Initial commit

.gitignore

@@ -0,0 +1,233 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,macos,python
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,macos,python
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+
+test audio
+.vscode

BAET/AppArgs.py

@@ -0,0 +1,124 @@
+import argparse
+import re
+from pathlib import Path
+from re import Pattern
+from typing import Any, Callable, cast
+
+from pydantic import (
+    BaseModel,
+    BeforeValidator,
+    ConfigDict,
+    DirectoryPath,
+    Field,
+    ValidationInfo,
+    field_validator,
+)
+from typing_extensions import Annotated
+
+
+class AppArgs(BaseModel):
+    """Application commandline arguments.
+
+    Raises:
+        ValueError: The provided path is not a directory.
+
+    Returns:
+        DirectoryPath: Validated directory path.
+    """
+
+    model_config = ConfigDict(frozen=True)
+
+    input_dir: DirectoryPath = Field(...)
+    output_dir: DirectoryPath = Field(...)
+    overwrite_existing: bool = Field(...)
+    fallback_freq: Annotated[int, Field(gt=0)] = Field(...)
+    fast: bool = Field(...)
+    no_output_subdirs: bool = Field(...)
+    include: Pattern | None = Field(...)
+    exclude: Pattern | None = Field(...)
+
+    @field_validator("include", mode="before")
+    @classmethod
+    def validate_include_nonempty(cls, v: str):
+        if not v or not str.strip(v):
+            return ".*"
+        return v
+
+    @field_validator("exclude", mode="before")
+    @classmethod
+    def validate_exclude_nonempty(cls, v: str):
+        if not v or not str.strip(v):
+            return None
+        return v
+
+    @field_validator("include", "exclude", mode="before")
+    @classmethod
+    def compile_to_pattern(cls, v: str):
+        if not v:
+            return None
+        if isinstance(v, str):
+            return re.compile(v)
+        else:
+            return v
+
+
+def GetArgs() -> AppArgs:
+    cwd = str(Path.cwd())
+
+    parser = argparse.ArgumentParser(
+        prog="Bulk Audio Extract Tool (BAET)",
+        description="Extract audio from a directory of videos using FFMPEG",
+        epilog="Created by: Phillip Smith 2023",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+    parser.add_argument(
+        "--fast",
+        default=False,
+        action="store_true",
+        help="only extracting the first 10 seconds of audio for each file",
+    )
+
+    parser.add_argument(
+        "--overwrite-existing",
+        default=False,
+        action="store_true",
+        help="overwrite a file if it already exists",
+    )
+
+    parser.add_argument(
+        "--no-output-subdirs",
+        default=False,
+        action="store_true",
+        help="do not create subdirectories for each video's extracted audio tracks in the output directory",
+    )
+
+    parser.add_argument(
+        "--include",
+        default=None,
+        metavar="REGEX",
+        help="only include files that match a regex pattern",
+    )
+
+    parser.add_argument(
+        "--exclude",
+        default=None,
+        metavar="REGEX",
+        help="exclude files that match a regex pattern",
+    )
+
+    parser.add_argument(
+        "--fallback-freq",
+        default=48000,
+        metavar="FREQUENCY",
+        help="------------------",
+    )
+
+    parser.add_argument(
+        "-i", "--input-dir", default=cwd, type=Path, help="source location"
+    )
+    parser.add_argument(
+        "-o", "--output-dir", default=cwd, type=Path, help="destination location"
+    )
+
+    args = parser.parse_args()
+    return AppArgs.model_validate(vars(args))

BAET/AudioExtractor.py

@@ -0,0 +1,15 @@
+from pathlib import Path
+
+from BAET.AppArgs import AppArgs
+
+
+class AudioExtractor:
+    def __init__(
+        self,
+        file_name: str,
+        app_args: AppArgs,
+    ):
+        if not file_name:
+            pass
+        self.file = (app_args.input_dir / file_name).resolve(strict=True)
+        self.app_args = app_args

README.md

@@ -0,0 +1 @@
+# Bulk Audio Extract Tool