Can this skill handle websites that require JavaScript?

Yes, the third tier uses browser automation to fully render JavaScript-driven content before extracting the data, making it ideal for modern web applications.

Do I always need a Bright Data account to use this?

No, the skill first tries three local methods (Native, Curl, and Playwright) which are free and fast. The Bright Data tier is only activated as a final resort for highly protected sites or when explicitly requested.

In what format is the scraped data returned?

Regardless of the scraping tier used, the skill returns the final content in clean, structured Markdown, making it easy for Claude to analyze and process the information.

How does the four-tier scraping strategy work?

The skill attempts to fetch content using the simplest method first (WebFetch). If that is blocked, it automatically escalates to Curl with custom headers, then Browser Automation, and finally the Bright Data MCP for advanced bot mitigation.

Bright Data Advanced Scraper

Name: Bright Data Advanced Scraper
Author: Activer007

byActiver007

•

웹 스크래핑 및 데이터 수집

Retrieves web content through a progressive four-tier fallback strategy to bypass bot detection and JavaScript barriers.

The Bright Data skill equips Claude Code with a robust, multi-layered approach to web scraping and content extraction. It intelligently escalates through four distinct stages: starting with fast native fetching, moving to customized curl requests with browser headers, advancing to full browser automation for JavaScript-heavy sites, and finally utilizing professional Bright Data services for the most difficult anti-bot protections and CAPTCHAs. This ensures that you can retrieve reliable, markdown-formatted content from any URL while maintaining optimal speed and resource efficiency.

주요 기능

01Seamless Bright Data MCP integration for solving CAPTCHAs and residential proxy needs

02Four-tier progressive escalation strategy for reliable data retrieval

03Automatic fallback logic to bypass advanced bot detection and 403 errors

048 GitHub stars

05Full JavaScript rendering support via integrated browser automation

06Converts complex HTML structures into clean, structured Markdown automatically

사용 사례

01Scraping data from protected sites that block standard automated agents

02Extracting content from single-page applications (SPAs) and dynamic web pages

03Gathering research material from high-security domains with rate limiting

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills brightdata

For use in Claude.ai and ChatGPT

Download Skill