# ChatGPT Search Scraper: Answers, Citations, Products (`korado_labs/chatgpt-search-scraper`) Actor

Scrape ChatGPT's web search answers at scale: the full answer text, inline citations with source URLs, product results, and follow-up questions. No login, no API key. Export data, run via API, schedule runs, or integrate with other tools.

- **URL**: https://apify.com/korado\_labs/chatgpt-search-scraper.md
- **Developed by:** [Korado Labs](https://apify.com/korado_labs) (community)
- **Categories:** SEO tools, AI, Automation
- **Stats:** 1 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $150.00 / 1,000 chatgpt search answers

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## ChatGPT Search Scraper

Scrape **ChatGPT Search** at scale: ask ChatGPT any question with web search enabled and get back the **full AI answer**, **cited sources**, **product recommendations with live prices**, and **brand-mention analysis** — as clean, structured JSON.

Built for **GEO / AEO monitoring** (Generative Engine Optimization), SEO research, brand tracking, e-commerce intelligence, and LLM answer auditing.

### What you get for every query

| Field | Description |
|---|---|
| `text` | ChatGPT's full answer as clean plain text |
| `answerMarkdown` | The answer with inline citations resolved to markdown links |
| `queryFanOut` | The internal search queries ChatGPT generated to answer |
| `citations` | Sources cited inline: title, URL, **domain, publish date, snippet** |
| `searchResults` | Every web result ChatGPT consulted, with snippets and dates |
| `sources` | Combined list `{id, title, url, section}` (citations + more) |
| `widgets` | Product cards for shopping queries: **name, price, currency, rating, images, merchants with offer URLs** |
| `brandMentions` | Per tracked brand: mentioned in answer? cited? which URLs? |

### Why this scraper

- **Pay only for answers.** $0.15 per successfully extracted answer. Failed or blocked queries cost **$0** and there is **no Actor start fee**.
- **Richer output.** Citations include snippets, domains, and publish dates. Shopping queries return structured product widgets with merchant offers. The markdown answer keeps clickable citation links.
- **Brand tracking built in.** Pass `checkBrands: ["YourBrand", "competitor.com"]` and every result reports whether ChatGPT mentioned or cited each brand — the core metric of GEO/AEO.
- **Drop-in migration.** The input field (`queries`, one per line) and the core output fields (`query`, `text`, `queryFanOut`, `widgets`, `sources`) match the schema you may already use, so switching takes zero code changes.
- **Reliable.** Talks to ChatGPT's backend directly with a real Chrome network fingerprint (no browser to break), solving the anti-bot challenges the site itself solves. Fresh proxy exit IP per retry, automatic block detection, configurable retries.

### Input

```json
{
  "queries": "best CRM for small business\nbest running shoes under $150",
  "checkBrands": ["HubSpot", "Salesforce"],
  "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"] }
}
```

### Example output item

```json
{
  "query": "best CRM for small business",
  "text": "If you mean CRM software for managing leads...",
  "answerMarkdown": "If you mean CRM software... ([HubSpot](https://www.hubspot.com/products/crm))",
  "queryFanOut": ["best CRM small business 2026 comparison"],
  "citations": [
    {
      "title": "The Best CRM Software of 2026",
      "url": "https://www.pcmag.com/picks/the-best-crm-software",
      "domain": "PCMag",
      "pubDate": 1786974318.0,
      "snippet": "We tested the leading CRM platforms..."
    }
  ],
  "searchResults": [ ... ],
  "sources": [ {"id": 1, "title": "...", "url": "...", "section": "citations"} ],
  "widgets": [],
  "brandMentions": [
    {"brand": "HubSpot", "mentionedInAnswer": true, "cited": true, "citedUrls": ["https://www.hubspot.com/products/crm"]}
  ]
}
```

### Use cases

- **GEO / AEO monitoring** — track how often ChatGPT recommends your brand vs. competitors, and which pages it cites, over time.
- **SEO & content strategy** — see which domains and articles win citations for your target queries, including publish dates and snippets.
- **E-commerce intelligence** — monitor which products, prices, and merchants ChatGPT surfaces for shopping queries.
- **Query fan-out research** — learn what ChatGPT actually searches for, to target those long-tail queries.
- **LLM answer auditing** — archive what ChatGPT tells users about your company, industry, or topic.

### Pricing

**$0.15 per answer.** You are charged only when an answer is successfully extracted. No start fee, no charge for failures, no charge for blocked queries.

### FAQ

**Does it use the official API?** No — it captures what ChatGPT Search actually shows users, including citations, sources, and product widgets that no API returns.

**Which ChatGPT experience is scraped?** The anonymous (logged-out) chatgpt.com search experience, the same one shown to users clicking a ChatGPT search link.

**How fast is it?** A typical query completes in 15–40 seconds, depending on how long ChatGPT streams its answer.

**Is scraping ChatGPT legal?** This actor only accesses publicly available pages without logging in. You are responsible for how you use the data.

# Actor input Schema

## `queries` (type: `string`):

One query per line. Each query is asked to ChatGPT with web search enabled and returns the full answer with cited sources.

## `checkBrands` (type: `array`):

Optional list of brand, product or domain names. For each query the output reports whether the brand is mentioned in ChatGPT's answer and whether it appears in the cited sources.

## `maxRetriesPerQuery` (type: `integer`):

How many attempts per query. Each attempt rotates a fresh proxy exit IP. Failed queries are not charged.

## `requestTimeoutSecs` (type: `integer`):

Maximum seconds to wait for one query attempt (page bootstrap + streamed answer).

## `proxyConfiguration` (type: `object`):

Proxy used to reach ChatGPT. ChatGPT firewalls datacenter IPs, so a proxy is required — residential proxies pass most reliably. Each retry rotates a fresh proxy session (a new exit IP).

## Actor input object example

```json
{
  "queries": "What are the top 5 CRM tools",
  "checkBrands": [],
  "maxRetriesPerQuery": 3,
  "requestTimeoutSecs": 90,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}
```

# Actor output Schema

## `results` (type: `string`):

One dataset item per query: full answer (text + markdown), cited sources with snippets and dates, product widgets, query fan-out, and optional brand-mention analysis. Failed queries appear as {query, error} items and are never charged.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": "What are the top 5 CRM tools",
    "checkBrands": [],
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": [
            "RESIDENTIAL"
        ]
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("korado_labs/chatgpt-search-scraper").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "queries": "What are the top 5 CRM tools",
    "checkBrands": [],
    "proxyConfiguration": {
        "useApifyProxy": True,
        "apifyProxyGroups": ["RESIDENTIAL"],
    },
}

# Run the Actor and wait for it to finish
run = client.actor("korado_labs/chatgpt-search-scraper").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": "What are the top 5 CRM tools",
  "checkBrands": [],
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}' |
apify call korado_labs/chatgpt-search-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,korado_labs/chatgpt-search-scraper"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/bSrSpFvuupOyvBldu/builds/Gr5d4YGKVzYgTSlNf/openapi.json