How does this skill handle websites requiring login?

It implements a dedicated Login phase that detects authentication states via semantic elements and persists session data to an auth-state.json file to avoid repeated logins.

What is the benefit of the 3-phase process?

The Login-Index-Show sequence ensures each stage is verified before moving forward, preventing resource waste and ensuring the data model is fully understood before extraction begins.

Does it support modern JavaScript frameworks like React?

Yes, it includes specific strategies for interacting with React and HeadlessUI components, using ARIA roles and state-triggering actions instead of fragile CSS paths.

How does this skill ensure data quality?

The workflow mandates output verification, including file count matching, empty file detection, and content-type validation to ensure the extracted data matches the expected format.

Playwright Web Scraper

Name: Playwright Web Scraper
Author: alizain

byalizain

ウェブスクレイピングとデータ収集

Extracts structured data from complex websites using a robust, three-phase Playwright automation workflow.

概要

This skill provides a standardized framework for building resilient web scrapers with Playwright within the Claude Code environment. It guides users through a rigorous 3-phase process—Login, Index, and Show—ensuring that authentication is handled persistently, site hierarchies are accurately mapped, and data is extracted using stable semantic selectors. By emphasizing incremental script development over ephemeral exploration, this skill enables the creation of scrapers that are reproducible, recoverable from failures, and capable of handling dynamic modern web frameworks like React and HeadlessUI.

主な機能

0 GitHub stars
Standardized 3-phase sequential workflow: Login, Index, and Show
Robust authentication persistence using storage state patterns
Semantic selector design for stability against minor site updates
Incremental script building with built-in verification and screenshot checkpoints
Advanced handling for dynamic SPA components like tabs and accordions

ユースケース

Scraping high-volume product catalogs or documentation from complex SPAs
Automating data extraction from authenticated dashboards or paywalled content
Building long-running, recoverable scrapers for paginated or nested data structures

概要

主な機能

0 GitHub stars
Standardized 3-phase sequential workflow: Login, Index, and Show
Robust authentication persistence using storage state patterns
Semantic selector design for stability against minor site updates
Incremental script building with built-in verification and screenshot checkpoints
Advanced handling for dynamic SPA components like tabs and accordions

ユースケース

Scraping high-volume product catalogs or documentation from complex SPAs
Automating data extraction from authenticated dashboards or paywalled content
Building long-running, recoverable scrapers for paginated or nested data structures