📚 Book Summarizer & Obsidian Slide Visualizer

An advanced agentic skill that automates book ingestion, generates executive briefing reports and slide decks via NotebookLM, extracts slide visuals, and compiles them into a unified, rich Obsidian vault summary with semantic image mapping.

---

⚡ Why Use This?

• Say Goodbye to Bland Book Summaries: Text-only summaries lack context. This tool embeds visual slide highlights directly inline where they fit logically.
• Chapter-by-Chapter Granularity: Automatically splits textbooks and technical manuals into separate chapters, preserving complex diagrams and MCP instructions.
• Resilient Execution: Implements automatic multi-account cookie rotation and backoffs to bypass NotebookLM's rolling daily generation limits.

---

🏗️ How it Works

flowchart TD
    A[Input Book: EPUB/PDF/TXT] --> B{Granularity Classifier}
    B -- Textbook / Manual --> C[Split into Chapter Markdown files]
    B -- Fiction / General Non-Fiction --> D[Keep as Single Book Unit]
    C & D --> E[NotebookLM Upload]
    E --> F[Generate Briefing Report & Slide Deck]
    F --> G[Extract PDF slides to PNGs via PyMuPDF]
    G --> H[Organize into Obsidian Vault Directory]
    H --> I[Compile Comprehensive_Summary.md with Contextual Slide Placements]

Loading

---

⚙️ Features

• 📑 Smart File Conversion: Automatically converts .epub and unsupported formats into Markdown using markitdown.
• 📊 Visual Ingestion: Converts slide deck PDFs into clean PNGs at high resolutions.
• 📂 Obsidian Vault Standard Organization: Automatically places summaries and assets into your specified Obsidian folder.
• 🔁 Multi-Account Rotation: Rotates through Google account cookies (storage_state.json) automatically when RATE_LIMITED is detected.
• 🎨 Visual Style Enforcer: Enforce a unified slide theme across chapters using CLI description parameters.

---

🚀 Quick Start

1. Prerequisites

Ensure you have the following installed:

• Python 3.10+
• uv (Python package installer and runner)
• NotebookLM CLI (Authenticated and configured)

2. Installation

Clone the repository:

git clone https://github.com/alexjiaguo/book-summarizer.git
cd book-summarizer

3. Configuration

Copy the .env.example file to .env and customize the paths for your local machine:

cp .env.example .env

Open .env and configure:

• BOOK_SUMMARIZER_DIR: Root folder of your cloned repository.
• OBSIDIAN_VAULT_PATH: Destination path in your Obsidian vault.

Always source the environment file before running the scripts:

set -a; source .env; set +a

4. Usage

Run the conversion script directly or instruct your AI coding agent to execute the SKILL.md rules:

# Process a book using the default settings
uv run python $BOOK_SUMMARIZER_DIR/scripts/convert_book.py path/to/book.epub /tmp/converted_book.md

To run slide extraction:

uv run --with pymupdf python $BOOK_SUMMARIZER_DIR/scripts/slides_to_images.py /tmp/deck.pdf /tmp/extracted_slides/

---

🤝 Contributing

Contributions, issues, and feature requests are welcome! Feel free to check the issues page.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'feat: add some amazing feature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📝 License

Distributed under the MIT License. See LICENSE for more information.