# Web Scraper

> Extracts structured data from web pages. Use for: scrape page, extract from website, get page data, web extract.

- Skill: `stijnman/web-scraper` (Agent Skill)
- Install (CLI): `npx skillmds@latest add stijnman/web-scraper`
- Raw SKILL.md: https://api.skillmd.com/api/skills/stijnman/web-scraper/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: Stijnman (https://skillmd.com/u/stijnman)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/stijnman/web-scraper

---

# Web Scraper
## When to Use

- User says **scrape page** or task matches this capability
- User says **extract from website** or task matches this capability
- User says **get page data** or task matches this capability
- User says **web extract** or task matches this capability

## Workflow

1. Fetch via sandbox-internet-handler or WebFetch.
2. Parse HTML to text, tables, or JSON per user spec.
3. Respect robots.txt and rate limits.
4. Return data with source URL and timestamp.

## Integrations

- `sandbox-internet-handler`
- `humanization-stealth-browsing`
- `internet-enabler`

## Error Handling

| Failure | Response |
|---------|----------|
| Blocked by site | Try stealth mode or ask user for export. |

## Gotchas

- Never scrape authenticated pages without user session.

## Example

**Input:** User request matching triggers above.
**Output:** Structured result per workflow with integrations invoked as needed.