# Upscrape Universal Web Scraper LLM Integration Prompt

Give this to an LLM or coding agent. It must fetch the OpenAPI spec first and use this brief only for orientation.

## First Step

Fetch and read this OpenAPI spec before writing code:

https://data.upscrape.com/catalog/platforms/web/openapi.json?token=SFMyNTY.g2gDdAAAAAFtAAAAC3BsYXRmb3JtX2lkbQAAAAN3ZWJuBgDBD9VKnwFiAAFRgA.Xr2JtWa-TQB6AWCTHx3mu9j6UfeuWdQx9GHBUN73rr0
This signed OpenAPI URL is valid for approximately 7 days.

## Hard Rules

- Use the OpenAPI spec as the source of truth for endpoints, request bodies, response bodies, errors, and JSON schemas.
- Do not infer fields from capability descriptions; fetch the spec and use its component schemas.
- Authenticate every request with `Authorization: Bearer YOUR_API_KEY`.
- Start runs with `POST /execute`; do not invent platform-specific execute endpoints.
- Poll `GET /jobs/{id}` or `GET /jobs/{id}/result` until `state` is `completed` or `failed`.
- Optionally send `Prefer: wait=N` on `POST /execute` to wait up to N seconds for inline results.
- If the response is `200`, the job completed — read `results[0].data`. If `202`, poll `GET /jobs/{id}`.
- `stream` is public-facing but must remain `false` today.

## API Base

- Base URL: `https://data.upscrape.com`
- OpenAPI spec: `https://data.upscrape.com/catalog/platforms/web/openapi.json?token=SFMyNTY.g2gDdAAAAAFtAAAAC3BsYXRmb3JtX2lkbQAAAAN3ZWJuBgDBD9VKnwFiAAFRgA.Xr2JtWa-TQB6AWCTHx3mu9j6UfeuWdQx9GHBUN73rr0`
- Execute endpoint: `POST /execute`
- Job poll endpoint: `GET /jobs/{id}`
- Result alias: `GET /jobs/{id}/result`
- Content-Type: `application/json`
- Optional header: `Idempotency-Key`
- Optional header: `Prefer: wait=N` (hold connection up to N seconds for synchronous result)

## Execution Flow

1. Send `POST /execute` with a platform capability ID and its `input` object.
2. The API responds with a queued `job_id`.
3. Poll the job endpoint until `state` becomes `completed` or `failed`.
4. If completed, read `results[0].data`; its exact shape is defined by the OpenAPI component schema for the selected capability.

## Example Execute Request

```json
{
  "capability": "web.page.archive",
  "input": {
    "formats": [
      "single_html",
      "zip"
    ],
    "include_scripts": false,
    "url": "https://example.com/"
  }
}
```

## Optional Request Fields

- `network.session_id`: explicit reusable session identifier
- `network.session_key`: stable key used to derive a reusable session
- `network.sticky`: reuse the resolved session when `true`
- `timeout_ms`: per-capability timeout override up to the capability maximum listed below
- `stream`: must be `false`

## Supported Capabilities

- `web.page.archive` - Archive Page. Archive one public webpage into durable offline artifacts for saved-page collections. Returns best-effort self-contained HTML and ZIP snapshots with CSS/images/fonts/media/scripts rewritten or packed, plus optional PDF when a Chrome/Chromium backend is configured. Max `timeout_ms`: 120000. Streaming: disabled.
- `web.page.capture` - Capture Page. Capture one public webpage as a browser-rendered, domain-neutral artifact graph: DOM, text, elements, URLs, links, images, media, resources, structured data, forms, tables, and frames. Max `timeout_ms`: 120000. Streaming: disabled.
- `web.page.extract` - Extract Page. Capture one public webpage and return data shaped by a caller-provided JSON Schema or fields shorthand. Deterministic extraction (metadata, evidence graph, filtered URL enumeration) runs first; internal AI resolves remaining fields per the ai mode (never/auto/always), grounded to captured page content. Max `timeout_ms`: 120000. Streaming: disabled.