ScrapeGraphAI
scrapecraft
Python

🤖 AI-powered web scraping editor with visual workflow builder. Build, test & deploy web scrapers using natural language. Powered by ScrapeGraphAI & LangGraph.

Last updated Jul 7, 2026
666
Stars
104
Forks
1
Issues
+2
Stars/day
Attention Score
80
Language breakdown
Python 75.2%
TypeScript 23.6%
CSS 0.4%
Dockerfile 0.3%
JavaScript 0.3%
HTML 0.2%
Files click to expand
README

ScrapeCraft - AI-Powered Web Scraping Editor

ScrapeCraft is a web-based scraping editor similar to Cursor but specialized for web scraping. It uses AI assistance to help users build scraping pipelines with the ScrapeGraphAI API.

https://github.com/user-attachments/assets/defaf7ad-23da-40b7-82cd-3b2a4d1d22c9

API Banner

Features

  • 🤖 AI-powered assistant using OpenRouter (Kimi-k2 model)
  • 🔗 Multi-URL bulk scraping support
  • 📋 Dynamic schema definition with Pydantic
  • 💻 Python code generation with async support
  • 🚀 Real-time WebSocket streaming
  • 📊 Results visualization (table & JSON views)
  • 🔄 Auto-updating deployment with Watchtower

Tech Stack

  • Backend: FastAPI, LangGraph, ScrapeGraphAI
  • Frontend: React, TypeScript, Tailwind CSS
  • Database: PostgreSQL
  • Cache: Redis
  • Deployment: Docker, Docker Compose, Watchtower

Prerequisites

  • Docker and Docker Compose
  • OpenRouter API key (Get it from OpenRouter)
  • ScrapeGraphAI API key (Get it from ScrapeGraphAI)

Quick Start with Docker

  • Clone the repository
git clone https://github.com/ScrapeGraphAI/scrapecraft.git
   cd scrapecraft
  • Set up environment variables
cp .env.example .env
Edit the .env file and add your API keys: - OPENROUTERAPIKEY: Get from OpenRouter - SCRAPEGRAPHAPIKEY: Get from ScrapeGraphAI
  • Start the application with Docker
docker compose up -d
  • Access the application
- Frontend: http://localhost:3000 - API: http://localhost:8000 - API Docs: http://localhost:8000/docs
  • Stop the application
docker compose down

Development Mode

If you want to run the application in development mode without Docker:

Backend Development

cd backend
pip install -r requirements.txt
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Frontend Development

cd frontend
npm install
npm start

Usage

  • Create a Pipeline: Click "New Pipeline" to start
  • Add URLs: Use the URL Manager to add websites to scrape
  • Define Schema: Create fields for data extraction
  • Generate Code: Ask the AI to generate scraping code
  • Execute: Run the pipeline to scrape data
  • Export Results: Download as JSON or CSV

Remote Updates

The application includes Watchtower for automatic updates:

  • Push new Docker images to your registry
  • Watchtower will automatically detect and update containers
  • No manual intervention required

API Endpoints

  • POST /api/chat/message - Send message to AI assistant
  • GET /api/pipelines - List all pipelines
  • POST /api/pipelines - Create new pipeline
  • PUT /api/pipelines/{id} - Update pipeline
  • POST /api/pipelines/{id}/run - Execute pipeline
  • WS /ws/{pipeline_id} - WebSocket connection

Environment Variables

| Variable | Description | How to Get | |----------|-------------|------------| | OPENROUTERAPIKEY | Your OpenRouter API key | Get API Key | | SCRAPEGRAPHAPIKEY | Your ScrapeGraphAI API key | Get API Key | | JWT_SECRET | Secret key for JWT tokens | Generate a random string | | DATABASE_URL | PostgreSQL connection string | Auto-configured with Docker | | REDIS_URL | Redis connection string | Auto-configured with Docker |

License

MIT

🔗 More in this category

© 2026 GitRepoTrend · ScrapeGraphAI/scrapecraft · Updated daily from GitHub