }, 1000*Math.pow(2,(retryCount-1)));
+        }
         xhr.open('get', url);
+        xhr.timeout = 15000;
         xhr.responseType = 'arraybuffer';
         xhr.setRequestHeader('Range', 'bytes=' + start + '-' + end);
-        xhr.onload = function() {
+        xhr.onload = function (e) {
-            //bytesFetched += end - start + 1;
+            if (xhr.status >= 200 && xhr.status < 300) {
-            resolve(cb(xhr.response));
+                resolve(xhr.response);
+            } else {
+                onFailure(e,
+                    'Status '
+                    + String(xhr.status) + ' ' + String(xhr.statusText)
+                );
+            }
+        };
+        xhr.onerror = function (event) {
+            onFailure(e, 'Network error');
+        };
+        xhr.ontimeout = function (event){
+            xhr.timeout += 5000;
+            onFailure(null, 'Timeout (15s)', maxRetries=5);
         };
         xhr.send();
     });
@@ -573,9 +636,6 @@ function addEvent(obj, eventName, func) {
     return new RegisteredEvent(obj, eventName, func);
 }
 
-function reportInfo(...args){
-    console.info(...args);
-}
 function reportWarning(...args){
     console.warn(...args);
 }

youtube/static/js/common.js

@@ -114,3 +114,57 @@ function copyTextToClipboard(text) {
 window.addEventListener('DOMContentLoaded', function() {
     cur_track_idx = getDefaultTranscriptTrackIdx();
 });
+
+/**
+ * Thumbnail fallback handler
+ * Tries lower quality thumbnails when higher quality fails (404)
+ * Priority: hq720.jpg -> sddefault.jpg -> hqdefault.jpg -> mqdefault.jpg -> default.jpg
+ */
+function thumbnail_fallback(img) {
+    // Once src is set (image was loaded or attempted), always work with src
+    const src = img.src;
+    if (!src) return;
+
+    // Handle YouTube video thumbnails
+    if (src.includes('/i.ytimg.com/') || src.includes('/i.ytimg.com%2F')) {
+        // Extract video ID from URL
+        const match = src.match(/\/vi\/([^/]+)/);
+        if (!match) return;
+
+        const videoId = match[1];
+        const imgPrefix = settings_img_prefix || '';
+
+        // Define fallback order (from highest to lowest quality)
+        const fallbacks = [
+            'hq720.jpg',
+            'sddefault.jpg',
+            'hqdefault.jpg',
+        ];
+
+        // Find current quality and try next fallback
+        for (let i = 0; i < fallbacks.length; i++) {
+            if (src.includes(fallbacks[i])) {
+                if (i < fallbacks.length - 1) {
+                    img.src = imgPrefix + 'https://i.ytimg.com/vi/' + videoId + '/' + fallbacks[i + 1];
+                } else {
+                    // Last fallback failed, stop retrying
+                    img.onerror = null;
+                }
+                return;
+            }
+        }
+        // Unknown quality format, stop retrying
+        img.onerror = null;
+    }
+    // Handle YouTube channel avatars (ggpht.com)
+    else if (src.includes('ggpht.com') || src.includes('yt3.ggpht.com')) {
+        const newSrc = src.replace(/=s\d+-c-k/, '=s240-c-k-c0x00ffffff-no-rj');
+        if (newSrc !== src) {
+            img.src = newSrc;
+        } else {
+            img.onerror = null;
+        }
+    } else {
+        img.onerror = null;
+    }
+}

youtube/static/js/plyr-start.js

@@ -1,77 +1,66 @@
 (function main() {
   'use strict';
 
-  let captionsActive;
+  // Captions
-
+  let captionsActive = false;
-  switch(true) {
+  if (data.settings.subtitles_mode === 2 || (data.settings.subtitles_mode === 1 && data.has_manual_captions)) {
-    case data.settings.subtitles_mode == 2:
+    captionsActive = true;
-      captionsActive = true;
-      break;
-    case data.settings.subtitles_mode == 1 && data.has_manual_captions:
-      captionsActive = true;
-      break;
-    default:
-      captionsActive = false;
   }
 
+  // AutoPlay
+  let autoplayActive = data.settings.autoplay_videos || false;
+
   let qualityOptions = [];
   let qualityDefault;
-  for (let src of data['uni_sources']) {
+
-    qualityOptions.push(src.quality_string)
+  for (let src of data.uni_sources) {
+    qualityOptions.push(src.quality_string);
   }
-  for (let src of data['pair_sources']) {
+
-    qualityOptions.push(src.quality_string)
+  for (let src of data.pair_sources) {
+    qualityOptions.push(src.quality_string);
   }
-  if (data['using_pair_sources'])
+
-    qualityDefault = data['pair_sources'][data['pair_idx']].quality_string;
+  if (data.using_pair_sources) {
-  else if (data['uni_sources'].length != 0)
+    qualityDefault = data.pair_sources[data.pair_idx].quality_string;
-    qualityDefault = data['uni_sources'][data['uni_idx']].quality_string;
+  } else if (data.uni_sources.length !== 0) {
-  else
+    qualityDefault = data.uni_sources[data.uni_idx].quality_string;
+  } else {
     qualityDefault = 'None';
+  }
 
   // Fix plyr refusing to work with qualities that are strings
   Object.defineProperty(Plyr.prototype, 'quality', {
-    set: function(input) {
+    set: function (input) {
       const config = this.config.quality;
       const options = this.options.quality;
-      let quality;
+      let quality = input;
+      let updateStorage = true;
 
       if (!options.length) {
         return;
       }
 
-      // removing this line:
-      //let quality = [!is.empty(input) && Number(input), this.storage.get('quality'), config.selected, config.default].find(is.number);
-      // replacing with:
-      quality = input;
-      let updateStorage = true;
-
       if (!options.includes(quality)) {
-        // Plyr sets quality to null at startup, resulting in the erroneous
-        // calling of this setter function with input = null, and the
-        // commented out code below would set the quality to something
-        // unrelated at startup. Comment out and just return.
         return;
-        /*const value = closest(options, quality);
-          this.debug.warn(`Unsupported quality option: ${quality}, using ${value} instead`);
-          quality = value; // Don't update storage if quality is not supported
-          updateStorage = false;*/
-      } // Update config
-
-
-      config.selected = quality; // Set quality
-
-      this.media.quality = quality; // Save to storage
-
-      if (updateStorage) {
-        this.storage.set({
-          quality
-        });
       }
-    }
+
+      // Update config
+      config.selected = quality;
+
+      // Set quality
+      this.media.quality = quality;
+
+      // Save to storage
+      if (updateStorage) {
+        this.storage.set({ quality });
+      }
+    },
   });
 
-  const player = new Plyr(document.getElementById('js-video-player'), {
+  const playerOptions = {
+    // Learning about autoplay permission https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Permissions-Policy/autoplay#syntax
+    autoplay: autoplayActive,
     disableContextMenu: false,
     captions: {
       active: captionsActive,
@@ -89,29 +78,31 @@
       'settings',
       'pip',
       'airplay',
-      'fullscreen'
+      'fullscreen',
     ],
-    iconUrl: "/youtube.com/static/modules/plyr/plyr.svg",
+    iconUrl: '/youtube.com/static/modules/plyr/plyr.svg',
-    blankVideo: "/youtube.com/static/modules/plyr/blank.webm",
+    blankVideo: '/youtube.com/static/modules/plyr/blank.webm',
     debug: false,
-    storage: {enabled: false},
+    storage: { enabled: false },
     quality: {
       default: qualityDefault,
       options: qualityOptions,
       forced: true,
-      onChange: function(quality) {
+      onChange: function (quality) {
-        if (quality == 'None') {return;}
+        if (quality == 'None') {
+          return;
+        }
         if (quality.includes('(integrated)')) {
-          for (let i=0; i < data['uni_sources'].length; i++) {
+          for (let i = 0; i < data.uni_sources.length; i++) {
-            if (data['uni_sources'][i].quality_string == quality) {
+            if (data.uni_sources[i].quality_string == quality) {
-              changeQuality({'type': 'uni', 'index': i});
+              changeQuality({ type: 'uni', index: i });
               return;
             }
           }
         } else {
-          for (let i=0; i < data['pair_sources'].length; i++) {
+          for (let i = 0; i < data.pair_sources.length; i++) {
-            if (data['pair_sources'][i].quality_string == quality) {
+            if (data.pair_sources[i].quality_string == quality) {
-              changeQuality({'type': 'pair', 'index': i});
+              changeQuality({ type: 'pair', index: i });
               return;
             }
           }
@@ -119,12 +110,27 @@
       },
     },
     previewThumbnails: {
-      enabled: storyboard_url != null,
+      enabled: storyboard_url !== null,
       src: [storyboard_url],
     },
     settings: ['captions', 'quality', 'speed', 'loop'],
     tooltips: {
       controls: true,
     },
+  }
+
+  const player = new Plyr(document.getElementById('js-video-player'), playerOptions);
+
+  // disable double click to fullscreen
+  // https://github.com/sampotts/plyr/issues/1370#issuecomment-528966795
+  player.eventListeners.forEach(function(eventListener) {
+    if(eventListener.type === 'dblclick') {
+        eventListener.element.removeEventListener(eventListener.type, eventListener.callback, eventListener.options);
+    }
   });
-}());
+
+  // Add .started property, true after the playback has been started
+  // Needed so controls won't be hidden before playback has started
+  player.started = false;
+  player.once('playing', function(){this.started = true});
+})();

youtube/static/js/watch.js

@@ -5,8 +5,9 @@ function changeQuality(selection) {
     let videoPaused = video.paused;
     let videoSpeed = video.playbackRate;
     let srcInfo;
-    if (avMerge)
+    if (avMerge && typeof avMerge.close === 'function') {
         avMerge.close();
+    }
     if (selection.type == 'uni'){
         srcInfo = data['uni_sources'][selection.index];
         video.src = srcInfo.url;

youtube/static/license.css

@@ -181,7 +181,7 @@ label[for=options-toggle-cbox] {
 
 .table td,.table th {
     padding: 10px 10px;
-    border: 1px solid var(--secondary-background);
+    border: 1px solid var(--border-bg-license);
     text-align: center;
 }
 

youtube/static/light_theme.css

@@ -10,9 +10,11 @@
     --link:                 #212121;
     --link-visited:         #808080;
     --border-bg:            #212121;
-    --buttom:               #DCDCDC;
+    --border-bg-settings:   #91918C;
+    --border-bg-license:    #91918C;
+    --buttom:               #FFFFFF;
     --buttom-text:          #212121;
-    --button-border:        #91918c;
+    --button-border:        #91918C;
     --buttom-hover:         #BBBBBB;
     --search-text:          #212121;
     --time-background:      #212121;

youtube/static/modules/plyr/custom_plyr.css

@@ -0,0 +1,77 @@
+/* Prevent this div from blocking right-click menu for video
+e.g. Firefox playback speed options */
+.plyr__poster {
+    display: none;
+}
+
+/* plyr fix */
+.plyr:-moz-full-screen video {
+    max-height: initial;
+}
+
+.plyr:-webkit-full-screen video {
+    max-height: initial;
+}
+
+.plyr:-ms-fullscreen video {
+    max-height: initial;
+}
+
+.plyr:fullscreen video {
+    max-height: initial;
+}
+
+.plyr__preview-thumb__image-container {
+    width: 158px;
+    height: 90px;
+}
+
+.plyr__preview-thumb {
+    bottom: 100%;
+}
+
+.plyr__menu__container [role="menu"],
+.plyr__menu__container [role="menucaptions"] {
+    /* Set vertical scroll */
+    /* issue https://github.com/sampotts/plyr/issues/1420 */
+    max-height: 320px;
+    overflow-y: auto;
+}
+
+/*
+* Custom styles similar to youtube
+*/
+.plyr__controls {
+    display: flex;
+    justify-content: center;
+}
+
+.plyr__progress__container {
+    position: absolute;
+    bottom: 0;
+    width: 100%;
+    margin-bottom: -10px;
+}
+
+.plyr__controls .plyr__controls__item:first-child {
+    margin-left: 0;
+    margin-right: 0;
+    z-index: 5;
+}
+
+.plyr__controls .plyr__controls__item.plyr__volume {
+    margin-left: auto;
+}
+
+.plyr__controls .plyr__controls__item.plyr__progress__container {
+    padding-left: 10px;
+    padding-right: 10px;
+}
+
+.plyr__progress input[type="range"] {
+    margin-bottom: 50px;
+}
+
+/*
+* End custom styles
+*/

youtube/static/settings.css

@@ -155,7 +155,7 @@ label[for=options-toggle-cbox] {
 }
 
 .settings-form > h2 {
-    border-bottom: 2px solid var(--border-bg);
+    border-bottom: 2px solid var(--border-bg-settings);
     padding-bottom: 0.5rem;
 }
 

youtube/static/watch.css

@@ -21,21 +21,7 @@ img {
 video {
     width: 100%;
     height: auto;
-    max-height: 480px;
+    max-height: calc(100vh/1.5);
-}
-
-/* plyr fix */
-.plyr:-moz-full-screen video {
-    max-height: initial;
-}
-.plyr:-webkit-full-screen video {
-    max-height: initial;
-}
-.plyr:-ms-fullscreen video {
-    max-height: initial;
-}
-.plyr:fullscreen video {
-    max-height: initial;
 }
 
 a:link {
@@ -142,6 +128,29 @@ header {
     background-color: var(--buttom-hover);
 }
 
+.live-url-choices {
+    background-color: var(--thumb-background);
+    margin: 1rem 0;
+    padding: 1rem;
+}
+
+.playability-error {
+    position: relative;
+    box-sizing: border-box;
+    height: 30vh;
+    margin: 1rem 0;
+}
+
+.playability-error > span {
+    display: flex;
+    background-color: var(--thumb-background);
+    height: 100%;
+    object-fit: cover;
+    justify-content: center;
+    align-items: center;
+    text-align: center;
+}
+
 .playlist {
     display: grid;
     grid-gap: 4px;
@@ -636,6 +645,9 @@ figure.sc-video {
         max-height: 80vh;
         overflow-y: scroll;
     }
+    .playability-error {
+        height: 60vh;
+    }
     .playlist {
         display: grid;
         grid-gap: 1px;

youtube/subscriptions.py

@@ -1,4 +1,4 @@
-from youtube import util, yt_data_extract, channel, local_playlist
+from youtube import util, yt_data_extract, channel, local_playlist, playlist
 from youtube import yt_app
 import settings
 
@@ -30,8 +30,7 @@ database_path = os.path.join(settings.data_dir, "subscriptions.sqlite")
 
 
 def open_database():
-    if not os.path.exists(settings.data_dir):
+    os.makedirs(settings.data_dir, exist_ok=True)
-        os.makedirs(settings.data_dir)
     connection = sqlite3.connect(database_path, check_same_thread=False)
 
     try:
@@ -108,8 +107,7 @@ def _subscribe(channels):
         with connection as cursor:
             channel_ids_to_check = [channel[0] for channel in channels if not _is_subscribed(cursor, channel[0])]
 
-            rows = ((channel_id, channel_name, 0, 0) for channel_id,
+            rows = ((channel_id, channel_name, 0, 0) for channel_id, channel_name in channels)
-                    channel_name in channels)
             cursor.executemany('''INSERT OR IGNORE INTO subscribed_channels (yt_channel_id, channel_name, time_last_checked, next_check_time)
                                   VALUES (?, ?, ?, ?)''', rows)
 
@@ -236,8 +234,7 @@ def _get_channel_names(cursor, channel_ids):
     return result
 
 
-def _channels_with_tag(cursor, tag, order=False, exclude_muted=False,
+def _channels_with_tag(cursor, tag, order=False, exclude_muted=False, include_muted_status=False):
-                       include_muted_status=False):
     ''' returns list of (channel_id, channel_name) '''
 
     statement = '''SELECT yt_channel_id, channel_name'''
@@ -434,8 +431,10 @@ def autocheck_setting_changed(old_value, new_value):
         stop_autocheck_system()
 
 
-settings.add_setting_changed_hook('autocheck_subscriptions',
+settings.add_setting_changed_hook(
-                                  autocheck_setting_changed)
+    'autocheck_subscriptions',
+    autocheck_setting_changed
+)
 if settings.autocheck_subscriptions:
     start_autocheck_system()
 # ----------------------------
@@ -463,7 +462,24 @@ def _get_atoma_feed(channel_id):
 
 def _get_channel_videos_first_page(channel_id, channel_status_name):
     try:
-        return channel.get_channel_first_page(channel_id=channel_id)
+        # First try the playlist method
+        pl_json = playlist.get_videos(
+            'UU' + channel_id[2:],
+            1,
+            include_shorts=settings.include_shorts_in_subscriptions,
+            report_text=None
+        )
+        pl_info = yt_data_extract.extract_playlist_info(pl_json)
+        if pl_info.get('items'):
+            pl_info['items'] = pl_info['items'][0:30]
+            return pl_info
+
+        # Try the channel api method
+        channel_json = channel.get_channel_first_page(channel_id=channel_id)
+        channel_info = yt_data_extract.extract_channel_info(
+            json.loads(channel_json), 'videos'
+        )
+        return channel_info
     except util.FetchError as e:
         if e.code == '429' and settings.route_tor:
             error_message = ('Error checking channel ' + channel_status_name
@@ -497,7 +513,7 @@ def _get_upstream_videos(channel_id):
     )
     gevent.joinall(tasks)
 
-    channel_tab, feed = tasks[0].value, tasks[1].value
+    channel_info, feed = tasks[0].value, tasks[1].value
 
     # extract published times from atoma feed
     times_published = {}
@@ -535,9 +551,8 @@ def _get_upstream_videos(channel_id):
     except defusedxml.ElementTree.ParseError:
         print('Failed to read atoma feed for ' + channel_status_name)
 
-    if channel_tab is None: # there was an error
+    if channel_info is None: # there was an error
         return
-    channel_info = yt_data_extract.extract_channel_info(json.loads(channel_tab), 'videos')
     if channel_info['error']:
         print('Error checking channel ' + channel_status_name + ': ' + channel_info['error'])
         return
@@ -552,14 +567,38 @@ def _get_upstream_videos(channel_id):
         if video_item['id'] in times_published:
             video_item['time_published'] = times_published[video_item['id']]
             video_item['is_time_published_exact'] = True
-        else:
+        elif video_item.get('time_published'):
             video_item['is_time_published_exact'] = False
             try:
                 video_item['time_published'] = youtube_timestamp_to_posix(video_item['time_published']) - i  # subtract a few seconds off the videos so they will be in the right order
-            except KeyError:
+            except Exception:
                 print(video_item)
-
+        else:
+            video_item['is_time_published_exact'] = False
+            video_item['time_published'] = None
         video_item['channel_id'] = channel_id
+    if len(videos) > 1:
+        # Go back and fill in any videos that don't have a time published
+        # using the time published of the surrounding ones
+        for i in range(len(videos)-1):
+            if (videos[i+1]['time_published'] is None
+                and videos[i]['time_published'] is not None
+            ):
+                videos[i+1]['time_published'] = videos[i]['time_published'] - 1
+        for i in reversed(range(1,len(videos))):
+            if (videos[i-1]['time_published'] is None
+                and videos[i]['time_published'] is not None
+            ):
+                videos[i-1]['time_published'] = videos[i]['time_published'] + 1
+    # Special case: none of the videos have a time published.
+    # In this case, make something up
+    if videos and videos[0]['time_published'] is None:
+        assert all(v['time_published'] is None for v in videos)
+        now = time.time()
+        for i in range(len(videos)):
+            # 1 month between videos
+            videos[i]['time_published'] = now - i*3600*24*30
+
 
     if len(videos) == 0:
         average_upload_period = 4*7*24*3600  # assume 1 month for channel with no videos
@@ -578,26 +617,31 @@ def _get_upstream_videos(channel_id):
     with open_database() as connection:
         with connection as cursor:
 
-            # calculate how many new videos there are
+            # Get video ids and duration of existing vids so we
-            existing_vids = set(row[0] for row in cursor.execute(
+            # can see how many new ones there are and update
-                '''SELECT video_id
+            # livestreams/premiers
+            existing_vids = list(cursor.execute(
+                '''SELECT video_id, duration
                    FROM videos
                    INNER JOIN subscribed_channels
                        ON videos.sql_channel_id = subscribed_channels.id
                    WHERE yt_channel_id=?
                    ORDER BY time_published DESC
                    LIMIT 30''', [channel_id]).fetchall())
+            existing_vid_ids = set(row[0] for row in existing_vids)
+            existing_durs = dict(existing_vids)
 
             # new videos the channel has uploaded since last time we checked
             number_of_new_videos = 0
             for video in videos:
-                if video['id'] in existing_vids:
+                if video['id'] in existing_vid_ids:
                     break
                 number_of_new_videos += 1
 
             is_first_check = cursor.execute('''SELECT time_last_checked FROM subscribed_channels WHERE yt_channel_id=?''', [channel_id]).fetchone()[0] in (None, 0)
             time_videos_retrieved = int(time.time())
             rows = []
+            update_rows = []
             for i, video_item in enumerate(videos):
                 if (is_first_check
                         or number_of_new_videos > 6
@@ -613,16 +657,34 @@ def _get_upstream_videos(channel_id):
                     time_noticed = video_item['time_published']
                 else:
                     time_noticed = time_videos_retrieved
-                rows.append((
+
-                    video_item['channel_id'],
+                # videos which need durations updated
-                    video_item['id'],
+                non_durations = ('upcoming', 'none', 'live', '')
-                    video_item['title'],
+                v_id = video_item['id']
-                    video_item['duration'],
+                if (existing_durs.get(v_id) is not None
-                    video_item['time_published'],
+                    and existing_durs[v_id].lower() in non_durations
-                    video_item['is_time_published_exact'],
+                    and video_item['duration'] not in non_durations
-                    time_noticed,
+                ):
-                    video_item['description'],
+                    update_rows.append((
-                ))
+                        video_item['title'],
+                        video_item['duration'],
+                        video_item['time_published'],
+                        video_item['is_time_published_exact'],
+                        video_item['description'],
+                        video_item['id'],
+                    ))
+                # all other videos
+                else:
+                    rows.append((
+                        video_item['channel_id'],
+                        video_item['id'],
+                        video_item['title'],
+                        video_item['duration'],
+                        video_item['time_published'],
+                        video_item['is_time_published_exact'],
+                        time_noticed,
+                        video_item['description'],
+                    ))
 
             cursor.executemany('''INSERT OR IGNORE INTO videos (
                                       sql_channel_id,
@@ -635,6 +697,13 @@ def _get_upstream_videos(channel_id):
                                       description
                                   )
                                   VALUES ((SELECT id FROM subscribed_channels WHERE yt_channel_id=?), ?, ?, ?, ?, ?, ?, ?)''', rows)
+            cursor.executemany('''UPDATE videos SET
+                                      title=?,
+                                      duration=?,
+                                      time_published=?,
+                                      is_time_published_exact=?,
+                                      description=?
+                                  WHERE video_id=?''', update_rows)
             cursor.execute('''UPDATE subscribed_channels
                               SET time_last_checked = ?, next_check_time = ?
                               WHERE yt_channel_id=?''', [int(time.time()), next_check_time, channel_id])
@@ -767,7 +836,7 @@ def import_subscriptions():
         error = 'Unsupported file format: ' + mime_type
         error += (' . Only subscription.json, subscriptions.csv files'
                   ' (from Google Takeouts)'
-                  ' and XML OPML files exported from Youtube\'s'
+                  ' and XML OPML files exported from YouTube\'s'
                   ' subscription manager page are supported')
         return (flask.render_template('error.html', error_message=error),
                 400)
@@ -962,7 +1031,8 @@ def get_subscriptions_page():
                     'muted': muted,
                 })
 
-    return flask.render_template('subscriptions.html',
+    return flask.render_template(
+        'subscriptions.html',
         header_playlist_names=local_playlist.get_playlist_names(),
         videos=videos,
         num_pages=math.ceil(number_of_videos_in_db/60),
@@ -1018,12 +1088,26 @@ def serve_subscription_thumbnail(thumbnail):
             f.close()
             return flask.Response(image, mimetype='image/jpeg')
 
-    url = "https://i.ytimg.com/vi/" + video_id + "/mqdefault.jpg"
+    image = None
-    try:
+    for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
-        image = util.fetch_url(url, report_text="Saved thumbnail: " + video_id)
+        url = f"https://i.ytimg.com/vi/{video_id}/{quality}"
-    except urllib.error.HTTPError as e:
+        try:
-        print("Failed to download thumbnail for " + video_id + ": " + str(e))
+            image = util.fetch_url(url, report_text="Saved thumbnail: " + video_id)
-        abort(e.code)
+            break
+        except util.FetchError as e:
+            if '404' in str(e):
+                continue
+            print("Failed to download thumbnail for " + video_id + ": " + str(e))
+            flask.abort(500)
+        except urllib.error.HTTPError as e:
+            if e.code == 404:
+                continue
+            print("Failed to download thumbnail for " + video_id + ": " + str(e))
+            flask.abort(e.code)
+
+    if image is None:
+        flask.abort(404)
+
     try:
         f = open(thumbnail_path, 'wb')
     except FileNotFoundError:

youtube/templates/base.html

@@ -26,6 +26,12 @@
              // @license-end
             </script>
         {% endif %}
+        <script>
+            // @license magnet:?xt=urn:btih:0b31508aeb0634b347b8270c7bee4d411b5d4109&dn=agpl-3.0.txt AGPL-v3-or-Later
+            // Image prefix for thumbnails
+            let settings_img_prefix = "{{ settings.img_prefix or '' }}";
+            // @license-end
+        </script>
     </head>
 
     <body>
@@ -35,57 +41,57 @@
             </nav>
             <form class="form" id="site-search" action="/youtube.com/results">
                 <input type="search" name="search_query" class="search-box" value="{{ search_box_value }}"
-                       {{ "autofocus" if (request.path in ("/", "/results") or error_message) else "" }} required placeholder="Type to search...">
+                       {{ "autofocus" if (request.path in ("/", "/results") or error_message) else "" }} required placeholder="{{ _('Type to search...') }}">
-                <button type="submit" value="Search" class="search-button">Search</button>
+                <button type="submit" value="Search" class="search-button">{{ _('Search') }}</button>
                 <!-- options -->
                 <div class="dropdown">
                     <!-- hidden box -->
                     <input id="options-toggle-cbox" class="opt-box" type="checkbox">
                     <!-- end hidden box -->
-                    <label class="dropdown-label" for="options-toggle-cbox">Options</label>
+                    <label class="dropdown-label" for="options-toggle-cbox">{{ _('Options') }}</label>
                     <div class="dropdown-content">
-                        <h3>Sort by</h3>
+                        <h3>{{ _('Sort by') }}</h3>
                         <div class="option">
                             <input type="radio" id="sort_relevance" name="sort" value="0">
-                            <label for="sort_relevance">Relevance</label>
+                            <label for="sort_relevance">{{ _('Relevance') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="sort_upload_date" name="sort" value="2">
-                            <label for="sort_upload_date">Upload date</label>
+                            <label for="sort_upload_date">{{ _('Upload date') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="sort_view_count" name="sort" value="3">
-                            <label for="sort_view_count">View count</label>
+                            <label for="sort_view_count">{{ _('View count') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="sort_rating" name="sort" value="1">
-                            <label for="sort_rating">Rating</label>
+                            <label for="sort_rating">{{ _('Rating') }}</label>
                         </div>
 
-                        <h3>Upload date</h3>
+                        <h3>{{ _('Upload date') }}</h3>
                         <div class="option">
                             <input type="radio" id="time_any" name="time" value="0">
-                            <label for="time_any">Any</label>
+                            <label for="time_any">{{ _('Any') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="time_last_hour" name="time" value="1">
-                            <label for="time_last_hour">Last hour</label>
+                            <label for="time_last_hour">{{ _('Last hour') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="time_today" name="time" value="2">
-                            <label for="time_today">Today</label>
+                            <label for="time_today">{{ _('Today') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="time_this_week" name="time" value="3">
-                            <label for="time_this_week">This week</label>
+                            <label for="time_this_week">{{ _('This week') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="time_this_month" name="time" value="4">
-                            <label for="time_this_month">This month</label>
+                            <label for="time_this_month">{{ _('This month') }}</label>
                         </div>
                         <div class="option">
                             <input type="radio" id="time_this_year" name="time" value="5">
-                            <label for="time_this_year">This year</label>
+                            <label for="time_this_year">{{ _('This year') }}</label>
                         </div>
 
                         <h3>Type</h3>

youtube/templates/channel.html

@@ -1,7 +1,7 @@
 {% if current_tab == 'search' %}
     {% set page_title = search_box_value + ' - Page ' + page_number|string %}
 {% else %}
-    {% set page_title = channel_name + ' - Channel' %}
+    {% set page_title = channel_name|string + ' - Channel' %}
 {% endif %}
 
 {% extends "base.html" %}
@@ -33,7 +33,7 @@
     <hr/>
 
     <nav class="channel-tabs">
-        {% for tab_name in ('Videos', 'Playlists', 'About') %}
+        {% for tab_name in ('Videos', 'Shorts', 'Streams', 'Playlists', 'About') %}
             {% if tab_name.lower() == current_tab %}
                 <a class="tab page-button">{{ tab_name }}</a>
             {% else %}
@@ -51,8 +51,11 @@
             <ul>
                 {% for (before_text, stat, after_text) in [
                     ('Joined ', date_joined, ''),
-                    ('', view_count|commatize, ' views'),
+                    ('', approx_view_count, ' views'),
                     ('', approx_subscriber_count, ' subscribers'),
+                    ('', approx_video_count, ' videos'),
+                    ('Country: ', country, ''),
+                    ('Canonical Url: ', canonical_url, ''),
                 ] %}
                     {% if stat %}
                         <li>{{ before_text + stat|string + after_text }}</li>
@@ -65,7 +68,11 @@
             <hr>
             <ul>
                 {% for text, url in links %}
-                    <li><a href="{{ url }}">{{ text }}</a></li>
+                    {% if url %}
+                        <li><a href="{{ url }}">{{ text }}</a></li>
+                    {% else %}
+                        <li>{{ text }}</li>
+                    {% endif %}
                 {% endfor %}
             </ul>
         </div>
@@ -73,11 +80,11 @@
 
         <!-- new-->
         <div id="links-metadata">
-                {% if current_tab == 'videos' %}
+                {% if current_tab in ('videos', 'shorts', 'streams') %}
-                    {% set sorts = [('1', 'views'), ('2', 'oldest'), ('3', 'newest')] %}
+                    {% set sorts = [('3', 'newest'), ('4', 'newest - no shorts')] %}
                     <div id="number-of-results">{{ number_of_videos }} videos</div>
                 {% elif current_tab == 'playlists' %}
-                    {% set sorts = [('2', 'oldest'), ('3', 'newest'), ('4', 'last video added')] %}
+                    {% set sorts = [('3', 'newest'), ('4', 'last video added')] %}
                     {% if items %}
                         <h2 class="page-number">Page {{ page_number }}</h2>
                     {% else %}
@@ -110,13 +117,9 @@
         <hr/>
 
         <footer class="pagination-container">
-            {% if current_tab == 'videos' and current_sort.__str__() == '2' %}
+            {% if current_tab in ('videos', 'shorts', 'streams') %}
-                <nav class="next-previous-button-row">
-                    {{ common_elements.next_previous_ctoken_buttons(None, ctoken, channel_url + '/' + current_tab, parameters_dictionary) }}
-                </nav>
-            {% elif current_tab == 'videos' %}
                 <nav class="pagination-list">
-                    {{ common_elements.page_buttons(number_of_pages, channel_url + '/' + current_tab, parameters_dictionary, include_ends=(current_sort.__str__() == '3')) }}
+                    {{ common_elements.page_buttons(number_of_pages, channel_url + '/' + current_tab, parameters_dictionary, include_ends=(current_sort.__str__() in '34')) }}
                 </nav>
             {% elif current_tab == 'playlists' or current_tab == 'search' %}
                 <nav class="next-previous-button-row">

youtube/templates/comments.html

@@ -3,13 +3,13 @@
 {% macro render_comment(comment, include_avatar, timestamp_links=False) %}
     <div class="comment-container">
         <div class="comment">
-            <a class="author-avatar" href="{{ comment['author_url'] }}" title="{{ comment['author'] }}">
+            <a class="author-avatar" href="{{ comment['author_url'] or '#' }}" title="{{ comment['author'] }}">
                 {% if include_avatar %}
                     <img class="author-avatar-img" alt="{{ comment['author'] }}" src="{{ comment['author_avatar'] }}">
                 {% endif %}
             </a>
             <address class="author-name">
-                <a class="author" href="{{ comment['author_url'] }}" title="{{ comment['author'] }}">{{ comment['author'] }}</a>
+                <a class="author" href="{{ comment['author_url'] or '#' }}" title="{{ comment['author'] }}">{{ comment['author'] }}</a>
             </address>
             <a class="permalink" href="{{ comment['permalink'] }}" title="permalink">
                 <span>{{ comment['time_published'] }}</span>

youtube/templates/common_elements.html

@@ -20,14 +20,14 @@
             {{ info['error'] }}
         {% else %}
             <div class="item-video {{ info['type'] + '-item' }}">
-                <a class="thumbnail-box" href="{{ info['url'] }}" title="{{ info['title'] }}">
+                <a class="thumbnail-box" href="{{ info['url'] or '#' }}" title="{{ info['title'] }}">
                     <div class="thumbnail {% if info['type'] == 'channel' %} channel {% endif %}">
                         {% if lazy_load %}
-                            <img class="thumbnail-img lazy" alt="&#x20;" data-src="{{ info['thumbnail'] }}">
+                            <img class="thumbnail-img lazy" alt="&#x20;" data-src="{{ info['thumbnail'] }}" onerror="thumbnail_fallback(this)">
                         {% elif info['type'] == 'channel' %}
-                            <img class="thumbnail-img channel" alt="&#x20;" src="{{ info['thumbnail'] }}">
+                            <img class="thumbnail-img channel" alt="&#x20;" src="{{ info['thumbnail'] }}" onerror="thumbnail_fallback(this)">
                         {% else %}
-                            <img class="thumbnail-img" alt="&#x20;" src="{{ info['thumbnail'] }}">
+                            <img class="thumbnail-img" alt="&#x20;" src="{{ info['thumbnail'] }}" onerror="thumbnail_fallback(this)">
                         {% endif %}
 
                         {% if info['type'] != 'channel' %}
@@ -35,7 +35,7 @@
                         {% endif %}
                     </div>
                 </a>
-                <h4 class="title"><a href="{{ info['url'] }}" title="{{ info['title'] }}">{{ info['title'] }}</a></h4>
+                <h4 class="title"><a href="{{ info['url'] or '#' }}" title="{{ info['title'] }}">{{ info['title'] }}</a></h4>
 
                 {% if include_author %}
                     {% set author_description = info['author'] %}
@@ -58,7 +58,9 @@
 
                 <div class="stats {{'horizontal-stats' if horizontal else 'vertical-stats'}}">
                     {% if info['type'] == 'channel' %}
-                        <div>{{ info['approx_subscriber_count'] }} subscribers</div>
+                        {% if info.get('approx_subscriber_count') %}
+                            <div>{{ info['approx_subscriber_count'] }} subscribers</div>
+                        {% endif %}
                         <div>{{ info['video_count']|commatize }} videos</div>
                     {% else %}
                         {% if info.get('time_published') %}

youtube/templates/error.html

@@ -1,4 +1,8 @@
-{% set page_title = 'Error' %}
+{% if error_code %}
+    {% set page_title = 'Error: ' ~ error_code %}
+{% else %}
+    {% set page_title = 'Error' %}
+{% endif %}
 
 {% if not slim %}
     {% extends "base.html" %}

youtube/templates/playlist.html

@@ -10,11 +10,17 @@
 
     <div class="playlist-metadata">
         <div class="author">
+            {% if thumbnail %}
             <img alt="{{ title }}" src="{{ thumbnail }}">
+            {% endif %}
             <h2>{{ title }}</h2>
         </div>
         <div class="summary">
+            {% if author_url %}
             <a class="playlist-author" href="{{ author_url }}">{{ author }}</a>
+            {% else %}
+            <span class="playlist-author">{{ author }}</span>
+            {% endif %}
         </div>
         <div class="playlist-stats">
             <div>{{ video_count|commatize }} videos</div>

youtube/templates/settings.html

@@ -31,11 +31,19 @@
                                     <input type="number" id="{{ 'setting_' + setting_name }}" name="{{ setting_name }}" value="{{ value }}" step="1">
                                 {% endif %}
                             {% elif setting_info['type'].__name__ == 'float' %}
-
+                                <input type="number" id="{{ 'setting_' + setting_name }}" name="{{ setting_name }}" value="{{ value }}" step="0.01">
                             {% elif setting_info['type'].__name__ == 'str' %}
-                                <input type="text" id="{{ 'setting_' + setting_name }}" name="{{ setting_name }}" value="{{ value }}">
+                                {% if 'options' is in(setting_info) %}
+                                    <select id="{{ 'setting_' + setting_name }}" name="{{ setting_name }}">
+                                        {% for option in setting_info['options'] %}
+                                            <option value="{{ option[0] }}" {{ 'selected' if option[0] == value else '' }}>{{ option[1] }}</option>
+                                        {% endfor %}
+                                    </select>
+                                {% else %}
+                                    <input type="text" id="{{ 'setting_' + setting_name }}" name="{{ setting_name }}" value="{{ value }}">
+                                {% endif %}
                             {% else %}
-                                <span>Error: Unknown setting type: setting_info['type'].__name__</span>
+                                <span>Error: Unknown setting type: {{ setting_info['type'].__name__ }}</span>
                             {% endif %}
                         </li>
                     {% endif %}

youtube/templates/watch.html

@@ -8,14 +8,8 @@
     {% if settings.use_video_player == 2 %}
         <!-- plyr -->
         <link href="/youtube.com/static/modules/plyr/plyr.css" rel="stylesheet">
+        <link href="/youtube.com/static/modules/plyr/custom_plyr.css" rel="stylesheet">
         <!--/ plyr -->
-        <style>
-         /* Prevent this div from blocking right-click menu for video
-         e.g. Firefox playback speed options */
-         .plyr__poster {
-             display: none !important;
-         }
-        </style>
     {% endif %}
 {% endblock style %}
 
@@ -40,7 +34,7 @@
         </div>
     {% else %}
         <figure class="sc-video">
-            <video id="js-video-player" playsinline controls>
+            <video id="js-video-player" playsinline controls {{ 'autoplay' if settings.autoplay_videos }}>
                 {% if uni_sources %}
                     <source src="{{ uni_sources[uni_idx]['url'] }}" type="{{ uni_sources[uni_idx]['type'] }}" data-res="{{ uni_sources[uni_idx]['quality'] }}">
                 {% endif %}
@@ -91,6 +85,7 @@
                             <option value='{"type": "pair", "index": {{ loop.index0}}}' {{ 'selected' if loop.index0 == pair_idx and using_pair_sources else '' }} >{{ src_pair['quality_string'] }}</option>
                         {% endfor %}
                     </select>
+
                 {% endif %}
             </div>
             <input class="v-checkbox" name="video_info_list" value="{{ video_info }}" form="playlist-edit" type="checkbox">
@@ -135,7 +130,11 @@
                         {% for track in music_list %}
                             <tr>
                                 {% for attribute in music_attributes %}
-                                    <td>{{ track.get(attribute.lower(), '') }}</td>
+                                    {% if attribute.lower() == 'title' and track['url'] is not none %}
+                                        <td><a href="{{ track['url'] }}">{{ track.get(attribute.lower(), '') }}</a></td>
+                                    {% else %}
+                                        <td>{{ track.get(attribute.lower(), '') }}</td>
+                                    {% endif %}
                                 {% endfor %}
                             </tr>
                         {% endfor %}
@@ -173,7 +172,11 @@
                             {% else %}
                                 <li>{{ playlist['current_index']+1 }}/{{ playlist['video_count'] }}</li>
                             {% endif %}
+                            {% if playlist['author_url'] %}
                             <li><a href="{{ playlist['author_url'] }}" title="{{ playlist['author'] }}">{{ playlist['author'] }}</a></li>
+                            {% elif playlist['author'] %}
+                            <li>{{ playlist['author'] }}</li>
+                            {% endif %}
                         </ul>
                     </div>
                     <nav class="playlist-videos">
@@ -229,7 +232,7 @@
                 <div class="comments-area-outer comments-disabled">Comments disabled</div>
             {% else %}
                 <details class="comments-area-outer" {{'open' if settings.comments_mode == 1 else ''}}>
-                    <summary>{{ comment_count|commatize }} comment{{'s' if comment_count != 1 else ''}}</summary>
+                    <summary>{{ comment_count|commatize }} comment{{'s' if comment_count != '1' else ''}}</summary>
                     <div class="comments-area-inner comments-area">
                         {% if comments_info %}
                             {{ comments.video_comments(comments_info) }}
@@ -248,6 +251,7 @@
      let storyboard_url = {{ storyboard_url | tojson }};
      // @license-end
     </script>
+
     <script src="/youtube.com/static/js/common.js"></script>
     <script src="/youtube.com/static/js/transcript-table.js"></script>
     {% if settings.use_video_player == 2 %}

youtube/util.py

@@ -1,4 +1,5 @@
 from datetime import datetime
+import logging
 import settings
 import socks
 import sockshandler
@@ -18,6 +19,8 @@ import gevent.queue
 import gevent.lock
 import collections
 import stem
+
+logger = logging.getLogger(__name__)
 import stem.control
 import traceback
 
@@ -302,72 +305,140 @@ def fetch_url_response(url, headers=(), timeout=15, data=None,
 def fetch_url(url, headers=(), timeout=15, report_text=None, data=None,
               cookiejar_send=None, cookiejar_receive=None, use_tor=True,
               debug_name=None):
-    while True:
+    """
-        start_time = time.monotonic()
+    Fetch URL with exponential backoff retry logic for rate limiting.
 
-        response, cleanup_func = fetch_url_response(
+    Retries:
-            url, headers, timeout=timeout, data=data,
+    - 429 Too Many Requests: Exponential backoff (1s, 2s, 4s, 8s, 16s)
-            cookiejar_send=cookiejar_send, cookiejar_receive=cookiejar_receive,
+    - 503 Service Unavailable: Exponential backoff
-            use_tor=use_tor)
+    - 302 Redirect to Google Sorry: Treated as rate limit
-        response_time = time.monotonic()
 
-        content = response.read()
+    Max retries: 5 attempts with exponential backoff
+    """
+    import random
 
-        read_finish = time.monotonic()
+    max_retries = 5
+    base_delay = 1.0  # Base delay in seconds
 
-        cleanup_func(response)  # release_connection for urllib3
+    for attempt in range(max_retries):
-        content = decode_content(
+        try:
-            content,
+            start_time = time.monotonic()
-            response.getheader('Content-Encoding', default='identity'))
 
-        if (settings.debugging_save_responses
+            response, cleanup_func = fetch_url_response(
-                and debug_name is not None and content):
+                url, headers, timeout=timeout, data=data,
-            save_dir = os.path.join(settings.data_dir, 'debug')
+                cookiejar_send=cookiejar_send, cookiejar_receive=cookiejar_receive,
-            if not os.path.exists(save_dir):
+                use_tor=use_tor)
-                os.makedirs(save_dir)
+            response_time = time.monotonic()
 
-            with open(os.path.join(save_dir, debug_name), 'wb') as f:
+            content = response.read()
-                f.write(content)
 
-        if response.status == 429 or (
+            read_finish = time.monotonic()
-            response.status == 302 and (response.getheader('Location') == url
-                or response.getheader('Location').startswith(
-                       'https://www.google.com/sorry/index'
-                   )
-            )
-        ):
-            print(response.status, response.reason, response.getheaders())
-            ip = re.search(
-                br'IP address: ((?:[\da-f]*:)+[\da-f]+|(?:\d+\.)+\d+)',
-                content)
-            ip = ip.group(1).decode('ascii') if ip else None
-            if not ip:
-                ip = re.search(r'IP=((?:\d+\.)+\d+)',
-                               response.getheader('Set-Cookie') or '')
-                ip = ip.group(1) if ip else None
 
-            # don't get new identity if we're not using Tor
+            cleanup_func(response)  # release_connection for urllib3
-            if not use_tor:
+            content = decode_content(
-                raise FetchError('429', reason=response.reason, ip=ip)
+                content,
+                response.headers.get('Content-Encoding', default='identity'))
 
-            print('Error: YouTube blocked the request because the Tor exit node is overutilized. Exit node IP address: %s' % ip)
+            if (settings.debugging_save_responses
+                    and debug_name is not None
+                    and content):
+                save_dir = os.path.join(settings.data_dir, 'debug')
+                os.makedirs(save_dir, exist_ok=True)
 
-            # get new identity
+                with open(os.path.join(save_dir, debug_name), 'wb') as f:
-            error = tor_manager.new_identity(start_time)
+                    f.write(content)
-            if error:
-                raise FetchError(
-                    '429', reason=response.reason, ip=ip,
-                    error_message='Automatic circuit change: ' + error)
-            else:
-                continue # retry now that we have new identity
 
-        elif response.status >= 400:
+            # Check for rate limiting (429) or redirect to Google Sorry
-            raise FetchError(str(response.status), reason=response.reason,
+            if response.status == 429 or (
-                             ip=None)
+                response.status == 302 and (response.getheader('Location') == url
-        break
+                    or response.getheader('Location').startswith(
+                           'https://www.google.com/sorry/index'
+                       )
+                    )
+            ):
+                logger.info(f'Rate limit response: {response.status} {response.reason}')
+                ip = re.search(
+                    br'IP address: ((?:[\da-f]*:)+[\da-f]+|(?:\d+\.)+\d+)',
+                    content)
+                ip = ip.group(1).decode('ascii') if ip else None
+                if not ip:
+                    ip = re.search(r'IP=((?:\d+\.)+\d+)',
+                                   response.getheader('Set-Cookie') or '')
+                    ip = ip.group(1) if ip else None
+
+                # Without Tor, no point retrying with same IP
+                if not use_tor or not settings.route_tor:
+                    logger.warning('Rate limited (429). Enable Tor routing to retry with new IP.')
+                    raise FetchError('429', reason=response.reason, ip=ip)
+
+                # Tor: exhausted retries
+                if attempt >= max_retries - 1:
+                    logger.error(f'Rate limited after {max_retries} retries. Exit IP: {ip}')
+                    raise FetchError('429', reason=response.reason, ip=ip,
+                                    error_message='Tor exit node overutilized after multiple retries')
+
+                # Tor: get new identity and retry
+                logger.info(f'Rate limited. Getting new Tor identity... (IP: {ip})')
+                error = tor_manager.new_identity(start_time)
+                if error:
+                    raise FetchError(
+                        '429', reason=response.reason, ip=ip,
+                        error_message='Automatic circuit change: ' + error)
+                continue  # retry with new identity
+
+            # Check for client errors (400, 404) - don't retry these
+            if response.status == 400:
+                logger.error(f'Bad Request (400) - Invalid parameters or URL: {url[:100]}')
+                raise FetchError('400', reason='Bad Request - Invalid parameters or URL format', ip=None)
+
+            if response.status == 404:
+                logger.warning(f'Not Found (404): {url[:100]}')
+                raise FetchError('404', reason='Not Found', ip=None)
+
+            # Check for other server errors (503, 502, 504)
+            if response.status in (502, 503, 504):
+                if attempt >= max_retries - 1:
+                    logger.error(f'Server error {response.status} after {max_retries} retries')
+                    raise FetchError(str(response.status), reason=response.reason, ip=None)
+
+                # Exponential backoff for server errors
+                delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
+                logger.warning(f'Server error ({response.status}). Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
+                time.sleep(delay)
+                continue
+
+            # Success - break out of retry loop
+            break
+
+        except urllib3.exceptions.MaxRetryError as e:
+            # If this is the last attempt, raise the error
+            if attempt >= max_retries - 1:
+                exception_cause = e.__context__.__context__
+                if (isinstance(exception_cause, socks.ProxyConnectionError)
+                        and settings.route_tor):
+                    msg = ('Failed to connect to Tor. Check that Tor is open and '
+                           'that your internet connection is working.\n\n'
+                           + str(e))
+                    logger.error(f'Tor connection failed: {msg}')
+                    raise FetchError('502', reason='Bad Gateway',
+                                     error_message=msg)
+                elif isinstance(e.__context__,
+                                urllib3.exceptions.NewConnectionError):
+                    msg = 'Failed to establish a connection.\n\n' + str(e)
+                    logger.error(f'Connection failed: {msg}')
+                    raise FetchError(
+                        '502', reason='Bad Gateway',
+                         error_message=msg)
+                else:
+                    raise
+
+            # Wait and retry
+            delay = (base_delay * (2 ** attempt)) + random.uniform(0, 1)
+            logger.warning(f'Connection error. Waiting {delay:.1f}s before retry {attempt + 1}/{max_retries}...')
+            time.sleep(delay)
 
     if report_text:
-        print(report_text, '    Latency:', round(response_time - start_time, 3), '    Read time:', round(read_finish - response_time,3))
+        logger.info(f'{report_text} - Latency: {round(response_time - start_time, 3)}s - Read time: {round(read_finish - response_time, 3)}s')
 
     return content
 
@@ -394,7 +465,6 @@ def head(url, use_tor=False, report_text=None, max_redirects=10):
             round(time.monotonic() - start_time, 3))
     return response
 
-
 mobile_user_agent = 'Mozilla/5.0 (Linux; Android 7.0; Redmi Note 4 Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Mobile Safari/537.36'
 mobile_ua = (('User-Agent', mobile_user_agent),)
 desktop_user_agent = 'Mozilla/5.0 (Windows NT 6.1; rv:52.0) Gecko/20100101 Firefox/52.0'
@@ -404,13 +474,13 @@ desktop_xhr_headers = (
     ('Accept', '*/*'),
     ('Accept-Language', 'en-US,en;q=0.5'),
     ('X-YouTube-Client-Name', '1'),
-    ('X-YouTube-Client-Version', '2.20180830'),
+    ('X-YouTube-Client-Version', '2.20240304.00.00'),
 ) + desktop_ua
 mobile_xhr_headers = (
     ('Accept', '*/*'),
     ('Accept-Language', 'en-US,en;q=0.5'),
     ('X-YouTube-Client-Name', '2'),
-    ('X-YouTube-Client-Version', '2.20180830'),
+    ('X-YouTube-Client-Version', '2.20240304.08.00'),
 ) + mobile_ua
 
 
@@ -462,21 +532,31 @@ class RateLimitedQueue(gevent.queue.Queue):
 
 
 def download_thumbnail(save_directory, video_id):
-    url = "https://i.ytimg.com/vi/" + video_id + "/mqdefault.jpg"
     save_location = os.path.join(save_directory, video_id + ".jpg")
-    try:
+    for quality in ('hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'):
-        thumbnail = fetch_url(url, report_text="Saved thumbnail: " + video_id)
+        url = f"https://i.ytimg.com/vi/{video_id}/{quality}"
-    except urllib.error.HTTPError as e:
+        try:
-        print("Failed to download thumbnail for " + video_id + ": " + str(e))
+            thumbnail = fetch_url(url, report_text="Saved thumbnail: " + video_id)
-        return False
+        except FetchError as e:
-    try:
+            if '404' in str(e):
-        f = open(save_location, 'wb')
+                continue
-    except FileNotFoundError:
+            print("Failed to download thumbnail for " + video_id + ": " + str(e))
-        os.makedirs(save_directory, exist_ok=True)
+            return False
-        f = open(save_location, 'wb')
+        except urllib.error.HTTPError as e:
-    f.write(thumbnail)
+            if e.code == 404:
-    f.close()
+                continue
-    return True
+            print("Failed to download thumbnail for " + video_id + ": " + str(e))
+            return False
+        try:
+            f = open(save_location, 'wb')
+        except FileNotFoundError:
+            os.makedirs(save_directory, exist_ok=True)
+            f = open(save_location, 'wb')
+        f.write(thumbnail)
+        f.close()
+        return True
+    print("No thumbnail available for " + video_id)
+    return False
 
 
 def download_thumbnails(save_directory, ids):
@@ -502,9 +582,40 @@ def video_id(url):
     return urllib.parse.parse_qs(url_parts.query)['v'][0]
 
 
-# default, sddefault, mqdefault, hqdefault, hq720
+def get_thumbnail_url(video_id, quality='hq720'):
-def get_thumbnail_url(video_id):
+    """Get thumbnail URL with fallback to lower quality if needed.
-    return settings.img_prefix + "https://i.ytimg.com/vi/" + video_id + "/mqdefault.jpg"
+
+    Args:
+        video_id: YouTube video ID
+        quality: Preferred quality ('maxres', 'hq720', 'sd', 'hq', 'mq', 'default')
+
+    Returns:
+        Tuple of (best_available_url, quality_used)
+    """
+    # Quality priority order (highest to lowest)
+    quality_order = {
+        'maxres': ['maxresdefault.jpg', 'sddefault.jpg', 'hqdefault.jpg'],
+        'hq720': ['hq720.jpg', 'sddefault.jpg', 'hqdefault.jpg'],
+        'sd': ['sddefault.jpg', 'hqdefault.jpg'],
+        'hq': ['hqdefault.jpg', 'mqdefault.jpg'],
+        'mq': ['mqdefault.jpg', 'default.jpg'],
+        'default': ['default.jpg'],
+    }
+
+    qualities = quality_order.get(quality, quality_order['hq720'])
+    base_url = f"{settings.img_prefix}https://i.ytimg.com/vi/{video_id}/"
+
+    # For now, return the highest quality URL
+    # The browser will handle 404s gracefully with alt text
+    return base_url + qualities[0], qualities[0]
+
+
+def get_best_thumbnail_url(video_id):
+    """Get the best available thumbnail URL for a video.
+
+    Tries hq720 first (for HD videos), falls back to sddefault for SD videos.
+    """
+    return get_thumbnail_url(video_id, quality='hq720')[0]
 
 
 def seconds_to_timestamp(seconds):
@@ -538,6 +649,12 @@ def prefix_url(url):
     if url is None:
         return None
     url = url.lstrip('/')     # some urls have // before them, which has a special meaning
+
+    # Increase resolution for YouTube channel avatars
+    if url and ('ggpht.com' in url or 'yt3.ggpht.com' in url):
+        # Replace size parameter with higher resolution (s240 instead of s88)
+        url = re.sub(r'=s\d+-c-k', '=s240-c-k-c0x00ffffff-no-rj', url)
+
     return '/' + url
 
 
@@ -665,8 +782,185 @@ def to_valid_filename(name):
     return name
 
 
+# https://github.com/yt-dlp/yt-dlp/blob/master/yt_dlp/extractor/youtube.py#L72
+INNERTUBE_CLIENTS = {
+    'android': {
+        'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'hl': 'en',
+                'gl': 'US',
+                'clientName': 'ANDROID',
+                'clientVersion': '19.09.36',
+                'osName': 'Android',
+                'osVersion': '12',
+                'androidSdkVersion': 31,
+                'platform': 'MOBILE',
+                'userAgent': 'com.google.android.youtube/19.09.36 (Linux; U; Android 12; US) gzip'
+            },
+            # https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-887739287
+            #'thirdParty': {
+            #    'embedUrl': 'https://google.com',  # Can be any valid URL
+            #}
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
+        'REQUIRE_JS_PLAYER': False,
+    },
+
+    'android-test-suite': {
+        'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'hl': 'en',
+                'gl': 'US',
+                'clientName': 'ANDROID_TESTSUITE',
+                'clientVersion': '1.9',
+                'osName': 'Android',
+                'osVersion': '12',
+                'androidSdkVersion': 31,
+                'platform': 'MOBILE',
+                'userAgent': 'com.google.android.youtube/1.9 (Linux; U; Android 12; US) gzip'
+            },
+            # https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-887739287
+            #'thirdParty': {
+            #    'embedUrl': 'https://google.com',  # Can be any valid URL
+            #}
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
+        'REQUIRE_JS_PLAYER': False,
+    },
+
+    'ios': {
+        'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'hl': 'en',
+                'gl': 'US',
+                'clientName': 'IOS',
+                'clientVersion': '21.03.2',
+                'deviceMake': 'Apple',
+                'deviceModel': 'iPhone16,2',
+                'osName': 'iPhone',
+                'osVersion': '18.7.2.22H124',
+                'userAgent': 'com.google.ios.youtube/21.03.2 (iPhone16,2; U; CPU iOS 18_7_2 like Mac OS X)'
+            }
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
+        'REQUIRE_JS_PLAYER': False
+    },
+
+    # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
+    # See: https://github.com/zerodytrash/YouTube-Internal-Clients
+    'tv_embedded': {
+        'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'hl': 'en',
+                'gl': 'US',
+                'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
+                'clientVersion': '2.0',
+                'clientScreen': 'EMBED',
+            },
+            # https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-887739287
+            'thirdParty': {
+                'embedUrl': 'https://google.com',  # Can be any valid URL
+            }
+
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 85,
+        'REQUIRE_JS_PLAYER': True,
+    },
+
+    'web': {
+        'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'clientName': 'WEB',
+                'clientVersion': '2.20220801.00.00',
+                'userAgent': desktop_user_agent,
+            }
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 1
+    },
+    'android_vr': {
+        'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'clientName': 'ANDROID_VR',
+                'clientVersion': '1.60.19',
+                'deviceMake': 'Oculus',
+                'deviceModel': 'Quest 3',
+                'androidSdkVersion': 32,
+                'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.60.19 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip',
+                'osName': 'Android',
+                'osVersion': '12L',
+            },
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 28,
+        'REQUIRE_JS_PLAYER': False,
+    },
+}
+
+def get_visitor_data():
+    visitor_data = None
+    visitor_data_cache = os.path.join(settings.data_dir, 'visitorData.txt')
+    os.makedirs(settings.data_dir, exist_ok=True)
+    if os.path.isfile(visitor_data_cache):
+        with open(visitor_data_cache, 'r') as file:
+            print('Getting visitor_data from cache')
+            visitor_data = file.read()
+        max_age = 12*3600
+        file_age = time.time() - os.path.getmtime(visitor_data_cache)
+        if file_age > max_age:
+            print('visitor_data cache is too old. Removing file...')
+            os.remove(visitor_data_cache)
+        return visitor_data
+
+    print('Fetching youtube homepage to get visitor_data')
+    yt_homepage = 'https://www.youtube.com'
+    yt_resp = fetch_url(yt_homepage, headers={'User-Agent': mobile_user_agent}, report_text='Getting youtube homepage')
+    visitor_data_re = r'''"visitorData":\s*?"(.+?)"'''
+    visitor_data_match = re.search(visitor_data_re, yt_resp.decode())
+    if visitor_data_match:
+        visitor_data = visitor_data_match.group(1)
+        print(f'Got visitor_data: {len(visitor_data)}')
+        with open(visitor_data_cache, 'w') as file:
+            print('Saving visitor_data cache...')
+            file.write(visitor_data)
+        return visitor_data
+    else:
+        print('Unable to get visitor_data value')
+    return visitor_data
+
+def call_youtube_api(client, api, data):
+    client_params = INNERTUBE_CLIENTS[client]
+    context = client_params['INNERTUBE_CONTEXT']
+    key = client_params['INNERTUBE_API_KEY']
+    host = client_params.get('INNERTUBE_HOST') or 'www.youtube.com'
+    user_agent = context['client'].get('userAgent') or mobile_user_agent
+    visitor_data = get_visitor_data()
+
+    url = 'https://' + host + '/youtubei/v1/' + api + '?key=' + key
+    if visitor_data:
+        context['client'].update({'visitorData': visitor_data})
+    data['context'] = context
+
+    data = json.dumps(data)
+    headers = (('Content-Type', 'application/json'),('User-Agent', user_agent))
+    if visitor_data:
+        headers = ( *headers, ('X-Goog-Visitor-Id', visitor_data ))
+    response = fetch_url(
+        url, data=data, headers=headers,
+        debug_name='youtubei_' + api + '_' + client,
+        report_text='Fetched ' + client + ' youtubei ' + api
+    ).decode('utf-8')
+    return response
+
+
 def strip_non_ascii(string):
     ''' Returns the string without non ASCII characters'''
+    if string is None:
+        return ""
     stripped = (c for c in string if 0 < ord(c) < 127)
     return ''.join(stripped)
 

youtube/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '0.2.3'
+__version__ = 'v0.4.5'

youtube/watch.py

@@ -6,6 +6,9 @@ import settings
 
 from flask import request
 import flask
+import logging
+
+logger = logging.getLogger(__name__)
 
 import json
 import gevent
@@ -19,6 +22,7 @@ from urllib.parse import parse_qs, urlencode
 from types import SimpleNamespace
 from math import ceil
 
+
 try:
     with open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'r') as f:
         decrypt_cache = json.loads(f.read())['decrypt_cache']
@@ -49,6 +53,8 @@ def get_video_sources(info, target_resolution):
     video_only_sources = {}
     uni_sources = []
     pair_sources = []
+
+
     for fmt in info['formats']:
         if not all(fmt[attr] for attr in ('ext', 'url', 'itag')):
             continue
@@ -74,7 +80,6 @@ def get_video_sources(info, target_resolution):
                 fmt['audio_bitrate'] = int(fmt['bitrate']/1000)
             source = {
                 'type': 'audio/' + fmt['ext'],
-                'bitrate': fmt['audio_bitrate'],
                 'quality_string': audio_quality_string(fmt),
             }
             source.update(fmt)
@@ -175,8 +180,34 @@ def make_caption_src(info, lang, auto=False, trans_lang=None):
         label += ' (Automatic)'
     if trans_lang:
         label += ' -> ' + trans_lang
+
+    # Try to use Android caption URL directly (no PO Token needed)
+    caption_url = None
+    for track in info.get('_android_caption_tracks', []):
+        track_lang = track.get('languageCode', '')
+        track_kind = track.get('kind', '')
+        if track_lang == lang and (
+            (auto and track_kind == 'asr') or
+            (not auto and track_kind != 'asr')
+        ):
+            caption_url = track.get('baseUrl')
+            break
+
+    if caption_url:
+        # Add format
+        if '&fmt=' in caption_url:
+            caption_url = re.sub(r'&fmt=[^&]*', '&fmt=vtt', caption_url)
+        else:
+            caption_url += '&fmt=vtt'
+        if trans_lang:
+            caption_url += '&tlang=' + trans_lang
+        url = util.prefix_url(caption_url)
+    else:
+        # Fallback to old method
+        url = util.prefix_url(yt_data_extract.get_caption_url(info, lang, 'vtt', auto, trans_lang))
+
     return {
-        'url': util.prefix_url(yt_data_extract.get_caption_url(info, lang, 'vtt', auto, trans_lang)),
+        'url': url,
         'label': label,
         'srclang': trans_lang[0:2] if trans_lang else lang[0:2],
         'on': False,
@@ -298,24 +329,13 @@ def get_ordered_music_list_attributes(music_list):
 
 
 def save_decrypt_cache():
-    try:
+    os.makedirs(settings.data_dir, exist_ok=True)
-        f = open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'w')
+    f = open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'w')
-    except FileNotFoundError:
-        os.makedirs(settings.data_dir)
-        f = open(os.path.join(settings.data_dir, 'decrypt_function_cache.json'), 'w')
 
     f.write(json.dumps({'version': 1, 'decrypt_cache':decrypt_cache}, indent=4, sort_keys=True))
     f.close()
 
 
-watch_headers = (
-    ('Accept', '*/*'),
-    ('Accept-Language', 'en-US,en;q=0.5'),
-    ('X-YouTube-Client-Name', '2'),
-    ('X-YouTube-Client-Version', '2.20180830'),
-) + util.mobile_ua
-
-
 def decrypt_signatures(info, video_id):
     '''return error string, or False if no errors'''
     if not yt_data_extract.requires_decryption(info):
@@ -346,7 +366,13 @@ def _add_to_error(info, key, additional_message):
         info[key] = additional_message
 
 
-def extract_info(video_id, use_invidious, playlist_id=None, index=None):
+def fetch_player_response(client, video_id):
+    return util.call_youtube_api(client, 'player', {
+        'videoId': video_id,
+    })
+
+
+def fetch_watch_page_info(video_id, playlist_id, index):
     # bpctr=9999999999 will bypass are-you-sure dialogs for controversial
     # videos
     url = 'https://m.youtube.com/embed/' + video_id + '?bpctr=9999999999'
@@ -354,57 +380,74 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
         url += '&list=' + playlist_id
     if index:
         url += '&index=' + index
-    watch_page = util.fetch_url(url, headers=watch_headers,
+
+    headers = (
+        ('Accept', '*/*'),
+        ('Accept-Language', 'en-US,en;q=0.5'),
+        ('X-YouTube-Client-Name', '2'),
+        ('X-YouTube-Client-Version', '2.20180830'),
+    ) + util.mobile_ua
+
+    watch_page = util.fetch_url(url, headers=headers,
                                 debug_name='watch')
     watch_page = watch_page.decode('utf-8')
-    info = yt_data_extract.extract_watch_info_from_html(watch_page)
+    return yt_data_extract.extract_watch_info_from_html(watch_page)
 
-    context = {
+
-        'client': {
+def extract_info(video_id, use_invidious, playlist_id=None, index=None):
-            'clientName': 'ANDROID',
+    primary_client = 'android_vr'
-            'clientVersion': '16.20',
+    fallback_client = 'ios'
-            'gl': 'US',
+    last_resort_client = 'tv_embedded'
-            'hl': 'en',
+
-        },
+    tasks = (
-        # https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-887739287
+        # Get video metadata from here
-        'thirdParty': {
+        gevent.spawn(fetch_watch_page_info, video_id, playlist_id, index),
-            'embedUrl': 'https://google.com',  # Can be any valid URL
+        gevent.spawn(fetch_player_response, primary_client, video_id)
-        }
+    )
-    }
+    gevent.joinall(tasks)
-    if info['age_restricted'] or info['player_urls_missing']:
+    util.check_gevent_exceptions(*tasks)
-        if info['age_restricted']:
+
-            print('Age restricted video. Fetching /youtubei/v1/player page')
+    info = tasks[0].value or {}
-        else:
+    player_response = tasks[1].value or {}
-            print('Missing player. Fetching /youtubei/v1/player page')
+
-        context['client']['clientScreen'] = 'EMBED'
+    # Save android_vr caption tracks (no PO Token needed for these URLs)
+    if isinstance(player_response, str):
+        try:
+            pr_data = json.loads(player_response)
+        except Exception:
+            pr_data = {}
     else:
-        print('Fetching /youtubei/v1/player page')
+        pr_data = player_response or {}
+    android_caption_tracks = yt_data_extract.deep_get(
+        pr_data, 'captions', 'playerCaptionsTracklistRenderer',
+        'captionTracks', default=[])
+    info['_android_caption_tracks'] = android_caption_tracks
 
-    # https://github.com/yt-dlp/yt-dlp/issues/574#issuecomment-887171136
+    yt_data_extract.update_with_new_urls(info, player_response)
-    # ANDROID is used instead because its urls don't require decryption
-    # The URLs returned with WEB for videos requiring decryption
-    # couldn't be decrypted with the base.js from the web page for some
-    # reason
-    url ='https://youtubei.googleapis.com/youtubei/v1/player'
-    url += '?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
-    data = {
-        'videoId': video_id,
-        'context': context,
-    }
-    data = json.dumps(data)
-    content_header = (('Content-Type', 'application/json'),)
-    player_response = util.fetch_url(
-        url, data=data, headers=util.mobile_ua + content_header,
-        debug_name='youtubei_player',
-        report_text='Fetched youtubei player page').decode('utf-8')
 
-    yt_data_extract.update_with_age_restricted_info(info, player_response)
+    # Fallback to 'ios' if no valid URLs are found
+    if not info.get('formats') or info.get('player_urls_missing'):
+        print(f"No URLs found in '{primary_client}', attempting with '{fallback_client}'.")
+        try:
+            player_response = fetch_player_response(fallback_client, video_id) or {}
+            yt_data_extract.update_with_new_urls(info, player_response)
+        except util.FetchError as e:
+            print(f"Fallback '{fallback_client}' failed: {e}")
+
+    # Final attempt with 'tv_embedded' if there are still no URLs
+    if not info.get('formats') or info.get('player_urls_missing'):
+        print(f"No URLs found in '{fallback_client}', attempting with '{last_resort_client}'")
+        try:
+            player_response = fetch_player_response(last_resort_client, video_id) or {}
+            yt_data_extract.update_with_new_urls(info, player_response)
+        except util.FetchError as e:
+            print(f"Fallback '{last_resort_client}' failed: {e}")
 
     # signature decryption
-    decryption_error = decrypt_signatures(info, video_id)
+    if info.get('formats'):
-    if decryption_error:
+        decryption_error = decrypt_signatures(info, video_id)
-        decryption_error = 'Error decrypting url signatures: ' + decryption_error
+        if decryption_error:
-        info['playability_error'] = decryption_error
+            info['playability_error'] = 'Error decrypting url signatures: ' + decryption_error
 
     # check if urls ready (non-live format) in former livestream
     # urls not ready if all of them have no filesize
@@ -418,26 +461,26 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
 
     # livestream urls
     # sometimes only the livestream urls work soon after the livestream is over
-    if (info['hls_manifest_url']
+    info['hls_formats'] = []
-        and (info['live'] or not info['formats'] or not info['urls_ready'])
+    if info.get('hls_manifest_url') and (info.get('live') or not info.get('formats') or not info['urls_ready']):
-    ):
+        try:
-        manifest = util.fetch_url(
+            manifest = util.fetch_url(info['hls_manifest_url'],
-            info['hls_manifest_url'],
+                debug_name='hls_manifest.m3u8',
-            debug_name='hls_manifest.m3u8',
+                report_text='Fetched hls manifest'
-            report_text='Fetched hls manifest'
+            ).decode('utf-8')
-        ).decode('utf-8')
+            info['hls_formats'], err = yt_data_extract.extract_hls_formats(manifest)
-
+            if not err:
-        info['hls_formats'], err = yt_data_extract.extract_hls_formats(manifest)
+                info['playability_error'] = None
-        if not err:
+            for fmt in info['hls_formats']:
-            info['playability_error'] = None
+                fmt['video_quality'] = video_quality_string(fmt)
-        for fmt in info['hls_formats']:
+        except Exception as e:
-            fmt['video_quality'] = video_quality_string(fmt)
+            print(f"Error obteniendo HLS manifest: {e}")
-    else:
+            info['hls_formats'] = []
-        info['hls_formats'] = []
 
     # check for 403. Unnecessary for tor video routing b/c ip address is same
     info['invidious_used'] = False
     info['invidious_reload_button'] = False
+    info['tor_bypass_used'] = False
     if (settings.route_tor == 1
             and info['formats'] and info['formats'][0]['url']):
         try:
@@ -451,6 +494,7 @@ def extract_info(video_id, use_invidious, playlist_id=None, index=None):
         if response.status == 403:
             print('Access denied (403) for video urls.')
             print('Routing video through Tor')
+            info['tor_bypass_used'] = True
             for fmt in info['formats']:
                 fmt['url'] += '&use_tor=1'
         elif 300 <= response.status < 400:
@@ -572,8 +616,6 @@ def get_storyboard_vtt():
 
 
 time_table = {'h': 3600, 'm': 60, 's': 1}
-
-
 @yt_app.route('/watch')
 @yt_app.route('/embed')
 @yt_app.route('/embed/<video_id>')
@@ -628,11 +670,22 @@ def get_watch_page(video_id=None):
 
     # prefix urls, and other post-processing not handled by yt_data_extract
     for item in info['related_videos']:
+        # Only set thumbnail if YouTube didn't provide one
+        if not item.get('thumbnail'):
+            if item.get('type') == 'playlist' and item.get('first_video_id'):
+                item['thumbnail'] = "https://i.ytimg.com/vi/{}/hqdefault.jpg".format(item['first_video_id'])
+            elif item.get('type') == 'video' and item.get('id'):
+                item['thumbnail'] = "https://i.ytimg.com/vi/{}/hqdefault.jpg".format(item['id'])
         util.prefix_urls(item)
         util.add_extra_html_info(item)
+    for song in info['music_list']:
+        song['url'] = util.prefix_url(song['url'])
     if info['playlist']:
         playlist_id = info['playlist']['id']
         for item in info['playlist']['items']:
+            # Only set thumbnail if YouTube didn't provide one
+            if not item.get('thumbnail') and item.get('type') == 'video' and item.get('id'):
+                item['thumbnail'] = "https://i.ytimg.com/vi/{}/hqdefault.jpg".format(item['id'])
             util.prefix_urls(item)
             util.add_extra_html_info(item)
             if playlist_id:
@@ -659,12 +712,6 @@ def get_watch_page(video_id=None):
             '/videoplayback',
             '/videoplayback/name/' + filename)
 
-    if settings.gather_googlevideo_domains:
-        with open(os.path.join(settings.data_dir, 'googlevideo-domains.txt'), 'a+', encoding='utf-8') as f:
-            url = info['formats'][0]['url']
-            subdomain = url[0:url.find(".googlevideo.com")]
-            f.write(subdomain + "\n")
-
     download_formats = []
 
     for format in (info['formats'] + info['hls_formats']):
@@ -681,20 +728,19 @@ def get_watch_page(video_id=None):
             'codecs': codecs_string,
         })
 
-    target_resolution = settings.default_resolution
+    if (settings.route_tor == 2) or info['tor_bypass_used']:
+        target_resolution = 240
+    else:
+        target_resolution = settings.default_resolution
+
     source_info = get_video_sources(info, target_resolution)
     uni_sources = source_info['uni_sources']
     pair_sources = source_info['pair_sources']
     uni_idx, pair_idx = source_info['uni_idx'], source_info['pair_idx']
-    video_height = yt_data_extract.deep_get(source_info, 'uni_sources',
-                                            uni_idx, 'height',
-                                            default=360)
-    video_width = yt_data_extract.deep_get(source_info, 'uni_sources',
-                                           uni_idx, 'width',
-                                           default=640)
 
     pair_quality = yt_data_extract.deep_get(pair_sources, pair_idx, 'quality')
     uni_quality = yt_data_extract.deep_get(uni_sources, uni_idx, 'quality')
+
     pair_error = abs((pair_quality or 360) - target_resolution)
     uni_error = abs((uni_quality or 360) - target_resolution)
     if uni_error == pair_error:
@@ -704,9 +750,18 @@ def get_watch_page(video_id=None):
         closer_to_target = 'uni'
     else:
         closer_to_target = 'pair'
-    using_pair_sources = (
+
-        bool(pair_sources) and (not uni_sources or closer_to_target == 'pair')
+    if settings.prefer_uni_sources == 2:
-    )
+        # Use uni sources unless there's no choice.
+        using_pair_sources = (
+            bool(pair_sources) and (not uni_sources)
+        )
+    else:
+        # Use the pair sources if they're closer to the desired resolution
+        using_pair_sources = (
+            bool(pair_sources)
+            and (not uni_sources or closer_to_target == 'pair')
+        )
     if using_pair_sources:
         video_height = pair_sources[pair_idx]['height']
         video_width = pair_sources[pair_idx]['width']
@@ -718,6 +773,8 @@ def get_watch_page(video_id=None):
             uni_sources, uni_idx, 'width', default=640
         )
 
+
+
     # 1 second per pixel, or the actual video width
     theater_video_target_width = max(640, info['duration'] or 0, video_width)
 
@@ -750,14 +807,13 @@ def get_watch_page(video_id=None):
         template_name = 'embed.html'
     else:
         template_name = 'watch.html'
-    return flask.render_template(
+    return flask.render_template(template_name,
-        template_name,
+        header_playlist_names   = local_playlist.get_playlist_names(),
-        header_playlist_names = local_playlist.get_playlist_names(),
+        uploader_channel_url    = ('/' + info['author_url']) if info['author_url'] else '',
-        uploader_channel_url = ('/' + info['author_url']) if info['author_url'] else '',
+        time_published             = info['time_published'],
-        time_published = info['time_published'],
-        time_published_utc=time_utc_isoformat(info['time_published']),
         view_count    = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("view_count", None)),
         like_count    = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("like_count", None)),
+        dislike_count = (lambda x: '{:,}'.format(x) if x is not None else "")(info.get("dislike_count", None)),
         download_formats        = download_formats,
         other_downloads         = other_downloads,
         video_info              = json.dumps(video_info),
@@ -806,7 +862,7 @@ def get_watch_page(video_id=None):
             'related': info['related_videos'],
             'playability_error': info['playability_error'],
         },
-        font_family=youtube.font_choices[settings.font],
+        font_family = youtube.font_choices[settings.font], # for embed page
         **source_info,
         using_pair_sources = using_pair_sources,
     )
@@ -814,9 +870,14 @@ def get_watch_page(video_id=None):
 
 @yt_app.route('/api/<path:dummy>')
 def get_captions(dummy):
-    result = util.fetch_url('https://www.youtube.com' + request.full_path)
+    url = 'https://www.youtube.com' + request.full_path
-    result = result.replace(b"align:start position:0%", b"")
+    try:
-    return result
+        result = util.fetch_url(url, headers=util.mobile_ua)
+        result = result.replace(b"align:start position:0%", b"")
+        return flask.Response(result, mimetype='text/vtt')
+    except Exception as e:
+        logger.debug(f'Caption fetch failed: {e}')
+        return flask.Response(b'WEBVTT\n\n', mimetype='text/vtt', status=200)
 
 
 times_reg = re.compile(r'^\d\d:\d\d:\d\d\.\d\d\d --> \d\d:\d\d:\d\d\.\d\d\d.*$')

youtube/yt_data_extract/__init__.py

@@ -7,7 +7,7 @@ from .everything_else import (extract_channel_info, extract_search_info,
     extract_playlist_metadata, extract_playlist_info, extract_comments_info)
 
 from .watch_extraction import (extract_watch_info, get_caption_url,
-    update_with_age_restricted_info, requires_decryption,
+    update_with_new_urls, requires_decryption,
     extract_decryption_function, decrypt_signatures, _formats,
     update_format_with_type_info, extract_hls_formats,
     extract_watch_info_from_html, captions_available)

youtube/yt_data_extract/common.py

@@ -109,7 +109,7 @@ def concat_or_none(*strings):
 def remove_redirect(url):
     if url is None:
         return None
-    if re.fullmatch(r'(((https?:)?//)?(www.)?youtube.com)?/redirect\?.*', url) is not None: # youtube puts these on external links to do tracking
+    if re.fullmatch(r'(((https?:)?//)?(www.)?youtube.com)?/redirect\?.*', url) is not None: # YouTube puts these on external links to do tracking
         query_string = url[url.find('?')+1: ]
         return urllib.parse.parse_qs(query_string)['q'][0]
     return url
@@ -133,11 +133,11 @@ def _recover_urls(runs):
     for run in runs:
         url = deep_get(run, 'navigationEndpoint', 'urlEndpoint', 'url')
         text = run.get('text', '')
-        # second condition is necessary because youtube makes other things into urls, such as hashtags, which we want to keep as text
+        # second condition is necessary because YouTube makes other things into urls, such as hashtags, which we want to keep as text
         if url is not None and (text.startswith('http://') or text.startswith('https://')):
             url = remove_redirect(url)
             run['url'] = url
-            run['text'] = url # youtube truncates the url text, use actual url instead
+            run['text'] = url # YouTube truncates the url text, use actual url instead
 
 def extract_str(node, default=None, recover_urls=False):
     '''default is the value returned if the extraction fails. If recover_urls is true, will attempt to fix YouTube's truncation of url text (most prominently seen in descriptions)'''
@@ -185,7 +185,7 @@ def extract_int(string, default=None, whole_word=True):
         return default
 
 def extract_approx_int(string):
-    '''e.g. "15.1M" from "15.1M subscribers"'''
+    '''e.g. "15.1M" from "15.1M subscribers" or '4,353' from 4353'''
     if not isinstance(string, str):
         string = extract_str(string)
     if not string:
@@ -193,7 +193,10 @@ def extract_approx_int(string):
     match = re.search(r'\b(\d+(?:\.\d+)?[KMBTkmbt]?)\b', string.replace(',', ''))
     if match is None:
         return None
-    return match.group(1)
+    result = match.group(1)
+    if re.fullmatch(r'\d+', result):
+        result = '{:,}'.format(int(result))
+    return result
 
 MONTH_ABBREVIATIONS = {'jan':'1', 'feb':'2', 'mar':'3', 'apr':'4', 'may':'5', 'jun':'6', 'jul':'7', 'aug':'8', 'sep':'9', 'oct':'10', 'nov':'11', 'dec':'12'}
 def extract_date(date_text):
@@ -223,6 +226,190 @@ def check_missing_keys(object, *key_sequences):
 
     return None
 
+
+def extract_lockup_view_model_info(item, additional_info={}):
+    """Extract info from new lockupViewModel format (YouTube 2024+)"""
+    info = {'error': None}
+
+    content_type = item.get('contentType', '')
+    content_id = item.get('contentId', '')
+
+    # Extract title from metadata
+    metadata = item.get('metadata', {})
+    lockup_metadata = metadata.get('lockupMetadataViewModel', {})
+    title_data = lockup_metadata.get('title', {})
+    info['title'] = title_data.get('content', '')
+
+    # Determine type based on contentType
+    if 'PLAYLIST' in content_type or 'PODCAST' in content_type:
+        info['type'] = 'playlist'
+        info['playlist_type'] = 'playlist'
+        info['id'] = content_id
+        info['video_count'] = None
+        info['first_video_id'] = None
+
+        # Try to get video count from metadata
+        metadata_rows = lockup_metadata.get('metadata', {})
+        for row in metadata_rows.get('contentMetadataViewModel', {}).get('metadataRows', []):
+            for part in row.get('metadataParts', []):
+                text = part.get('text', {}).get('content', '')
+                if 'video' in text.lower() or 'episode' in text.lower():
+                    info['video_count'] = extract_int(text)
+    elif 'VIDEO' in content_type:
+        info['type'] = 'video'
+        info['id'] = content_id
+        info['view_count'] = None
+        info['approx_view_count'] = None
+        info['time_published'] = None
+        info['duration'] = None
+
+        # Extract duration/other info from metadata rows
+        metadata_rows = lockup_metadata.get('metadata', {})
+        for row in metadata_rows.get('contentMetadataViewModel', {}).get('metadataRows', []):
+            for part in row.get('metadataParts', []):
+                text = part.get('text', {}).get('content', '')
+                if 'view' in text.lower():
+                    info['approx_view_count'] = extract_approx_int(text)
+                elif 'ago' in text.lower():
+                    info['time_published'] = text
+    elif 'CHANNEL' in content_type:
+        info['type'] = 'channel'
+        info['id'] = content_id
+        info['approx_subscriber_count'] = None
+        info['video_count'] = None
+
+        # Extract subscriber count and video count from metadata rows
+        metadata_rows = lockup_metadata.get('metadata', {})
+        for row in metadata_rows.get('contentMetadataViewModel', {}).get('metadataRows', []):
+            for part in row.get('metadataParts', []):
+                text = part.get('text', {}).get('content', '')
+                if 'subscriber' in text.lower():
+                    info['approx_subscriber_count'] = extract_approx_int(text)
+                elif 'video' in text.lower():
+                    info['video_count'] = extract_int(text)
+    else:
+        info['type'] = 'unsupported'
+        return info
+
+    # Extract thumbnail from contentImage
+    content_image = item.get('contentImage', {})
+    info['thumbnail'] = normalize_url(multi_deep_get(content_image,
+        # playlists with collection thumbnail
+        ['collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image', 'sources', 0, 'url'],
+        # single thumbnail (some playlists, videos)
+        ['thumbnailViewModel', 'image', 'sources', 0, 'url'],
+    )) or ''
+
+    # Extract video/episode count from thumbnail overlay badges
+    # (podcasts and some playlists put the count here instead of metadata rows)
+    thumb_vm = multi_deep_get(content_image,
+        ['collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel'],
+        ['thumbnailViewModel'],
+    ) or {}
+    for overlay in thumb_vm.get('overlays', []):
+        for badge in deep_get(overlay, 'thumbnailOverlayBadgeViewModel', 'thumbnailBadges', default=[]):
+            badge_text = deep_get(badge, 'thumbnailBadgeViewModel', 'text', default='')
+            if badge_text and not info.get('video_count'):
+                conservative_update(info, 'video_count', extract_int(badge_text))
+
+    # Extract author info if available
+    info['author'] = None
+    info['author_id'] = None
+    info['author_url'] = None
+    info['description'] = None
+    info['badges'] = []
+
+    # Try to get first video ID from inline player data
+    item_playback = item.get('itemPlayback', {})
+    inline_player = item_playback.get('inlinePlayerData', {})
+    on_select = inline_player.get('onSelect', {})
+    innertube_cmd = on_select.get('innertubeCommand', {})
+    watch_endpoint = innertube_cmd.get('watchEndpoint', {})
+    if watch_endpoint.get('videoId'):
+        info['first_video_id'] = watch_endpoint.get('videoId')
+
+    info.update(additional_info)
+    return info
+
+
+def extract_shorts_lockup_view_model_info(item, additional_info={}):
+    """Extract info from shortsLockupViewModel format (YouTube Shorts)"""
+    info = {'error': None, 'type': 'video'}
+
+    # Video ID from reelWatchEndpoint or entityId
+    info['id'] = deep_get(item,
+        'onTap', 'innertubeCommand', 'reelWatchEndpoint', 'videoId')
+    if not info['id']:
+        entity_id = item.get('entityId', '')
+        if entity_id.startswith('shorts-shelf-item-'):
+            info['id'] = entity_id[len('shorts-shelf-item-'):]
+
+    # Thumbnail
+    info['thumbnail'] = normalize_url(deep_get(item,
+        'onTap', 'innertubeCommand', 'reelWatchEndpoint',
+        'thumbnail', 'thumbnails', 0, 'url'))
+
+    # Parse title and views from accessibilityText
+    # Format: "Title, N views - play Short"
+    acc_text = item.get('accessibilityText', '')
+    info['title'] = ''
+    info['view_count'] = None
+    info['approx_view_count'] = None
+    if acc_text:
+        # Remove trailing " - play Short"
+        cleaned = re.sub(r'\s*-\s*play Short$', '', acc_text)
+        # Split on last comma+views pattern to separate title from view count
+        match = re.match(r'^(.*?),\s*([\d,.]+\s*(?:thousand|million|billion|)\s*views?)$',
+                         cleaned, re.IGNORECASE)
+        if match:
+            info['title'] = match.group(1).strip()
+            view_text = match.group(2)
+            info['view_count'] = extract_int(view_text)
+            # Convert "7.1 thousand" -> "7.1 K" for display
+            suffix_map = {'thousand': 'K', 'million': 'M', 'billion': 'B'}
+            suffix_match = re.search(r'([\d,.]+)\s*(thousand|million|billion)?', view_text, re.IGNORECASE)
+            if suffix_match:
+                num = suffix_match.group(1)
+                word = suffix_match.group(2)
+                if word:
+                    info['approx_view_count'] = num + ' ' + suffix_map[word.lower()]
+                else:
+                    info['approx_view_count'] = '{:,}'.format(int(num.replace(',', ''))) if num.isdigit() or num.replace(',','').isdigit() else num
+            else:
+                info['approx_view_count'] = extract_approx_int(view_text)
+        else:
+            # Fallback: try "N views" at end
+            match2 = re.match(r'^(.*?),\s*(.+views?)$', cleaned, re.IGNORECASE)
+            if match2:
+                info['title'] = match2.group(1).strip()
+                info['approx_view_count'] = extract_approx_int(match2.group(2))
+            else:
+                info['title'] = cleaned
+
+    # Overlay text (usually has the title too)
+    overlay_metadata = deep_get(item, 'overlayMetadata',
+        'secondaryText', 'content')
+    if overlay_metadata and not info['approx_view_count']:
+        info['approx_view_count'] = extract_approx_int(overlay_metadata)
+
+    primary_text = deep_get(item, 'overlayMetadata',
+        'primaryText', 'content')
+    if primary_text and not info['title']:
+        info['title'] = primary_text
+
+    info['duration'] = ''
+    info['time_published'] = None
+    info['description'] = None
+    info['badges'] = []
+    info['author'] = None
+    info['author_id'] = None
+    info['author_url'] = None
+    info['index'] = None
+
+    info.update(additional_info)
+    return info
+
+
 def extract_item_info(item, additional_info={}):
     if not item:
         return {'error': 'No item given'}
@@ -240,6 +427,14 @@ def extract_item_info(item, additional_info={}):
         info['type'] = 'unsupported'
         return info
 
+    # Handle new lockupViewModel format (YouTube 2024+)
+    if type == 'lockupViewModel':
+        return extract_lockup_view_model_info(item, additional_info)
+
+    # Handle shortsLockupViewModel format (YouTube Shorts)
+    if type == 'shortsLockupViewModel':
+        return extract_shorts_lockup_view_model_info(item, additional_info)
+
     # type looks like e.g. 'compactVideoRenderer' or 'gridVideoRenderer'
     # camelCase split, https://stackoverflow.com/a/37697078
     type_parts = [s.lower() for s in re.sub(r'([A-Z][a-z]+)', r' \1', type).split()]
@@ -249,6 +444,9 @@ def extract_item_info(item, additional_info={}):
     primary_type = type_parts[-2]
     if primary_type == 'video':
         info['type'] = 'video'
+    elif type_parts[0] == 'reel': # shorts
+        info['type'] = 'video'
+        primary_type = 'video'
     elif primary_type in ('playlist', 'radio', 'show'):
         info['type'] = 'playlist'
         info['playlist_type'] = primary_type
@@ -276,9 +474,9 @@ def extract_item_info(item, additional_info={}):
         ['detailedMetadataSnippets', 0, 'snippetText'],
     ))
     info['thumbnail'] = normalize_url(multi_deep_get(item,
-        ['thumbnail', 'thumbnails', 0, 'url'],      # videos
+        ['thumbnail', 'thumbnails', -1, 'url'],      # videos (highest quality)
-        ['thumbnails', 0, 'thumbnails', 0, 'url'],  # playlists
+        ['thumbnails', 0, 'thumbnails', -1, 'url'],  # playlists
-        ['thumbnailRenderer', 'showCustomThumbnailRenderer', 'thumbnail', 'thumbnails', 0, 'url'], # shows
+        ['thumbnailRenderer', 'showCustomThumbnailRenderer', 'thumbnail', 'thumbnails', -1, 'url'], # shows
     ))
 
     info['badges'] = []
@@ -295,7 +493,11 @@ def extract_item_info(item, additional_info={}):
             info['time_published'] = timestamp.group(1)
 
     if primary_type == 'video':
-        info['id'] = item.get('videoId')
+        info['id'] = multi_deep_get(item,
+            ['videoId'],
+            ['navigationEndpoint', 'watchEndpoint', 'videoId'],
+            ['navigationEndpoint', 'reelWatchEndpoint', 'videoId'] # shorts
+        )
         info['view_count'] = extract_int(item.get('viewCountText'))
 
         # dig into accessibility data to get view_count for videos marked as recommended, and to get time_published
@@ -313,17 +515,35 @@ def extract_item_info(item, additional_info={}):
         if info['view_count']:
             info['approx_view_count'] = '{:,}'.format(info['view_count'])
         else:
-            info['approx_view_count'] = extract_approx_int(item.get('shortViewCountText'))
+            info['approx_view_count'] = extract_approx_int(multi_get(item,
+                'shortViewCountText',
+                'viewCountText' # shorts
+            ))
 
         # handle case where it is "No views"
         if not info['approx_view_count']:
             if ('No views' in item.get('shortViewCountText', '')
-                    or 'no views' in accessibility_label.lower()):
+                    or 'no views' in accessibility_label.lower()
+                    or 'No views' in extract_str(item.get('viewCountText', '')) # shorts
+            ):
                 info['view_count'] = 0
                 info['approx_view_count'] = '0'
 
         info['duration'] = extract_str(item.get('lengthText'))
 
+        # dig into accessibility data to get duration for shorts
+        accessibility_label = deep_get(item,
+            'accessibility', 'accessibilityData', 'label',
+            default='')
+        duration = re.search(r'(\d+) (second|seconds|minute) - play video$',
+                            accessibility_label)
+        if duration:
+            if duration.group(2) == 'minute':
+                conservative_update(info, 'duration', '1:00')
+            else:
+                conservative_update(info,
+                    'duration', '0:' + duration.group(1).zfill(2))
+
         # if it's an item in a playlist, get its index
         if 'index' in item: # url has wrong index on playlist page
             info['index'] = extract_int(item.get('index'))
@@ -348,6 +568,13 @@ def extract_item_info(item, additional_info={}):
     elif primary_type == 'channel':
         info['id'] = item.get('channelId')
         info['approx_subscriber_count'] = extract_approx_int(item.get('subscriberCountText'))
+        # YouTube sometimes puts the handle (@name) in subscriberCountText
+        # instead of the actual count. Fall back to accessibility data.
+        if not info['approx_subscriber_count']:
+            acc_label = deep_get(item, 'subscriberCountText',
+                'accessibility', 'accessibilityData', 'label', default='')
+            if 'subscriber' in acc_label.lower():
+                info['approx_subscriber_count'] = extract_approx_int(acc_label)
     elif primary_type == 'show':
         info['id'] = deep_get(item, 'navigationEndpoint', 'watchEndpoint', 'playlistId')
         info['first_video_id'] = deep_get(item, 'navigationEndpoint',
@@ -395,6 +622,8 @@ _item_types = {
     'gridVideoRenderer',
     'playlistVideoRenderer',
 
+    'reelItemRenderer',
+
     'playlistRenderer',
     'compactPlaylistRenderer',
     'gridPlaylistRenderer',
@@ -411,6 +640,10 @@ _item_types = {
     'channelRenderer',
     'compactChannelRenderer',
     'gridChannelRenderer',
+
+    # New viewModel format (YouTube 2024+)
+    'lockupViewModel',
+    'shortsLockupViewModel',
 }
 
 def _traverse_browse_renderer(renderer):
@@ -542,9 +775,13 @@ def extract_items(response, item_types=_item_types,
                     item_types=item_types)
                 if items:
                     break
-    elif 'onResponseReceivedEndpoints' in response:
+    if ('onResponseReceivedEndpoints' in response
-        for endpoint in response.get('onResponseReceivedEndpoints', []):
+          or 'onResponseReceivedActions' in response):
-            items, ctoken = extract_items_from_renderer_list(
+        for endpoint in multi_get(response,
+                                  'onResponseReceivedEndpoints',
+                                  'onResponseReceivedActions',
+                                  []):
+            new_items, new_ctoken = extract_items_from_renderer_list(
                 multi_deep_get(
                     endpoint,
                     ['reloadContinuationItemsCommand', 'continuationItems'],
@@ -553,13 +790,17 @@ def extract_items(response, item_types=_item_types,
                 ),
                 item_types=item_types,
             )
-            if items:
+            items += new_items
-                break
+            if (not ctoken) or (new_ctoken and new_items):
-    elif 'contents' in response:
+                ctoken = new_ctoken
+    if 'contents' in response:
         renderer = get(response, 'contents', {})
-        items, ctoken = extract_items_from_renderer(
+        new_items, new_ctoken = extract_items_from_renderer(
             renderer,
             item_types=item_types)
+        items += new_items
+        if (not ctoken) or (new_ctoken and new_items):
+            ctoken = new_ctoken
 
     if search_engagement_panels and 'engagementPanels' in response:
         new_items, new_ctoken = extract_items_from_renderer_list(

youtube/yt_data_extract/everything_else.py

@@ -9,7 +9,7 @@ import re
 import urllib
 from math import ceil
 
-def extract_channel_info(polymer_json, tab):
+def extract_channel_info(polymer_json, tab, continuation=False):
     response, err = extract_response(polymer_json)
     if err:
         return {'error': err}
@@ -23,7 +23,8 @@ def extract_channel_info(polymer_json, tab):
 
     # channel doesn't exist or was terminated
     # example terminated channel: https://www.youtube.com/channel/UCnKJeK_r90jDdIuzHXC0Org
-    if not metadata:
+    # metadata and microformat are not present for continuation requests
+    if not metadata and not continuation:
         if response.get('alerts'):
             error_string = ' '.join(
                 extract_str(deep_get(alert, 'alertRenderer', 'text'), default='')
@@ -44,7 +45,7 @@ def extract_channel_info(polymer_json, tab):
     info['approx_subscriber_count'] = extract_approx_int(deep_get(response,
         'header', 'c4TabbedHeaderRenderer', 'subscriberCountText'))
 
-    # stuff from microformat (info given by youtube for every page on channel)
+    # stuff from microformat (info given by youtube for first page on channel)
     info['short_description'] = metadata.get('description')
     if info['short_description'] and len(info['short_description']) > 730:
         info['short_description'] = info['short_description'][0:730] + '...'
@@ -69,10 +70,10 @@ def extract_channel_info(polymer_json, tab):
     info['ctoken'] = None
 
     # empty channel
-    if 'contents' not in response and 'continuationContents' not in response:
+    #if 'contents' not in response and 'continuationContents' not in response:
-        return info
+    #    return info
 
-    if tab in ('videos', 'playlists', 'search'):
+    if tab in ('videos', 'shorts', 'streams', 'playlists', 'search'):
         items, ctoken = extract_items(response)
         additional_info = {
             'author': info['channel_name'],
@@ -84,23 +85,84 @@ def extract_channel_info(polymer_json, tab):
         if tab in ('search', 'playlists'):
             info['is_last_page'] = (ctoken is None)
     elif tab == 'about':
-        items, _ = extract_items(response, item_types={'channelAboutFullMetadataRenderer'})
+        # Latest type
-        if not items:
+        items, _ = extract_items(response, item_types={'aboutChannelRenderer'})
-            info['error'] = 'Could not find channelAboutFullMetadataRenderer'
+        if items:
-            return info
+            a_metadata = deep_get(items, 0, 'aboutChannelRenderer',
-        channel_metadata = items[0]['channelAboutFullMetadataRenderer']
+                'metadata', 'aboutChannelViewModel')
+            if not a_metadata:
+                info['error'] = 'Could not find aboutChannelViewModel'
+                return info
 
-        info['links'] = []
+            info['links'] = []
-        for link_json in channel_metadata.get('primaryLinks', ()):
+            for link_outer in a_metadata.get('links', ()):
-            url = remove_redirect(deep_get(link_json, 'navigationEndpoint', 'urlEndpoint', 'url'))
+                link = link_outer.get('channelExternalLinkViewModel') or {}
-            if not (url.startswith('http://') or url.startswith('https://')):
+                link_content = extract_str(deep_get(link, 'link', 'content'))
-                url = 'http://' + url
+                for run in deep_get(link, 'link', 'commandRuns') or ():
-            text = extract_str(link_json.get('title'))
+                    url = remove_redirect(deep_get(run, 'onTap',
-            info['links'].append( (text, url) )
+                        'innertubeCommand', 'urlEndpoint', 'url'))
+                    if url and not (url.startswith('http://')
+                            or url.startswith('https://')):
+                        url = 'https://' + url
+                    if link_content is None or (link_content in url):
+                        break
+                else: # didn't break
+                    url = link_content
+                    if url and not (url.startswith('http://')
+                            or url.startswith('https://')):
+                        url = 'https://' + url
+                text = extract_str(deep_get(link, 'title', 'content'))
+                info['links'].append( (text, url) )
 
-        info['date_joined'] = extract_date(channel_metadata.get('joinedDateText'))
+            info['date_joined'] = extract_date(
-        info['view_count'] = extract_int(channel_metadata.get('viewCountText'))
+                a_metadata.get('joinedDateText')
-        info['description'] = extract_str(channel_metadata.get('description'), default='')
+            )
+            info['view_count'] = extract_int(a_metadata.get('viewCountText'))
+            info['approx_view_count'] = extract_approx_int(
+                a_metadata.get('viewCountText')
+            )
+            info['description'] = extract_str(
+                a_metadata.get('description'), default=''
+            )
+            info['approx_video_count'] = extract_approx_int(
+                a_metadata.get('videoCountText')
+            )
+            info['approx_subscriber_count'] = extract_approx_int(
+                a_metadata.get('subscriberCountText')
+            )
+            info['country'] = extract_str(a_metadata.get('country'))
+            info['canonical_url'] = extract_str(
+                a_metadata.get('canonicalChannelUrl')
+            )
+
+        # Old type
+        else:
+            items, _ = extract_items(response,
+                item_types={'channelAboutFullMetadataRenderer'})
+            if not items:
+                info['error'] = 'Could not find aboutChannelRenderer or channelAboutFullMetadataRenderer'
+                return info
+            a_metadata = items[0]['channelAboutFullMetadataRenderer']
+
+            info['links'] = []
+            for link_json in a_metadata.get('primaryLinks', ()):
+                url = remove_redirect(deep_get(link_json, 'navigationEndpoint',
+                    'urlEndpoint', 'url'))
+                if url and not (url.startswith('http://')
+                                or url.startswith('https://')):
+                    url = 'https://' + url
+                text = extract_str(link_json.get('title'))
+                info['links'].append( (text, url) )
+
+            info['date_joined'] = extract_date(a_metadata.get('joinedDateText'))
+            info['view_count'] = extract_int(a_metadata.get('viewCountText'))
+            info['description'] = extract_str(a_metadata.get(
+                'description'), default='')
+
+            info['approx_video_count'] = None
+            info['approx_subscriber_count'] = None
+            info['country'] = None
+            info['canonical_url'] = None
     else:
         raise NotImplementedError('Unknown or unsupported channel tab: ' + tab)
 
@@ -156,39 +218,112 @@ def extract_playlist_metadata(polymer_json):
         return {'error': err}
 
     metadata = {'error': None}
-    header = deep_get(response, 'header', 'playlistHeaderRenderer', default={})
+    metadata['title'] = None
-    metadata['title'] = extract_str(header.get('title'))
+    metadata['first_video_id'] = None
+    metadata['thumbnail'] = None
+    metadata['video_count'] = None
+    metadata['description'] = ''
+    metadata['author'] = None
+    metadata['author_id'] = None
+    metadata['author_url'] = None
+    metadata['view_count'] = None
+    metadata['like_count'] = None
+    metadata['time_published'] = None
+
+    header = deep_get(response, 'header', 'playlistHeaderRenderer', default={})
+
+    if header:
+        # Classic playlistHeaderRenderer format
+        metadata['title'] = extract_str(header.get('title'))
+        metadata['first_video_id'] = deep_get(header, 'playEndpoint', 'watchEndpoint', 'videoId')
+        first_id = re.search(r'([a-z_\-]{11})', deep_get(header,
+            'thumbnail', 'thumbnails', 0, 'url', default=''))
+        if first_id:
+            conservative_update(metadata, 'first_video_id', first_id.group(1))
+
+        metadata['video_count'] = extract_int(header.get('numVideosText'))
+        metadata['description'] = extract_str(header.get('descriptionText'), default='')
+        metadata['author'] = extract_str(header.get('ownerText'))
+        metadata['author_id'] = multi_deep_get(header,
+            ['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
+            ['ownerEndpoint', 'browseEndpoint', 'browseId'])
+        metadata['view_count'] = extract_int(header.get('viewCountText'))
+        metadata['like_count'] = extract_int(header.get('likesCountWithoutLikeText'))
+        for stat in header.get('stats', ()):
+            text = extract_str(stat)
+            if 'videos' in text or 'episodes' in text:
+                conservative_update(metadata, 'video_count', extract_int(text))
+            elif 'views' in text:
+                conservative_update(metadata, 'view_count', extract_int(text))
+            elif 'updated' in text:
+                metadata['time_published'] = extract_date(text)
+    else:
+        # New pageHeaderRenderer format (YouTube 2024+)
+        page_header = deep_get(response, 'header', 'pageHeaderRenderer', default={})
+        metadata['title'] = page_header.get('pageTitle')
+        view_model = deep_get(page_header, 'content', 'pageHeaderViewModel', default={})
+
+        # Extract title from viewModel if not found
+        if not metadata['title']:
+            metadata['title'] = deep_get(view_model,
+                'title', 'dynamicTextViewModel', 'text', 'content')
+
+        # Extract metadata from rows (author, video count, views, etc.)
+        meta_rows = deep_get(view_model,
+            'metadata', 'contentMetadataViewModel', 'metadataRows', default=[])
+        for row in meta_rows:
+            for part in row.get('metadataParts', []):
+                text_content = deep_get(part, 'text', 'content', default='')
+                # Author from avatarStack
+                avatar_stack = deep_get(part, 'avatarStack', 'avatarStackViewModel', default={})
+                if avatar_stack:
+                    author_text = deep_get(avatar_stack, 'text', 'content')
+                    if author_text:
+                        metadata['author'] = author_text
+                    # Extract author_id from commandRuns
+                    for run in deep_get(avatar_stack, 'text', 'commandRuns', default=[]):
+                        browse_id = deep_get(run, 'onTap', 'innertubeCommand',
+                            'browseEndpoint', 'browseId')
+                        if browse_id:
+                            metadata['author_id'] = browse_id
+                # Video/episode count
+                if text_content and ('video' in text_content.lower() or 'episode' in text_content.lower()):
+                    conservative_update(metadata, 'video_count', extract_int(text_content))
+                # View count
+                elif text_content and 'view' in text_content.lower():
+                    conservative_update(metadata, 'view_count', extract_int(text_content))
+                # Last updated
+                elif text_content and 'updated' in text_content.lower():
+                    metadata['time_published'] = extract_date(text_content)
+
+        # Extract description from sidebar if available
+        sidebar = deep_get(response, 'sidebar', 'playlistSidebarRenderer', 'items', default=[])
+        for sidebar_item in sidebar:
+            desc = deep_get(sidebar_item, 'playlistSidebarPrimaryInfoRenderer',
+                'description', 'simpleText')
+            if desc:
+                metadata['description'] = desc
+
+    if metadata['author_id']:
+        metadata['author_url'] = 'https://www.youtube.com/channel/' + metadata['author_id']
 
-    metadata['first_video_id'] = deep_get(header, 'playEndpoint', 'watchEndpoint', 'videoId')
-    first_id = re.search(r'([a-z_\-]{11})', deep_get(header,
-        'thumbnail', 'thumbnails', 0, 'url', default=''))
-    if first_id:
-        conservative_update(metadata, 'first_video_id', first_id.group(1))
     if metadata['first_video_id'] is None:
         metadata['thumbnail'] = None
     else:
-        metadata['thumbnail'] = 'https://i.ytimg.com/vi/' + metadata['first_video_id'] + '/mqdefault.jpg'
+        metadata['thumbnail'] = f"https://i.ytimg.com/vi/{metadata['first_video_id']}/hqdefault.jpg"
 
-    metadata['video_count'] = extract_int(header.get('numVideosText'))
+    microformat = deep_get(response, 'microformat', 'microformatDataRenderer',
-    metadata['description'] = extract_str(header.get('descriptionText'), default='')
+                           default={})
-    metadata['author'] = extract_str(header.get('ownerText'))
+    conservative_update(
-    metadata['author_id'] = multi_deep_get(header,
+        metadata, 'title', extract_str(microformat.get('title'))
-        ['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
+    )
-        ['ownerEndpoint', 'browseEndpoint', 'browseId'])
+    conservative_update(
-    if metadata['author_id']:
+        metadata, 'description', extract_str(microformat.get('description'))
-        metadata['author_url'] = 'https://www.youtube.com/channel/' + metadata['author_id']
+    )
-    else:
+    conservative_update(
-        metadata['author_url'] = None
+        metadata, 'thumbnail', deep_get(microformat, 'thumbnail',
-    metadata['view_count'] = extract_int(header.get('viewCountText'))
+                                        'thumbnails', -1, 'url')
-    metadata['like_count'] = extract_int(header.get('likesCountWithoutLikeText'))
+    )
-    for stat in header.get('stats', ()):
-        text = extract_str(stat)
-        if 'videos' in text:
-            conservative_update(metadata, 'video_count', extract_int(text))
-        elif 'views' in text:
-            conservative_update(metadata, 'view_count', extract_int(text))
-        elif 'updated' in text:
-            metadata['time_published'] = extract_date(text)
 
     return metadata
 
@@ -197,13 +332,11 @@ def extract_playlist_info(polymer_json):
     if err:
         return {'error': err}
     info = {'error': None}
-    first_page = 'continuationContents' not in response
     video_list, _ = extract_items(response)
 
     info['items'] = [extract_item_info(renderer) for renderer in video_list]
 
-    if first_page:
+    info['metadata'] = extract_playlist_metadata(polymer_json)
-        info['metadata'] = extract_playlist_metadata(polymer_json)
 
     return info
 

youtube/yt_data_extract/watch_extraction.py

@@ -111,14 +111,10 @@ _formats = {
     '_rtmp': {'protocol': 'rtmp'},
 
     # av01 video only formats sometimes served with "unknown" codecs
-    '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
+    '394': {'vcodec': 'av01.0.05M.08'},
-    '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
+    '395': {'vcodec': 'av01.0.05M.08'},
-    '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
+    '396': {'vcodec': 'av01.0.05M.08'},
-    '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
+    '397': {'vcodec': 'av01.0.05M.08'},
-    '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
-    '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
-    '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
-    '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
 }
 
 
@@ -137,29 +133,59 @@ def _extract_from_video_information_renderer(renderer_content):
     return info
 
 def _extract_likes_dislikes(renderer_content):
-    info = {
+    def extract_button_count(toggle_button_renderer):
-        'like_count': None,
-    }
-    for button in renderer_content.get('buttons', ()):
-        button_renderer = button.get('slimMetadataToggleButtonRenderer', {})
-
         # all the digits can be found in the accessibility data
-        count = extract_int(deep_get(
+        count = extract_int(multi_deep_get(
-                    button_renderer,
+            toggle_button_renderer,
-                    'button', 'toggleButtonRenderer', 'defaultText',
+            ['defaultText', 'accessibility', 'accessibilityData', 'label'],
-                    'accessibility', 'accessibilityData', 'label'))
+            ['accessibility', 'label'],
+            ['accessibilityData', 'accessibilityData', 'label'],
+            ['accessibilityText'],
+        ))
 
         # this count doesn't have all the digits, it's like 53K for instance
-        dumb_count = extract_int(extract_str(deep_get(
+        dumb_count = extract_int(extract_str(multi_get(
-            button_renderer, 'button', 'toggleButtonRenderer', 'defaultText')))
+            toggle_button_renderer, ['defaultText', 'title'])))
 
         # The accessibility text will be "No likes" or "No dislikes" or
         # something like that, but dumb count will be 0
         if dumb_count == 0:
             count = 0
+        return count
 
-        if 'isLike' in button_renderer:
+    info = {
-            info['like_count'] = count
+        'like_count': None,
+        'dislike_count': None,
+    }
+    for button in renderer_content.get('buttons', ()):
+        if 'slimMetadataToggleButtonRenderer' in button:
+            button_renderer = button['slimMetadataToggleButtonRenderer']
+            count = extract_button_count(deep_get(button_renderer,
+                                                  'button',
+                                                  'toggleButtonRenderer'))
+            if 'isLike' in button_renderer:
+                info['like_count'] = count
+            elif 'isDislike' in button_renderer:
+                info['dislike_count'] = count
+        elif 'slimMetadataButtonRenderer' in button:
+            button_renderer = button['slimMetadataButtonRenderer']
+            liberal_update(info, 'like_count', extract_button_count(
+                multi_deep_get(button_renderer,
+                    ['button', 'segmentedLikeDislikeButtonRenderer',
+                     'likeButton', 'toggleButtonRenderer'],
+                    ['button', 'segmentedLikeDislikeButtonViewModel',
+                     'likeButtonViewModel', 'likeButtonViewModel',
+                     'toggleButtonViewModel', 'toggleButtonViewModel',
+                     'defaultButtonViewModel', 'buttonViewModel']
+                )
+            ))
+            '''liberal_update(info, 'dislike_count', extract_button_count(
+                deep_get(
+                    button_renderer, 'button',
+                    'segmentedLikeDislikeButtonRenderer',
+                    'dislikeButton', 'toggleButtonRenderer'
+                )
+            ))'''
     return info
 
 def _extract_from_owner_renderer(renderer_content):
@@ -213,6 +239,36 @@ def _extract_metadata_row_info(renderer_content):
 
     return info
 
+def _extract_from_music_renderer(renderer_content):
+    # latest format for the music list
+    info = {
+        'music_list': [],
+    }
+
+    for carousel in renderer_content.get('carouselLockups', []):
+        song = {}
+        carousel = carousel.get('carouselLockupRenderer', {})
+        video_renderer = carousel.get('videoLockup', {})
+        video_renderer_info = extract_item_info(video_renderer)
+        video_id = video_renderer_info.get('id')
+        song['url'] = concat_or_none('https://www.youtube.com/watch?v=',
+                                     video_id)
+        song['title'] = video_renderer_info.get('title')
+        for row in carousel.get('infoRows', []):
+            row = row.get('infoRowRenderer', {})
+            title = extract_str(row.get('title'))
+            data = extract_str(row.get('defaultMetadata'))
+            if title == 'SONG':
+                song['title'] = data
+            elif title == 'ARTIST':
+                song['artist'] = data
+            elif title == 'ALBUM':
+                song['album'] = data
+            elif title == 'WRITERS':
+                song['writers'] = data
+        info['music_list'].append(song)
+    return info
+
 def _extract_from_video_metadata(renderer_content):
     info = _extract_from_video_information_renderer(renderer_content)
     liberal_dict_update(info, _extract_likes_dislikes(renderer_content))
@@ -236,6 +292,7 @@ visible_extraction_dispatch = {
     'slimVideoActionBarRenderer': _extract_likes_dislikes,
     'slimOwnerRenderer': _extract_from_owner_renderer,
     'videoDescriptionHeaderRenderer': _extract_from_video_header_renderer,
+    'videoDescriptionMusicSectionRenderer': _extract_from_music_renderer,
     'expandableVideoDescriptionRenderer': _extract_from_description_renderer,
     'metadataRowContainerRenderer': _extract_metadata_row_info,
     # OR just this one, which contains SOME of the above inside it
@@ -308,17 +365,18 @@ def _extract_watch_info_mobile(top_level):
         # https://www.androidpolice.com/2019/10/31/google-youtube-app-comment-section-below-videos/
         # https://www.youtube.com/watch?v=bR5Q-wD-6qo
         if header_type == 'commentsEntryPointHeaderRenderer':
-            comment_count_text = extract_str(comment_info.get('headerText'))
+            comment_count_text = extract_str(multi_get(
+                comment_info, 'commentCount', 'headerText'))
         else:
             comment_count_text = extract_str(deep_get(comment_info,
                 'header', 'commentSectionHeaderRenderer', 'countText'))
         if comment_count_text == 'Comments':    # just this with no number, means 0 comments
-            info['comment_count'] = 0
+            info['comment_count'] = '0'
         else:
-            info['comment_count'] = extract_int(comment_count_text)
+            info['comment_count'] = extract_approx_int(comment_count_text)
         info['comments_disabled'] = False
     else:   # no comment section present means comments are disabled
-        info['comment_count'] = 0
+        info['comment_count'] = '0'
         info['comments_disabled'] = True
 
     # check for limited state
@@ -354,8 +412,10 @@ def _extract_watch_info_desktop(top_level):
     likes_dislikes = deep_get(video_info, 'sentimentBar', 'sentimentBarRenderer', 'tooltip', default='').split('/')
     if len(likes_dislikes) == 2:
         info['like_count'] = extract_int(likes_dislikes[0])
+        info['dislike_count'] = extract_int(likes_dislikes[1])
     else:
         info['like_count'] = None
+        info['dislike_count'] = None
 
     info['title'] = extract_str(video_info.get('title', None))
     info['author'] = extract_str(deep_get(video_info, 'owner', 'videoOwnerRenderer', 'title'))
@@ -368,26 +428,28 @@ def _extract_watch_info_desktop(top_level):
     return info
 
 def update_format_with_codec_info(fmt, codec):
-    if (codec.startswith('av')
+    if any(codec.startswith(c) for c in ('av', 'vp', 'h263', 'h264', 'mp4v')):
-            or codec in ('vp9', 'vp8', 'vp8.0', 'h263', 'h264', 'mp4v')):
         if codec == 'vp8.0':
             codec = 'vp8'
         conservative_update(fmt, 'vcodec', codec)
     elif (codec.startswith('mp4a')
-            or codec in ('opus', 'mp3', 'aac', 'dtse', 'ec-3', 'vorbis')):
+            or codec in ('opus', 'mp3', 'aac', 'dtse', 'ec-3', 'vorbis',
+                        'ac-3')):
         conservative_update(fmt, 'acodec', codec)
     else:
         print('Warning: unrecognized codec: ' + codec)
 
 fmt_type_re = re.compile(
-    r'(text|audio|video)/([\w0-9]+); codecs="([\w0-9\.]+(?:, [\w0-9\.]+)*)"')
+    r'(text|audio|video)/([\w0-9]+); codecs="([^"]+)"')
 def update_format_with_type_info(fmt, yt_fmt):
     # 'type' for invidious api format
     mime_type = multi_get(yt_fmt, 'mimeType', 'type')
     if mime_type is None:
         return
     match = re.fullmatch(fmt_type_re, mime_type)
-
+    if match is None:
+        print('Warning: Could not read mimetype', mime_type)
+        return
     type, fmt['ext'], codecs = match.groups()
     codecs = codecs.split(', ')
     for codec in codecs:
@@ -410,6 +472,13 @@ def _extract_formats(info, player_response):
     for yt_fmt in yt_formats:
         itag = yt_fmt.get('itag')
 
+        # Translated audio track
+        # Example: https://www.youtube.com/watch?v=gF9kkB0UWYQ
+        # Only get the original language for now so a foreign
+        # translation will not be picked just because it comes first
+        if deep_get(yt_fmt, 'audioTrack', 'audioIsDefault') is False:
+            continue
+
         fmt = {}
         fmt['itag'] = itag
         fmt['ext'] = None
@@ -559,6 +628,7 @@ def extract_watch_info(polymer_json):
     info['manual_caption_languages'] = []
     info['_manual_caption_language_names'] = {}     # language name written in that language, needed in some cases to create the url
     info['translation_languages'] = []
+    info['_caption_track_urls'] = {}  # lang_code -> full baseUrl from player response
     captions_info = player_response.get('captions', {})
     info['_captions_base_url'] = normalize_url(deep_get(captions_info, 'playerCaptionsRenderer', 'baseUrl'))
     # Sometimes the above playerCaptionsRender is randomly missing
@@ -589,6 +659,10 @@ def extract_watch_info(polymer_json):
         else:
             info['manual_caption_languages'].append(lang_code)
         base_url = caption_track.get('baseUrl', '')
+        # Store the full URL from the player response (includes valid tokens)
+        if base_url:
+            normalized = normalize_url(base_url) if base_url.startswith('/') or not base_url.startswith('http') else base_url
+            info['_caption_track_urls'][lang_code + ('_asr' if caption_track.get('kind') == 'asr' else '')] = normalized
         lang_name = deep_get(urllib.parse.parse_qs(urllib.parse.urlparse(base_url).query), 'name', 0)
         if lang_name:
             info['_manual_caption_language_names'][lang_code] = lang_name
@@ -756,6 +830,21 @@ def captions_available(info):
 
 def get_caption_url(info, language, format, automatic=False, translation_language=None):
     '''Gets the url for captions with the given language and format. If automatic is True, get the automatic captions for that language. If translation_language is given, translate the captions from `language` to `translation_language`. If automatic is true and translation_language is given, the automatic captions will be translated.'''
+    # Try to use the direct URL from the player response first (has valid tokens)
+    track_key = language + ('_asr' if automatic else '')
+    direct_url = info.get('_caption_track_urls', {}).get(track_key)
+    if direct_url:
+        url = direct_url
+        # Override format
+        if '&fmt=' in url:
+            url = re.sub(r'&fmt=[^&]*', '&fmt=' + format, url)
+        else:
+            url += '&fmt=' + format
+        if translation_language:
+            url += '&tlang=' + translation_language
+        return url
+
+    # Fallback to base_url construction
     url = info['_captions_base_url']
     if not url:
         return None
@@ -770,7 +859,7 @@ def get_caption_url(info, language, format, automatic=False, translation_languag
         url += '&tlang=' + translation_language
     return url
 
-def update_with_age_restricted_info(info, player_response):
+def update_with_new_urls(info, player_response):
     '''Inserts urls from player_response json'''
     ERROR_PREFIX = 'Error getting missing player or bypassing age-restriction: '