
from anakin20
Self-hosted web scraper API that returns cleaned markdown or structured JSON; includes browser rendering and proxy rotation for JS-heavy or protected sites.
AnakinScraper exposes a self-hosted scraping API that converts arbitrary web pages into readable markdown or structured JSON. It is designed to handle JavaScript-heavy single-page apps and anti-bot protections via an anti-detect browser and proxy auto-selection. The skill documents available endpoints for synchronous and asynchronous scraping, batch jobs, and job polling, plus recommended parameter usage for browser rendering and JSON extraction.
Use AnakinScraper when you need robust extraction from pages that standard HTTP fetches fail on—product listing pages, article archives, SPA-driven content, or sites with basic anti-bot measures. Prefer the async endpoints for slow pages and batch endpoints for multiple URLs.
Agents with network access and the ability to call local HTTP APIs or run containers; useful for data-extraction, research, and content migration tasks.
AnakinScraper is a self-hosted web scraper API skill that provides tools for scraping websites into clean markdown or structured JSON, with browser rendering (Camoufox) and proxy rotation. No bundled scripts were present to test. The SKILL.md is well-documented with clear tool descriptions and usage guidelines. Setup requires cloning a separate repo and running `make up`, which is a minor friction point but standard for self-hosted tools.
No security concerns found. No scripts to audit. The skill is purely a SKILL.md that defines tools calling a local REST API. AGPL-3.0 license noted in frontmatter.