
Web Scraper
A straightforward Python scraper that saves web pages as HTML or Markdown with downloaded images, no browser automation required. Just requests and BeautifulSoup4. Single page mode is fast for archiving articles or documentation. Recursive mode follows links with sensible guardrails: depth limits, rate limiting, robots.txt compliance by default. Images get saved to a local folder automatically, which is nice for offline viewing. The recursive crawling is sequential rather than parallel, so it's polite but not blazing fast. Good for documentation snapshots or building local archives when you need actual files on disk, not just viewing in a browser.
- skills.sh installs
- 230
- GitHub stars
- 50
- last updated
- Aug 21, 2026
Install
$ npx -y skills add agentbay-ai/agentbay-skills --skill web-scraper --agent claude-codeInstalls into .claude/skills of the current project.
Files
Web Scraper
Fetch web page content (text + images) and save as HTML or Markdown locally.
Minimal dependencies: Only requires requests and beautifulsoup4 - no browser automation.
Default behavior: Downloads images to local images/ directory automatically.
Quick start
Single page
{baseDir}/scripts/scrape.py --url "https://example.com" --format html --output /tmp/page.html
{baseDir}/scripts/scrape.py --url "https://example.com" --format md --output /tmp/page.md
Recursive (follow links)
{baseDir}/scripts/scrape.py --url "https://docs.example.com" --format md --recursive --max-depth 2 --output ~/Downloads/docs-archive
Setup
Requires Python 3.8+ and minimal dependencies:
cd {baseDir}
pip install -r requirements.txt
Or install manually:
pip install requests beautifulsoup4
Note: No browser or driver needed - uses pure HTTP requests.
Inputs to collect
Single page mode
- URL: The web page to scrape (required)
- Format:
htmlormd(default:html)
Sponsors
Details
- Repository
- github.com/agentbay-ai/agentbay-skills
- Category
- Frontend Development
- First seen
- Jun 3, 2026