web-scraper

Extract structured web data using Playwright and Codex Vision.

Updated Mar 1, 2026

Search Tags:#automation #structured data #data extraction #web scraping #playwright #codex vision

Ready to run

npx skills add https://github.com/mqzkim/trading --skill web-scraper-mqzkim

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-scraper
Source: https://github.com/mqzkim/trading/tree/main/.agents/skills/web-scraper
Command: npx skills add https://github.com/mqzkim/trading --skill web-scraper-mqzkim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the intelligent extraction of structured data from websites, overcoming the challenges of dynamic content and complex page structures.

Core Features & Use Cases

AI-Powered Scraping: Leverages Codex Vision to understand page structure and extract specific data points.
Dynamic Content Handling: Uses Playwright to render and interact with Single Page Applications (SPAs) and dynamic websites.
Structured Output: Provides extracted data in a structured JSON format based on defined schemas.
Use Case: Extracting product pricing and availability from an e-commerce site, or gathering contact information from a business directory.

Quick Start

Use the web-scraper skill to extract pricing information from the URL https://example.com/product.

Frequently Asked Questions about web-scraper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract structured data from a dynamic website?▼

Web scraping dynamic websites involves using headless browser technology to render JavaScript and AI to semantically understand the page. This Skill handles dynamic content rendering and extracts structured data into JSON format.

Can I scrape e-commerce product details and pricing information?▼

Yes, you can scrape e-commerce product details and pricing information. The Skill applies AI to intelligently extract specific data points like product pricing and availability from complex web structures.

Does web scraping with Playwright work for Single Page Applications?▼

Web scraping with Playwright works effectively for Single Page Applications by using its headless browser capabilities to fully render dynamic content before extracting the structured data.

What is the best way to automate web data extraction for contact information?▼

The best way to automate web data extraction for contact information is using an AI-driven approach that understands semantic page structure, allowing you to gather business directory details without manual formatting.

How does AI handle complex page structures during data extraction?▼

AI handles complex page structures during data extraction by leveraging Codex Vision to semantically understand the layout and identify specific data points, overcoming traditional scraping challenges.