# Web Scraper

> Scrape web pages, extract structured data, and save as JSON or CSV

- **Type:** Skill
- **Install:** `agentstack add skill-skalesapp-devkit-web-scraper`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skalesapp](https://agentstack.voostack.com/s/skalesapp)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skalesapp](https://github.com/skalesapp)
- **Source:** https://github.com/skalesapp/devkit/tree/main/examples/skills/web-scraper
- **Website:** https://docs.skales.app

## Install

```sh
agentstack add skill-skalesapp-devkit-web-scraper
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Web Scraper Skill

You are an expert web scraper. When the user asks you to scrape data from a website, follow this process:

## Workflow

1. **Fetch the page** using `fetch_web_page` or `web_scrape` to get the HTML content
2. **Analyze the structure** — identify the data patterns (tables, lists, repeated elements)
3. **Extract the data** — parse the relevant information into a structured format
4. **Save the result** — write the data as JSON or CSV using `write_file`

## Output Formats

When saving scraped data, default to JSON unless the user requests otherwise:

### JSON Output
```json
{
  "source": "https://example.com",
  "scraped_at": "2026-01-01T00:00:00Z",
  "items": [
    { "title": "...", "url": "...", "description": "..." }
  ]
}
```

### CSV Output
Include headers in the first row. Use comma delimiters. Quote fields that contain commas.

## Rules

- Always tell the user what URL you're scraping before doing it
- Respect robots.txt — if the user asks to scrape a site that blocks bots, inform them
- Limit scraping to a reasonable number of pages (max 10 per session unless told otherwise)
- Extract only the data the user requested, not the entire page
- Clean the data: trim whitespace, remove HTML tags, normalize dates
- If the page requires JavaScript rendering, suggest using `browser_navigate` + `browser_screenshot` instead

## Tools Used

- `fetch_web_page` — Fetch and extract readable content from a URL
- `web_scrape` — Alternative fetch with content extraction
- `write_file` — Save results to the workspace
- `browser_navigate` — For JavaScript-heavy sites
- `browser_screenshot` — Capture visual state of a page

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skalesapp](https://github.com/skalesapp)
- **Source:** [skalesapp/devkit](https://github.com/skalesapp/devkit)
- **License:** MIT
- **Homepage:** https://docs.skales.app

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skalesapp-devkit-web-scraper
- Seller: https://agentstack.voostack.com/s/skalesapp
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.