Overview

Use this section to extract web content, discover URLs, run search jobs, and connect Geonode to AI tools with MCP.

Getting Started

Start here if you are new to the Scraper API.

• Quick Start Guide — get your API key and authenticate requests
• Before You Start — prerequisites and setup basics

Products

Choose the API that matches your workflow.

• Extraction — extract Markdown or HTML from a webpage
• Batch — process multiple URLs in one job
• Crawl — discover and extract pages across a website
• Map — discover URLs under a base URL
• Search — submit search queries and retrieve results

Dashboard Guides

Use the Geonode Dashboard when you want to run jobs without writing code.

• Dashboard Overview — navigate Scraper, Map, and Search in the UI

SDKs & Integrations

Use these Python packages to call the Scraper API from your own code or to give its tools to an AI agent.

• Python SDK — Python client for every public Scraper API endpoint
• LangChain — LangChain tools for the Scraper API
• CrewAI — CrewAI tools for the Scraper API
• Tools Core — shared runtime behind the LangChain and CrewAI tools

MCP

You can also use Geonode through MCP to connect the Scraper API to AI assistants and IDEs. See the MCP Guides to get started.

API Reference

Use the API reference when you need endpoint details, parameters, and responses.

• API Overview — Scraper API reference entry point
• Extraction — extract content endpoints
• Batch — batch job endpoints
• Crawl — crawl job endpoints
• Map — map job endpoints
• Search — search job endpoints

Next Steps

• Start with the Quick Start Guide to authenticate
• Pick a product guide above for your use case