scrape

Extract structured data from public web pages into parsed JSON output.

Updated Jul 21, 2025
One-click install
npx skills add https://github.com/robertzengcn/aiFetchly --skill scrape-robertzengcn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/robertzengcn/aiFetchly/tree/main/.agents/skills/gstack/scrape
Command: npx skills add https://github.com/robertzengcn/aiFetchly --skill scrape-robertzengcn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the tedious manual work of copying and formatting data from web pages, saving you hours of repetitive data entry and reducing human error from manual transcription.

Core Features & Use Cases

  • Fast Read-Only Scraping: Pull structured data from any web page in ~200ms for repeat requests, with no risk of accidental form submissions or unintended site mutations.
  • Prototype-First Workflow: First calls on new intents prototype the extraction flow via $B primitives and return JSON, so you can validate data structure before codifying repeatable scraping tasks.
  • Use Case: Use it to scrape business names, ratings, and contact info from Google Maps listings for lead generation, or pull product details from e-commerce pages for market research, all without writing custom scraping scripts.

Quick Start

Use the scrape skill to pull all business names, ratings, and phone numbers from the Google Maps search results page for "coffee shops in Seattle".

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I extract structured data from a web page without writing custom scraping scripts?

Web scraping without custom scripts is possible by pulling structured data directly from public web pages. This Skill returns parsed JSON output, eliminating manual copy-paste and reducing human transcription errors.

What's the best way to scrape contact info and business listings for lead generation?

Scraping contact info for lead generation is best handled by pulling business names, ratings, and phone numbers directly from directory pages. It applies to business directory scraping and returns structured JSON for fast retrieval.

Can I pull structured data from Google Maps listings for market research?

Pulling structured data from Google Maps listings is supported for market research. You can scrape business names, ratings, and contact info from search results pages in about 200ms for repeat requests.

How do I validate the JSON data structure before codifying a repeatable scraping task?

Validating JSON data structure for repeat scraping tasks uses a prototype-first workflow. First calls on new intents prototype the extraction flow and return JSON, allowing you to validate the data structure before finalizing the task.

Does read-only web scraping risk accidental form submissions or site mutations?

Read-only web scraping carries no risk of accidental form submissions or unintended site mutations. It safely retrieves page content in approximately 200ms for repeat requests without altering the target site.

Can I extract product details from e-commerce pages without manual data entry?

Extracting product details from e-commerce pages is supported without manual data entry. The Skill pulls structured data from public web pages and returns parsed JSON output, saving hours of repetitive transcription.