skills.rest
BulloRosso
BulloRossoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

web-scraping

Crawl websites and extract content using the web-scraper MCP server.

32|3|Updated Sep 30, 2025
Search Tags:#javascript#web-scraping#crawl#content-extraction#css-selectors#data-retrieval
One-click install
npx skills add https://github.com/BulloRosso/etienne --skill web-scraping-bullorosso
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: web-scraping
Source: https://github.com/BulloRosso/etienne/tree/main/skill-repository/standard/web-scraping
Command: npx skills add https://github.com/BulloRosso/etienne --skill web-scraping-bullorosso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web scraping tasks can be tedious and error-prone when performed manually. This skill automates crawling websites and extracting their content, saving results to a centralized location (web-crawling/) organized by site.

Core Features & Use Cases

Three retrieval modes are supported: quick retrieval for fast, static pages; browser-based retrieval to render JavaScript-heavy sites; and stealth retrieval to handle bot protection. It saves results to web-crawling/ organized by site, and supports CSS selector filtering to extract only the relevant parts. Bulk operations allow fetching multiple URLs in parallel for efficient data collection.

Quick Start

Provide a target URL and instruct the agent to crawl it and save the extracted content to web-crawling/.

Frequently Asked Questions about web-scraping

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

FAQPage Schema
How do I extract content from JavaScript-rendered websites?▼

Extract content from JavaScript-rendered websites using browser-based retrieval to fully render dynamic pages. For bot-protected pages, stealth retrieval bypasses restrictions, saving extracted content to a localized directory.

Can I use CSS selectors to extract specific HTML elements from a web page?▼

Yes, you can use CSS selectors to extract specific HTML elements. By setting the css_selector option, the content extraction process filters the page and outputs only the matching elements.

What is the best way to crawl multiple URLs in parallel for data collection?▼

The best way to crawl multiple URLs in parallel is using bulk operations. This functionality fetches multiple targets simultaneously for efficient data collection, saving results organized by each site.

Do I need a specific service running to perform automated web scraping?▼

Yes, automated web scraping requires the web-scraper service to run on port 3480. This local service processes retrieval requests and manages content extraction across static, dynamic, and protected pages.

How are extracted web scraping results organized and saved?▼

Extracted web scraping results are saved to a centralized web-crawling directory organized by site. This structure ensures that crawled content from different domains remains separated and easily accessible.

Related Skills

Explore More Data & Analytics Skills→
platonaiplatonai
1.1k

web-scraping

Extract titles, text, and structured fields from web pages using browser automation.

Community
Intermediate
breverdbidderbreverdbidder
1

firecrawl-scrape

Extract clean markdown content from URLs with JavaScript rendering support.

Community
Basic
pynbj1001pynbj1001
2

scrapling-official

Scrapes JavaScript-rendered and anti-bot protected websites using adaptive parsing and stealth browser automation.

Community
Advanced
antgroupantgroup
16

web-pilot

Automate web searches and extract page content via Playwright and Chromium.

Official
Advanced