# zyte-web-data

Turn a site URL and an extraction request into a tested Scrapy project. Useful for product catalogs, job listings, and other pages with repeating structured content.

- plugin · `type=plugin` · Claude Code · ★ 33
- Author: Zyte
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/zytedata/claude-skills
- Updated: 2026-10-05
- HTML: https://affpapa.org/en/nevibecode/plugins/zyte-web-data

## What it does

Give the plugin a URL and say which fields you need. It explores the site, proposes an extraction schema for your approval, then builds a Scrapy project with web-poet page objects and test fixtures. The `/scrape` workflow plans the extraction before generating the spider and running a smoke test.

Run the generated spider locally with `uv run scrapy crawl <spider_name>` and test it with `uv run pytest fixtures/`. The project uses `uv`; its dependencies, including `scrapy` and `pytest`, are installed automatically. A Zyte account is needed for Scrapy Cloud or Zyte API. JavaScript browser rendering requires a Zyte API key.

Use `/zyte` to deploy a project to Scrapy Cloud. Zyte MCP is declared by the plugin, so there is no need to add it separately with `claude mcp add`; sign in from an active Claude Code session using `/mcp`.

## Install

### Claude Code (native platform)

**Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin install zyte-web-data@claude-plugins-official
```
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-community
```
In the agent chat (not a shell):
```text
/plugin install zyte-web-data@claude-community
```
In the agent chat (not a shell):
```text
/plugin marketplace add anthropics/claude-plugins-official
```

## When to use it
- extract requested fields from a site URL
- build a Scrapy project for a product catalog or job listings
- run spider tests and a smoke test
- deploy a project to Scrapy Cloud

## Example prompts
- Create a spider to collect product names and prices from this URL.
- Propose an extraction schema for these listing pages, then build and test the Scrapy project.
- Deploy the finished project to Scrapy Cloud.

## Similar
- [last-30-days-skill](https://affpapa.org/en/nevibecode/plugins/last-30-days-skill.md) — plugin · ★ 65701
- [playwright](https://affpapa.org/en/nevibecode/plugins/playwright.md) — plugin · ★ 44967
- [browser-harness](https://affpapa.org/en/nevibecode/plugins/browser-harness.md) — plugin · ★ 18664
- [visual-pr](https://affpapa.org/en/nevibecode/plugins/visual-pr.md) — plugin · ★ 40478
- [chromium-control-canvas](https://affpapa.org/en/nevibecode/plugins/chromium-control-canvas.md) — plugin · ★ 40478
- [exa](https://affpapa.org/en/nevibecode/plugins/exa.md) — plugin · ★ 5190

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md