# LLM-powered scraper (scrapegraph-ai) (/automation--scrapegraph-scraper)

/automation--scrapegraph-scraper is a Claude Code skill in the Code section. Builds a scraper on scrapegraph-ai where an LLM extracts data into Pydantic schemas, after checking whether the token cost is worth it.

- Web version: https://skills.sgomez.dev/en/s/automation--scrapegraph-scraper
- Section: [Code](https://skills.sgomez.dev/en/code.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/automation/scrapegraph-scraper.md
- Updated 26 Aug 2026

## How to ask for it

- `/automation--scrapegraph-scraper extract structured data from these pages with scrapegraph-ai`
- `/automation--scrapegraph-scraper define a Pydantic schema for the scraper's output`
- `/automation--scrapegraph-scraper how many tokens will crawling this site cost?`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install automation-skills@claude-skills-collection
```

## Permissions

- Reads: `pyproject.toml`, `requirements.txt`, `uv.lock`, `*.py`, `.env`, `.env.example`, `package.json`
- Writes: `scraper/**`, `scrape_*.py`, `schemas/*.py`, `data/**`, `.env.example`, `requirements.txt`, `pyproject.toml`
- Runs: `python`, `pip`, `uv`, `playwright`
- Network: Yes
- Destructive: No

## Author's description

Build an LLM-powered scraper with scrapegraph-ai — graph choice, Pydantic schemas, token cost

- [How we review this](https://skills.sgomez.dev/en/methodology.md)