just-scrape

Extract structured JSON data and convert webpages to markdown via the just-scrape CLI.

1|Updated Feb 20, 2026
One-click install
npx skills add https://github.com/makerjackie/jackie-skills-starter --skill just-scrape-makerjackie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: just-scrape
Source: https://github.com/makerjackie/jackie-skills-starter/tree/main/skills/just-scrape
Command: npx skills add https://github.com/makerjackie/jackie-skills-starter --skill just-scrape-makerjackie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the manual effort of collecting, structuring, and converting web content by providing an AI-powered command-line interface that extracts structured data, raw HTML, or clean markdown from webpages and automates browser interactions.

Core Features & Use Cases

  • Smart extraction: AI-driven extraction to produce JSON objects from product pages, articles, or dashboards.
  • Crawl & sitemap discovery: Multi-page crawling, sitemap URL listing, and depth/max-page controls for site-wide data collection.
  • Browser automation: Agentic actions for login, clicks, form fills, and session persistence to access protected or JS-heavy sites.
  • Search & convert: Web search with extraction and conversion of pages to markdown for documentation or research workflows.
  • Schema-first workflows: Generate or enforce JSON schemas to ensure consistent structured output for pipelines and integrations.

Quick Start

Run the just-scrape smart-scraper on a product page to extract names, prices, and ratings using a clear extraction prompt and an optional JSON schema.

Frequently Asked Questions about just-scrape

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

FAQPage Schema
How do I extract structured data from a webpage and convert it to JSON?

You can extract structured data from a webpage and output JSON by providing a URL and an extraction prompt to the scraper, optionally enforcing a JSON schema to ensure consistent structured output for your pipelines.

Can I crawl multiple pages and discover URLs using a sitemap?

Yes, you can crawl multiple pages and discover URLs using sitemap discovery, controlling the scope of site-wide data collection with depth and max-page limits.

Does web scraping work with JavaScript-heavy sites that require login?

Web scraping works with JavaScript-heavy sites requiring login through browser automation, handling agentic actions like clicks, form fills, and session persistence to access protected content.

What is the best way to convert webpages to markdown for research documentation?

The best way to convert webpages to markdown for research is using an AI-powered scraper that performs web searches and directly converts the retrieved pages into clean markdown outputs.

How do I handle anti-bot measures when scraping a website?

You can handle anti-bot measures during web scraping by enabling stealth mode, which allows the scraper to bypass detection while extracting raw HTML or structured data.

Do I need an API key to scrape web content from the command line?

Yes, you need an API key for authentication to integrate and run the command-line scraper, enabling automated web searches and data extraction workflows.