scrapurrr 0.4.0

Agentic Web Scraper

Agentic web scraping framework with a built-in chat CLI.

What is Scrapurrr?

Scrapurrr is a Python framework for building agentic web scraping and automation apps, with a ready-to-use interactive CLI called chatpurrr.

As a framework, you define a Pydantic schema, point it at a URL, and get back typed data. It handles browser rendering, anti-detection, pagination, and LLM-powered extraction automatically.

As a CLI tool, you run chatpurrr and talk to it in natural language. Navigate pages, inspect elements, extract data, all from your terminal.

Built on PatchRight and CloakBrowser for undetected browsing. Supports 100+ LLM providers via LiteLLM.

Install

pip install scrapurrr

Get Started

Use the chat CLI:

chatpurrr

Use the framework:

from scrapurrr import Scrapurrr

Documentation

• Chatpurrr - Interactive CLI usage, slash commands, setup
• Framework - Library API, extraction, agent mode, element inspection, configuration

Usage Policy

Scrapurrr is intended for legitimate use cases: data collection from public sources, authorized testing, research, and personal automation. Users are responsible for complying with the terms of service of any website they interact with. Respect robots.txt, rate limits, and applicable laws.

License

MIT. See LICENSE.