A high-performance browser automation tool for scraping complex, JavaScript-heavy websites using real browser interactions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install miliger-playwright-scraper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install miliger-playwright-scraper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Playwright Scraper?
The Playwright Scraper is a robust skill designed to handle modern, dynamic web environments that traditional scrapers often fail to process. By leveraging a real browser engine, it can perform human-like actions such as clicking buttons, scrolling through lazy-loaded content, and waiting for complex JavaScript to render. This makes it an essential component of Openclaw Skills for developers needing to extract structured data from Single Page Applications (SPAs) or multi-tabbed interfaces. It bridges the gap between simple HTTP requests and fully automated browser workflows, providing a reliable way to turn the dynamic web into structured, actionable data.
Playwright Scraper Use Cases
- Extracting data from complex public information sites like conference agendas, exhibition schedules, and event calendars.
- Scraping Single Page Applications (SPAs) where content is loaded asynchronously via JavaScript.
- Automating data collection from websites requiring multi-tab navigation or specific user interactions to reveal content.
- Gathering information from pages with infinite scroll or lazy-loaded elements that require triggered viewport movement.
How Playwright Scraper Works
- Initialize the browser environment using the Playwright engine, supporting both headless and headed modes for debugging.
- Navigate to the target URL and implement smart wait strategies, such as waiting for network idle or specific DOM selectors.
- Execute interaction scripts—either pre-defined or generated by AI—to perform clicks, scrolls, and tab switching.
- Evaluate the page context to extract specific DOM elements and map them to a defined data structure.
- Transform the raw extracted data into clean Markdown or JSON formats and save them to the local filesystem.
Playwright Scraper Setup
To integrate this into your environment, install the necessary dependencies and browser binaries using the following commands:
npm install playwright
npx playwright install chromium
Playwright Scraper Data Schema & Taxonomy
The skill organizes extracted data into structured formats, typically converting DOM elements into clear key-value pairs. Output is usually formatted as follows:
| Attribute | Description | Typical Format |
|---|---|---|
| title | The main heading or identifier of the data item | String |
| time | Temporal data associated with the entry | String |
| location | Physical or digital venue information | String |
| content | Detailed body text or session descriptions | Markdown |
Files are systematically saved using descriptive naming conventions like source-category.md or data.json for easy retrieval within Openclaw Skills workflows.
Playwright Scraper Advanced Features
- Real-time AI script generation that analyzes page structures on the fly without requiring pre-written selectors.
- Persistent Chrome profile support to maintain login sessions and cookies across multiple scraping instances.
- Aggressive performance optimization through resource interception, allowing the blocking of images and CSS to speed up data extraction.
- Advanced anti-detection techniques, including custom user-agent headers and the disabling of the navigator.webdriver flag.
SKILL.md
Loading
Related Openclaw Skills
Context Manager
An intelligent context management skill that automates session switching and memory persistence to ensure uninterrupted AI agent workflows.
Interactive Card Reader
A specialized tool for Openclaw Skills that automatically extracts and parses structured JSON data from interactive message cards on enterprise platforms.
Image Content Extractor
A smart OCR tool that automatically detects image types and extracts structured content into high-quality Markdown format.
Context Manager
An intelligent context management skill that automates session transitions through background monitoring and seamless memory persistence.
miliger-qmd-manager
A unified knowledge management skill that integrates official qmd search with custom project, testing, and content creation repositories.
Context Manager
An intelligent context management skill that monitors session usage and automates memory transfers to prevent data loss and ensure session continuity.
Featured*
