skills.rest
lemig
lemigCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

scrape

Extract structured data from public web pages as JSON.

Updated May 14, 2026
Search Tags:#json#tables#data-extraction#browser-automation#web-scrape#web-pages
One-click install
npx skills add https://github.com/lemig/transcriptor --skill scrape-lemig
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/lemig/transcriptor/tree/main/.claude/skills/gstack/scrape
Command: npx skills add https://github.com/lemig/transcriptor --skill scrape-lemig

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pull data from a web page. First call on a new intent prototypes the flow via $B primitives and returns JSON. Subsequent calls on a matching intent route to a codified browser-skill and return in ~200ms. Read-only — for mutating flows (form fills, clicks, submissions), use /automate.

Core Features & Use Cases

  • Prototyping data extraction flows on new intents using browser primitives
  • Routing to a codified browser-skill for deterministic JSON results on repeats
  • Read-only data gathering with mutation support via /automate

Quick Start

Provide a URL and data targets, and I will return the structured JSON data from that page.

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I extract structured JSON data from web pages?▼

You can extract structured JSON data from web pages by providing a URL and data targets. The Skill prototypes the extraction flow using browser primitives and returns results from tables, lists, or metadata.

What is the best way to scrape data from tables and lists on public web pages?▼

Scraping data from tables and lists is handled by prototyping a read-only extraction flow on the first call, which then routes to a codified browser-skill for fast, deterministic JSON responses on subsequent calls.

Can I use web scraping to fill out forms or submit data?▼

No, this web scraping capability is strictly read-only by default. For mutating flows like form fills, clicks, and submissions, you must route the task through the /automate command.

How fast is browser automation for repeated data extraction tasks?▼

For repeated data extraction tasks, browser automation routes to a codified browser-skill after the initial prototype call, delivering structured JSON results in approximately 200ms.

Do I need to install dependencies to scrape public web pages?▼

No dependencies are required to scrape public web pages. The Skill relies on built-in Bash, Read, and AskUserQuestion primitives to prototype the extraction flow and guide the interaction.

Why does my web scrape return incomplete data on multi-page flows?▼

A web scrape might return incomplete data if the multi-page flow is not fully prototyped. The first call prototypes the flow, and subsequent matching calls route to a codified browser-skill for deterministic results.

Related Skills

Explore More Software Engineering Skills→
eskoNBGeskoNBG
1

web-reader

Retrieve structured web page content and metadata from a URL.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
TwoTonedTwoToned

scrape

Prototype web scraping flows with shell-like primitives and return JSON.

Official
Advanced
TumeloRamaphosaTumeloRamaphosa

scrape

Extract read-only web page information into structured JSON.

Community
Intermediate