# AI Structured Web Data Extraction API
Extract structured JSON fields from a webpage using instructions.
## API Overview
- **HTTP Protocol:** HTTPS
- **HTTP Method:** POST
- **HTTP Endpoint:** https://api.gugudata.io/v1/websitetools/url2json
- **Response Type:** application/json; charset=utf-8
- **DEMO Endpoint:** https://api.gugudata.io/v1/websitetools/url2json/demo
- **Live Demo:** https://gugudata.io/demo/url2json
- **Postman:** https://www.postman.com/gugudata/gugudata-io
- **LLM Page:** https://gugudata.io/details/url2json/llm
- **Raw Markdown:** https://gugudata.io/details/url2json/llm.md
## Remote MCP
- **MCP Endpoint:** https://mcp.gugudata.io/mcp
- **MCP Guide:** https://gugudata.io/mcp/
- **Authorization:** OAuth authorization opens in the browser; do not paste appkeys into MCP clients.
- **Tool Scope:** MCP clients receive GuGuData API tools available to the authorized account.
## Data & API Features
- Webpage fields from an instruction: Provide a webpage URL and extraction instruction, then receive structured JSON fields for the requested data.
- AI agent extraction workflow: Use the response in agents, automations, and RAG pipelines that need clean structured data from public webpages.
- Flexible structured results: Describe the fields you need, then validate the extracted JSON for your application. Explicit empty lists represent no matches.
- Reduces custom parser work: Avoid writing one-off scrapers for every page layout when your product only needs a specific structured result.
- Automation-ready response fields: Return JSON that backend jobs, no-code tools, enrichment workflows, and internal dashboards can consume directly.
- Standalone structured extraction API: Subscribe to this interface when the output should be JSON; use fetchcontent when the workflow mainly needs article text.
## API Request Parameters
| Name | Type | Is Required | Default Value | Remark |
| --- | --- | --- | --- | --- |
| appkey | string | true | YOUR_APPKEY | API key used to authenticate the request. |
| url | string | true | | Public HTTP or HTTPS webpage URL to extract from. |
| prompt | string | true | | Describe the fields to extract. Returned fields depend on your instruction and the page content. |
## API Response Parameters
| Name | Type | Remark |
| --- | --- | --- |
| dataStatus | object | Response metadata returned by the current v1 contract. |
| dataStatus.requestParameter | string | Privacy-safe summary of the normalized request. |
| dataStatus.statusCode | integer | Application-level status code. |
| dataStatus.status | string | Application-level result status. |
| dataStatus.statusDescription | string | Human-readable application status message. |
| dataStatus.responseDateTime | string | Time at which the response was generated. |
| dataStatus.dataTotalCount | integer | Number of matching or returned records for this request. |
| data | object | Dynamic JSON object. Article arrays are wrapped in articles; other arrays in items. Explicit empty lists are valid no-match results. Empty content returns HTTP 422, invalid extraction responses HTTP 502, and unavailable service HTTP 503; these failures use business code 500. |
## API Response Status Codes
| Status Code | Explanation of Status Code | Remarks |
| --- | --- | --- |
| 200 | Request processed successfully. | Some endpoints expose a separate application-level status field in the response body, such as `dataStatus.statusCode`. |
| 400 | Invalid request parameters or request format. | Check required fields, data types, and request body format. |
| 401 | Missing or unknown application key. | Provide a valid `appkey` with the request. |
| 403 | The application key is recognized but access is not allowed. | The key may be expired, inactive, or not permitted for the requested API. |
| 429 | Request rate or trial usage limit exceeded. | Reduce request frequency and retry with backoff. If a trial allowance is exhausted, check Trial Keys for remaining requests and subscribe to continue. |
| 500 | Internal service error. | Retry later or contact support if the error persists. |
| 503 | Upstream service unavailable. | Retry later; the requested upstream dependency is temporarily unavailable. |
## cURL Example
```bash
curl --location 'https://api.gugudata.io/v1/websitetools/url2json?appkey=YOUR_APPKEY' --request POST --header 'Content-Type: application/json' --data '{
"url": "YOUR_VALUE",
"prompt": "YOUR_VALUE"
}'
```