site-miner

Extract targeted data from websites via Playwright MCP into JSON.

3|3|Updated Jan 26, 2026

Search Tags:#playwright #browser #information-extraction #structured-data #data-scraping #site-monitoring

Ready to run

npx skills add https://github.com/hs3180/disclaude --skill site-miner

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: site-miner
Source: https://github.com/hs3180/disclaude/tree/main/skills/site-miner
Command: npx skills add https://github.com/hs3180/disclaude --skill site-miner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Site information mining from a single website using browser automation to extract targeted data, monitor page content, and verify functionality.

Core Features & Use Cases

Automated data extraction from a specified site (prices, headers, metadata) using Playwright MCP.
Page monitoring and verification to detect content changes or issues over time.
Output data in structured formats (JSON) for downstream analysis and automation.

Quick Start

Navigate to the target website using Playwright MCP, snapshot the page structure, and extract the requested data into a structured result.

Frequently Asked Questions about site-miner

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

FAQPage Schema

How do I extract structured data from a website using browser automation?▼

You can extract structured data using browser automation by navigating to the target site, taking snapshots of the page structure, and pulling specified data points into a JSON result. This handles dynamic content by applying waits during navigation.

Can I monitor page content changes over time for a specific site?▼

Yes, page monitoring and verification detects content changes over time by repeatedly running browser automation against a defined target site. It validates site functionality and returns the observed changes in structured JSON format.

Does Playwright MCP work for scraping dynamic content that requires waits?▼

Yes, Playwright MCP handles dynamic content by applying navigation waits and capturing page snapshots. This ensures that dynamically loaded elements are fully rendered before the targeted data points are extracted into the JSON output.

How do I capture prices and metadata from a single website into JSON?▼

You capture prices and metadata by navigating to the target website with Playwright MCP, snapshotting the page structure, and extracting the requested data points. The output is returned as structured JSON data ready for downstream analysis.

What is the best way to verify site functionality without manual checking?▼

Browser automation verifies site functionality by navigating defined target sites, applying waits for dynamic elements, and capturing optional evidence via snapshots. This automates validation and returns structured data confirming page behavior.