Automated Screenshot Capture System

# What This Does
It visits a list of URLs, takes a screenshot of each, crops out the clutter (like sidebars or ads), and adds a professional "beautify" effect (shadows, gradients) to make them look like high-quality marketing assets.

# What You Need
- A list of URLs in a CSV file (e.g., `urls.csv`)
- Node.js installed on your computer
- (Optional) An API key if you want to use a cloud service, but this recipe works locally with Puppeteer.

# What You Get
- A folder full of high-quality `.jpg` or `.png` images
- Consistent framing and styling for all your screenshots
- No more manual cropping or editing in Photoshop/Canva

# How to Use
1. Prepare your `urls.csv` with the links you want to capture
2. Open Claude Code, Gemini CLI, or Cursor in a new folder
3. Copy and paste the prompt below
4. Run the generated script to get your images

---

# Prompt

You are a Senior Node.js Developer. Your job is to build a robust **Automated Screenshot Capture System** that takes a list of URLs and turns them into beautiful, marketing-ready images.

**Phase 1: Setup**
- Read `urls.csv` (columns: `url`, `platform`)
- If it doesn't exist, create it with sample data (Twitter/X link, GitHub link, generic link).
- Install necessary dependencies: `puppeteer` for capturing, `canvas` for image manipulation (adding shadows/gradients).

**Phase 2: The Capture Script (`capture.js`)**
Create a script that:
1. Launches a headless browser (Puppeteer).
2. Loops through each URL in the CSV.
3. **Smart Cropping:** based on the `platform` column, crop the screenshot to specific coordinates to remove UI clutter:
   - **Twitter/X:** Focus on the tweet content (e.g., width 900px, centered).
   - **GitHub:** Focus on the repo header/README.
   - **Default:** Full page or a standard viewport (1280x800).
4. **Beautify:** After capturing, use `canvas` to:
   - Add a subtle drop shadow.
   - Add a nice gradient background or solid border.
   - Round the corners of the screenshot.
5. Save the final image to an `output/` folder with a safe filename (e.g., `twitter-user-status-12345.jpg`).

**Phase 3: Execution**
- Run the script and show a progress bar in the terminal.
- Handle errors gracefully (e.g., if a page fails to load, log it and move to the next).
- When finished, print: "✅ Captured X screenshots. Check the 'output' folder!"

Start now.