# Scrapo

> Scrapo — vikast908-scrapo. Use this tool when you need to extract data from websites efficiently and reliably, solving problems of data collection and monitoring by handling anti-scraping measures and ensuring compliance. Scrapo takes in website URLs and extraction rules as input, and outputs structured data, with a Python interface for integration with other tools. Use Scrapo in web development, data science, and research contexts where automated data extraction is necessary.

Canonical page: https://skillsregistry.net/skills/vikast908-scrapo  
JSON: https://api.skillsregistry.net/v1/skills/vikast908-scrapo

## Description

AI-native, agent-first web scraping for Python. Cost-aware tiered fetching (HTTP, browser, stealth, agent), model-agnostic LLM extraction with self-healing selector caches, API-first resolution, deterministic replay and field-level diff, and an MCP server.

## Trust

- **Trust score (0–1):** 0.51
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** browser-automation
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/vikast908/Scrapo)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "vikast908-scrapo"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vikast908-scrapo` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vikast908-scrapo/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt