# Anakinscraper

Scrape any website into clean markdown or structured JSON.

- Repository: https://github.com/Anakin-Inc/anakin (3882 stars)
- Category: Engineering
- License: AGPL-3.0
- Last updated: 2026-08-18
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Anakin-Inc/anakin --skill anakinscraper -g -a claude-code -y`
Codex: `npx skills add Anakin-Inc/anakin --skill anakinscraper -g -a codex -y`
Cursor: `npx skills add Anakin-Inc/anakin --skill anakinscraper -g -a cursor -y`
Gemini CLI: `npx skills add Anakin-Inc/anakin --skill anakinscraper -g -a gemini-cli -y`

## Description

Scrape any website into clean markdown or structured JSON. Anti-detect browser, smart proxy rotation, AI-powered data extraction.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# AnakinScraper Skill

Scrape any website and get back clean markdown or structured JSON data. Uses an anti-detect browser (Camoufox) to handle JavaScript-heavy sites and anti-bot protection.

## Setup

1. Start AnakinScraper (if not already running):

```bash
git clone https://github.com/Anakin-Inc/anakinscraper-oss.git
cd anakinscraper-oss && make up
```

2. Copy the skill into your OpenClaw workspace:

```bash
cp -r openclaw-skill ~/.openclaw/workspace/skills/anakinscraper
```

The skill calls the AnakinScraper REST API at `http://localhost:8080` directly. No additional build step required.

## Available Tools

### anakinscraper_scrape
Scrape a single URL synchronously. Returns markdown, cleaned HTML, and optionally structured JSON.

Use this when the user asks to:
- "Scrape this website"
- "Get the content from this URL"
- "Turn this page into markdown"
- "What's on this webpage?"

Parameters:
- `url` (required), The URL to scrape
- `useBrowser` (optional, default false), Force browser rendering for JavaScript-heavy sites
- `generateJson` (optional, default false), Extract structured JSON data using AI

### anakinscraper_extract_json
Scrape a URL and extract structured data as JSON. Best for product pages, articles, listings.

Use this when the user asks to:
- "Extract the product data from this page"
- "Get structured data from this URL"
- "Parse this listing page into JSON"
- "What products are on this page?"

Parameters:
- `url` (required), The URL to extract data from

### anakinscraper_batch_scrape
Scrape multiple URLs at once (up to 10). Returns results for all URLs.

Use this when the user asks to:
- "Scrape these 5 URLs"
- "Get content from all these pages"
- "Batch scrape this list"

Parameters:
- `urls` (required), Array of URLs to scrape (max 10)
- `useBrowser` (optional), Force browser rendering
- `generateJson` (optional), Extract structured JSON from each page

The rest: https://github.com/Anakin-Inc/anakin/blob/HEAD/openclaw-skill/SKILL.md