Novel Scraper, Translator & EPUB Generator

This project scrapes online novel chapters, translates them into English using Google Gemini AI, and generates an EPUB eBook.

---

Features

• Scrapes novel chapters from URLs listed in input.txt.
• Translates content and titles while preserving HTML formatting.
• Caches translations to avoid redundant API calls.
• Generates a fully formatted EPUB eBook with optional cover image.

---

Prerequisites

• Node.js v18+
• NPM or Yarn
• Google Gemini AI API key

---

Installation

1. Clone the repository:

git clone <your-repo-url>
cd <repo-folder>

2. Install dependencies:

npm install

3. Create a .env file with your Gemini API key:

GEMINI_API_KEY=your_api_key_here

4. Prepare input.txt with a list of URLs to scrape, one per line.

5. (Optional) Add extra instructions in extra.txt to customize translation behavior.

---

Usage

Run the project with:

npm start

The workflow:

1. Scrapes chapters from URLs listed in input.txt.
2. Translates chapters and titles to English.
3. Generates an EPUB file in the output directory.

---

Project Structure

.
├── input.txt        # List of URLs to scrape
├── extra.txt        # Optional extra translation instructions
├── cache.json       # Translation cache
├── cover.jpg        # Optional EPUB cover image
├── src/
│   ├── scraper.ts
│   ├── translator.ts
│   ├── generator.ts
│   └── types/
│       └── chapter.type.ts
├── output/          # Generated EPUB files
└── .env

---

Configuration

You can customize the EPUB details in constants.ts:

export const EPUB_DETAILS = {
	TITLE: "My Translated Novel",
	AUTHOR: "Author Name",
	OUTPUT_FILE_NAME: "Test",
};

---

Notes

• Ensure each URL in input.txt points to a valid chapter page with an <article> containing headings and sections.
• Translations preserve all paragraph tags (<p>) and HTML structure.
• Cache is stored in cache.json to speed up repeated runs.

---