# ChatGPT

The LLM Scraper enables retrieval of ChatGPT responses- including optional search-enhanced answers and returns a structured JSON output.

***

### **API Setup**

#### **Endpoint**

```http
https://llm-scraper.netnut.io/search
```

***

### **Authentication**

Use HTTP Basic Authentication:

```
Authorization: Basic <base64(username:password)>
```

Where `<base64(username:password)>` is the Base64-encoded string of your NetNut credentials.

***

### **Request Body Schema**

```json
{
  "prompt": "Explain SEO ranking factors in 2025",   // Required
  "country": "us",                                   // Optional
  "web_search": false,                               // Optional, default false
  "follow_up_prompt": "Summarize in 5 bullets",      // Optional
  "engine": "chatgpt",                               // default: chatgpt
  "raw_response" : false,                            // Optional, default false
  "throttling": true                                 // Optional, default true
}
```

#### **Field Descriptions**

| Field                  | Description                                                                                                                                                                 | Parameter Type              |
| ---------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------- |
| **prompt**             | Main prompt sent to ChatGPT. Max length: 4096 chars.                                                                                                                        | Required                    |
| **web\_search**        | Enables ChatGPT’s built-in Web Search mode.                                                                                                                                 | Optional (default: false)   |
| **country**            | Target geographic region for contextual responses.                                                                                                                          | Optional                    |
| **engine**             | The chatbot engine to use. Currently only "chatgpt" is supported.                                                                                                           | Optional (default: chatgpt) |
| **follow\_up\_prompt** | A second message sent immediately after the first response.                                                                                                                 | Optional                    |
| **raw\_response**      | returns the raw output from the LLM session (including metadata and intermediate events)                                                                                    | Optional (default: false)   |
| **throttling**         | Controls automated throttling behavior. Enabled by default to help maintain a high success rate during heavy traffic or platform-side limitations. Set to false to opt out. | Optional (default: true)    |

***

### **Example Usage**

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST https://llm-scraper.netnut.io/search \
  -H "Content-Type: application/json" \
  -U "username:password" \
  -d '{
    "prompt": "Give me SEO trends for 2026",
    "engine: "chatgpt",
    "country": "uk",
    "web_search": true,
    "throttling": true
  }'

```

{% endtab %}

{% tab title="Python" %}

```python
import requests
from base64 import b64encode

headers = {
    "Authorization": "Basic " + b64encode(b"username:password").decode(),
    "Content-Type": "application/json"
}

body = {
    "prompt": "Give me SEO trends for 2026",
    "country": "us",
    "web_search": True
}

response = requests.post("https://llm-scraper.netnut.io/search", headers=headers, json=body)
print(response.json())

```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
const username = 'your_username';
const password = 'your_password';
const auth = Buffer.from(`${username}:${password}`).toString('base64');

const headers = {
  'Authorization': `Basic ${auth}`,
  'Content-Type': 'application/json'
};

const body = {
  prompt: 'Give me SEO trends for 2026',
  country: 'us',
  web_search: true
};

fetch('https://llm-scraper.netnut.io/search', {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error.message));
```

{% endtab %}
{% endtabs %}

***

### **Response Format**

The ChatGPT Scraper always returns **structured JSON**.\
No HTML is returned.

#### **Example JSON Response**

```json
{
  "timestamp": "2025-12-23T19:46:50.921Z",
  "traceID": "a6bc1d2e-1230-4b65-bde0-ab10c19e5345",
  "request_duration": 18.18,
  "process_duration": 18.18,
  "llm_model": "gpt-5.5",

  "response": {
    "prompt": "what are the leading SEO tips in 2025",

    "text_markdown": "Here are the **leading SEO tips for 2025**:\n\n### 1. High-quality, intent-focused content\n### 2. AI-aware optimization\n### 3. Strong UX and technical SEO\n\nIf you want tips tailored to your industry, let me know.",

    "text": "The leading SEO tips for 2025 include focusing on user intent, leveraging AI responsibly, improving user experience, and maintaining strong technical SEO foundations.",

    "model_search_queries": [
      "leading SEO tips in 2025",
      "top SEO best practices 2025"
    ],

    "widgets": [],

    "citations_found": true,
    "citations": [
      {
        "id": 1,
        "title": "SEO Trends for 2025",
        "url": "https://example.com/seo-trends-2025",
        "section": "citations"
      },
      {
        "id": 2,
        "title": "Future of Search Optimization",
        "url": "https://example.com/future-seo",
        "section": "more"
      }
    ]
  },

  "raw_response": [
    "data: {\"type\":\"server_metadata\",\"metadata\":{\"model_slug\":\"gpt-5.2\"}}",
    "event: delta",
    "data: {...}"
  ]
}


```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://help.netnut.io/netnut-documentation/netnut-scraper-apis/llm-scraper/chatgpt.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.