skills.rest
zhu637882-stack
zhu637882-stackCOMMUNITY
Explore all skills by this author →
GitHub

scrape

Extract structured data from web pages into JSON payloads.

1|Updated Apr 6, 2026
Search Tags:#automation#data#json#browser#web#scrape#gstack
One-click install
npx skills add https://github.com/zhu637882-stack/jiaoyi --skill scrape-zhu637882-stack
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/zhu637882-stack/jiaoyi/tree/main/qoder-config-backup/skills/gstack-scrape
Command: npx skills add https://github.com/zhu637882-stack/jiaoyi --skill scrape-zhu637882-stack

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables rapid extraction of structured data from web pages and outputs JSON, removing the need for manual scraping and ad-hoc scripts.

Core Features & Use Cases

  • Prototype browser-based data extraction from pages and produce JSON payloads for downstream workflows.
  • Read-only on the initial call; subsequent calls on a matching intent route to a codified browser-skill and return in ~200ms.
  • Use cases include extracting headlines, metadata, tables, and other structured data without mutating the page; for mutations, use /automate.

Quick Start

Provide a JSON payload containing extracted data from a sample web 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 data from a web page into JSON?▼

Web page data extraction converts on-page content like headlines, metadata, and tables into structured JSON payloads for downstream workflows. This Skill prototypes a read-only browser pass to capture the data without manual scraping scripts.

What's the best way to automate web scraping without writing ad-hoc scripts?▼

Automated web scraping here begins with a read-only prototype call to map the extraction intent, then routes subsequent matching requests to a codified browser-skill that returns JSON in about 200ms.

Does this browser-based extraction approach support mutating actions on web pages?▼

Browser-based extraction is read-only for on-page discovery and data capture. Mutating actions are not handled inline; they must be routed to the /automate endpoint to execute page modifications.

Can I use extracted JSON payloads for prototyping downstream data workflows?▼

Extracted JSON payloads from web pages are designed for downstream use. You provide the JSON output from a sample page to quickly start prototyping data pipelines or integration flows.

How fast is browser-skill data extraction after the initial prototype call?▼

Data extraction speed reaches approximately 200ms for subsequent requests. The initial call is a read-only prototype, after which matching intents route to a codified browser-skill for rapid JSON return.

What types of structured data can I scrape from web pages using this approach?▼

Structured data extraction targets on-page elements like headlines, metadata, and tables. It outputs JSON-ready payloads without mutating the page, making it suitable for discovery and prototyping flows.

Related Skills

Explore More Data & Analytics Skills→
nhattran998nhattran998

scrape

Extracts web page data into JSON using browser primitives and a codified skill.

Community
Intermediate
sanskarbasnetsanskarbasnet
1

scrape

Extract page titles, descriptions, and links as JSON from URLs.

Community
Intermediate
gmoigneugmoigneu
9

agent-browser

Automate browser interactions for testing, form filling, and data extraction.

Community
Intermediate
MonichreMonichre

open-researcher

Gather credible open-source research sources with ranked summaries and citations.

Community
Basic