Skip to main content
You are viewing the v1 (legacy) documentation. v1 is deprecated and will be removed in a future release. Please migrate to v2 for the latest features and improvements.
ScrapeGraphAI Documentation

​
Overview

ScrapeGraphAI is a powerful suite of LLM-driven web scraping tools designed to extract structured data from any website and HTML content. Our API is designed to be easy to use and integrate with your existing workflows.

​
Perfect For

AI Applications

Feed your AI agents with structured web data for enhanced decision-making

Data Analysis

Extract and structure web data for research and analysis

Dataset Creation

Build comprehensive datasets from web sources

Platform Building

Create scraping-powered platforms and applications

​
Getting Started

1

Get API Key

Sign up and access your API key from the dashboard
2

Choose Your Service

Select from our specialized extraction services based on your needs
3

Start Extracting

Begin extracting data using our SDKs or direct API calls

​
Core Services

  • SmartScraper: AI-powered extraction for any webpage
  • SearchScraper: Find and extract any data using AI starting from a prompt
  • SmartCrawler: AI-powered extraction for any webpage with crawl
  • Markdownify: Convert web content to clean Markdown format
  • Sitemap: Extract sitemaps from websites
  • AgenticScraper: Agent-based multi-step scraping
  • Toonify: Convert images to cartoon style

​
v1 SDKs

​
Python

from scrapegraph_py import Client

client = Client(api_key="your-api-key")

response = client.smartscraper(
    website_url="https://example.com",
    user_prompt="Extract the main content"
)

​
JavaScript

import { smartScraper } from "scrapegraph-js";

const response = await smartScraper(apiKey, {
  website_url: "https://example.com",
  user_prompt: "What does the company do?",
});

​
Migrate to v2

v2 brings significant improvements including renamed methods, unified configuration objects, and new endpoints. See the migration guides: