abdo-Mansour/axetract
Low-Cost Cross-Domain Web Structured Information Extraction using specialized LoRA adapters.
This tool helps you automatically pull specific pieces of information from almost any web page, turning unstructured web content into organized, structured data. You provide a web page URL and define exactly what data you need (like a product name, price, or rating), and it gives you that data in a clean, easy-to-use format like JSON. Anyone who needs to collect specific data points from many different websites, such as market researchers, e-commerce analysts, or data journalists, would find this valuable.
Available on PyPI.
Use this if you need to reliably extract specific, structured information from a wide variety of web pages (e.g., e-commerce sites, real estate listings) without having to write custom rules for each site.
Not ideal if you only need to extract data from a few specific, unchanging websites and are comfortable writing custom scripts or using simple browser extensions.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 30, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/abdo-Mansour/axetract"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NakaokaRei/SwiftAutoGUI
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and...
dashn9/rustenium
Rust browser automation over the WebDriver BiDi Protocol and CDP
TideSurf/core
Connect Chromium to LLM agents via token-efficient DOM compression. 50-200 tokens per page.
BlackRoadOS/search
Sovereign search engine — search.blackroad.io
johnkozaris/web-interact
Browser automation CLI for AI agents — navigate, discover, click, fill, screenshot, extract