Features

A detailed overview of the ChatGPT Scraper’s advanced capabilities, including Web Search mode, geographic targeting, citation extraction, and follow-up prompts.

The ChatGPT Scraper provides powerful customization options to help you generate more accurate, contextual, and verifiable responses from ChatGPT. These features allow you to tailor how ChatGPT behaves, what type of responses it returns, and how much detail it extracts.

---

Geolocation (country)

Influence ChatGPT’s responses based on a target region by specifying a country parameter. This can affect examples, perspectives, or localized insights within the answer.

Example

{
  "prompt": "Trending products in 2025",
  "country": "ca"
}

Use Cases

• Localized content generation

• Region-specific trend insights

• Country-influenced context within ChatGPT answers

---

Web Search (web_search)

ChatGPT includes a built-in Search mode accessible directly in its UI. When enabled, the scraper activates Web Search before sending your prompt.

This can lead to responses that are:

• more up-to-date

• based on external information

• more likely to include citations

Example

{
  "prompt": "Latest changes in AI regulation",
  "web_search": true
}

Use Cases

• Fresh factual information

• Real-time insight generation

• Content requiring references or external validation

---

Citation Extraction

When ChatGPT displays a Sources panel, the scraper automatically extracts all available citations.

Each citation includes:

• URL

• Title

• Section indicator ("citations" or "more")

• Sequential ID

Example

{
  "id": 1,
  "url": "https://example.com/ai-law",
  "title": "AI Regulation Updates 2025",
  "section": "citations"
}

Use Cases

• SEO research requiring verified sources

• Content enrichment pipelines

• Dataset building with reference links

---

Follow-up Prompts (follow_up_prompt)

Send a second prompt in the same ChatGPT session. The follow-up prompt runs after the first answer is fully generated.

Example

{
  "prompt": "List ranking factors",
  "follow_up_prompt": "Summarize them into three main themes"
}

Use Cases

• Refinement of initial answers

• Multi-step reasoning

• Structuring, summarizing, or analyzing generated content

---

Response Schema Overview

Each session includes:

• traceID for tracking

• timestamps

• request & processing durations

• primary response text

• citations with section classification

• follow-up response (if provided)

Example (condensed)

{
  "response": {
    "text": "...",
    "citations_found": true,
    "citations": [
      {
        "id": 1,
        "url": "https://example.com",
        "title": "SEO Trends",
        "section": "citations"
      }
    ]
  }
}

---

Error Handling

The ChatGPT Scraper includes standardized error responses.

400 — Validation Errors

Returned when:

• Prompt missing

• Invalid parameter

• Prompt > 4096 characters

Example:

{
  "message": "Prompt exceeds 4096 characters. Please shorten your prompt.",
  "error": "Bad Request",
  "statusCode": 400
}

---

401 — Credentials Error

Returned when:

• Username or Password is Incorrect

• No Active Package for the Product

Example:

{
    "message": "Request failed with status code 401"
}

---

500 — Internal Errors

Every Error of a Scraping error will return a 500 error code like so:

{
  "message": "The ChatGPT scraper could not complete the request. Please try again.",
  "error": "Internal Scraper Error",
  "statusCode": 500
}