manikantasai-playwright-automation
由 manikantasai1987 提供
Web & Frontend Development简介
Browser automation using Playwright API directly.
描述
该技能的功能
Browser automation using the Playwright API directly. Supports navigating websites, interacting with page elements, extracting data, taking screenshots, generating PDFs, and recording videos.
Direct API use avoids the overhead and reliability issues of MCP-based browser automation.
何时使用
- Scraping product prices from e-commerce sites
- Automating login and form submission flows
- Capturing full-page screenshots for visual regression
- Generating PDF reports from web dashboards
- Recording browser sessions for QA documentation
示例工作流
User asks: extract all product names and prices from a paginated table
- 1
Launch a headless Chromium browser
- 2
Navigate to the target URL and wait for the table to load
- 3
Use page.$$eval to iterate table rows and extract text from each cell
- 4
Handle pagination by clicking the next button and repeating extraction
- 5
Aggregate results and return as structured data
Array of objects with name and price fields for each product row
安装
clawhub install manikantasai1987/manikantasai-playwright-automation运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。