ayakashivscrawl4ai
Ayakashi is a web scraping library for Node.js that allows developers to easily extract structured data from websites. It is built on top of the popular "puppeteer" library and provides a simple and intuitive API for defining and querying the structure of a website.
Features:
- Powerful querying and data models
Ayakashi's way of finding things in the page and using them is done with props and domQL. Directly inspired by the relational database world (and SQL), domQL makes DOM access easy and readable no matter how obscure the page's structure is. Props are the way to package domQL expressions as re-usable structures which can then be passed around to actions or to be used as models for data extraction. - High level builtin actions
Ready made actions so you can focus on what matters. Easily handle infinite scrolling, single page navigation, events and more. Plus, you can always build your own actions, either from scratch or by composing other actions. - Preload code on pages
Need to include a bunch of code, a library you made or a 3rd party module and make it available on a page? Preloaders have you covered.
Crawl4AI is an open-source AI-powered web crawling and data extraction library for Python. It uses large language models (LLMs) to intelligently extract structured data from web pages with minimal code. Unlike traditional scraping frameworks that rely on CSS selectors or XPath, Crawl4AI can understand page content semantically and extract data based on natural language descriptions of what you want.
Key features include:
- LLM-based extraction Define what data you want in plain English and Crawl4AI uses LLMs to find and extract it from the page content. Supports multiple LLM providers including OpenAI, Anthropic, and local models.
- Automatic crawling Built-in crawler with support for JavaScript rendering, parallel crawling, and session management.
- Structured output Returns data in structured formats (JSON, Pydantic models) making it easy to integrate into data pipelines.
- Markdown conversion Can convert web pages to clean markdown format, useful for feeding content to LLMs.
- Chunking strategies Multiple strategies for breaking down large pages into processable chunks for LLM extraction.
- Async support Built on async Python for efficient concurrent crawling and extraction.
Crawl4AI is particularly useful for scraping unstructured content where writing traditional CSS/XPath selectors would be tedious or fragile. It excels at content extraction, article parsing, and data mining from diverse page layouts.