skills.rest
whmathews15
whmathews15COMMUNITY
Explore all skills by this author →
GitHub

scrape

Extract web page content with CSS selectors via Scrapling MCP.

1|Updated Jun 28, 2026
Search Tags:#data extraction#mcp#cloudflare#scraping#css selectors#stealth browsing#web extraction
One-click install
npx skills add https://github.com/whmathews15/DEX-Personal-Operating-System --skill scrape-whmathews15
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/whmathews15/DEX-Personal-Operating-System/tree/main/.claude/skills/scrape
Command: npx skills add https://github.com/whmathews15/DEX-Personal-Operating-System --skill scrape-whmathews15

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of collecting content from web pages that are hard to fetch, hard to parse, or protected by anti-bot systems.

Core Features & Use Cases

  • Selector-Based Extraction: Pull only the article, table, or content block you need with CSS selectors to reduce noise and token usage.
  • Adaptive Fetching: Start with fast page retrieval, then escalate to browser rendering or stealth mode when sites rely on JavaScript or Cloudflare protection.
  • Bulk Scraping: Process multiple URLs in parallel when you need consistent extraction across a set of pages.
  • Use Case: Gather pricing details from competitor pages, capture article text from news sites, or extract structured lists from dynamic dashboards.

Quick Start

Ask the assistant to scrape a URL and extract the main content, using a CSS selector if you want only a specific section.

Frequently Asked Questions about scrape

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

FAQPage Schema
How do I extract web data from pages protected by Cloudflare?▼

To extract web data from Cloudflare-protected pages, this Skill uses stealth browsing mode to bypass anti-bot defenses and retrieve rendered content reliably. It escalates from fast fetching to stealth mode when standard retrieval fails.

How do I scrape specific content blocks using CSS selectors?▼

Scraping specific content blocks with CSS selectors filters page elements to pull only the article, table, or section you need. This selector-based extraction reduces noise and lowers token usage by isolating target data.

Can I scrape dynamic JavaScript applications that require browser rendering?▼

Scraping dynamic JavaScript applications is supported through browser-based rendering variants. When sites rely on JavaScript to load content, the Skill escalates from fast page retrieval to full browser rendering to capture the dynamic output.

What is the best way to extract content from multiple URLs in bulk?▼

The best way to extract content from multiple URLs in bulk is using the parallel bulk fetching variant. It processes small-batch URL lists concurrently to retrieve and filter consistent page content across a set of pages.

Do I need Scrapling MCP access to use this web extraction Skill?▼

Yes, you need Scrapling MCP access to use this web extraction Skill. It requires the Scrapling MCP server to provide the fast, browser-based, stealth, and bulk fetch variants needed for reliable page retrieval.

Related Skills

Explore More Software Engineering Skills→
jezwebjezweb
961

cloudflare-browser-rendering

Automate headless browser rendering on Cloudflare Workers for screenshots, PDFs, and scraping.

Community
Intermediate
abdullah1854abdullah1854
1

chrome-data-extract

Generate JavaScript snippets to extract structured data from HTML tables, forms, and lists.

Community
Intermediate
pynbj1001pynbj1001
2

Smart Browser

Extract JavaScript-rendered web page agendas and session data to Markdown and JSON.

Community
Intermediate
Z43LZ43L

scrapling

Extract web content from static, dynamic, and Cloudflare-protected pages.

Community
Advanced