Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Updated SKILL.md to generalize all descriptions and examples, removing product-specific names and user-specific paths.
What This Skill Does
Scrapes documentation content from Zoomin Software portals using a headless Chromium browser. Standard HTTP fetching fails on these portals because content loads dynamically via JavaScript. The skill navigates to each URL, waits for the main article element to render, then extracts the text.
Executes JavaScript and waits for DOM rendering, capturing content that standard HTTP scrapers miss entirely on Zoomin portals.
When to use it
- Batch downloading Zoomin-hosted vendor documentation
- Archiving product docs before portal access expires
- Building a local knowledge base from dynamic documentation sites
- Extracting text from docs that return empty content via requests/BeautifulSoup
- Processing a list of documentation URLs into plain text files
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Scrape these 40 Zoomin documentation URLs and save the content to a local folder'
- 1Creates a text file with one target URL per line
- 2Runs run_scraper.sh with the URL file path, output directory, and virtual environment path
- 3Playwright launches headless Chromium and navigates to each URL in sequence
- 4Waits for the article element with id 'zDocsContent' to finish loading
- 5Saves the extracted text to individual files in the output directory
Plain text files in the output directory, each containing the rendered documentation body from one URL
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.