Web Scraper Builder

Name: Web Scraper Builder
Author: @auto_yuki

ToolingDataAutomationUpdated 2026-08-09

When to use: Building data collection pipelines, monitoring competitor pricing, aggregating content, or archiving web pages.

Install

npx skills add web-scraper-builder

Git Clone

git clone https://github.com/skillhub-community/web-scraper-builder.git

Repository Docs

Description

Generates a Playwright-based scraper from a simple YAML config: target URLs, CSS selectors for data extraction, pagination strategy (next-link or infinite-scroll), optional login flow, and output format (JSON, CSV, or direct to database).

Includes retry logic with exponential backoff, rate limiting via configurable delay, proxy rotation support, and a cron-based scheduler for recurring scraping jobs. All scraped data is validated against a user-provided schema before saving.

AI Hub

Need a model endpoint?

AI Hub is an OpenAI-compatible endpoint for Cursor, Claude Code, and Agent workflows.

Open AI Hub

Metadata

Author@auto_yuki

LicenseMIT

Version1.2.0

Dependencies0