Scraping

Community

Web scraping via progressive escalation.

AuthorRooseveltAdvisors
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a robust solution for extracting web content, even from sites that employ bot detection, CAPTCHAs, or require JavaScript rendering, by progressively escalating through different scraping methods.

Core Features & Use Cases

  • Four-Tier Scraping: Utilizes WebFetch, custom Curl, Browser Automation (Playwright), and Bright Data MCP as fallbacks.
  • URL Scraping: Reliably fetches content from any single URL.
  • Site Crawling: Capable of crawling multiple pages within a site.
  • Use Case: When a website blocks direct access or requires JavaScript to load content, this Skill can automatically switch to more advanced methods like Bright Data to ensure content retrieval.

Quick Start

Use the BrightData skill to scrape the content from the URL https://example.com.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Scraping
Download link: https://github.com/RooseveltAdvisors/claude-agent-stack/archive/main.zip#scraping

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.