Shell script to extract text from PDFs, Spreadsheets, Word/Powerpoint, and more

textract.sh

#!/usr/bin/env bash
# Self-contained script to extract text from a variety of file types
# Supported file types -- https://textract.readthedocs.io/en/stable/#currently-supporting
# Usage: ./textract <input.pdf> -o <output.csv>

set -euo pipefail

# Install uv if not available
if ! command -v uv &> /dev/null; then
    echo "Installing uv..."
    curl -LsSf https://astral.sh/uv/install.sh | sh
    export PATH="$HOME/.local/bin:$PATH"
fi

# Run textract using uv with Python 3.11 (installs textract if needed)
exec uv tool run --python 3.11 --from textract textract "$@"