# ChatGPT Scraper — Answers, Citations & Sources (`scrape.badger/chatgpt-scraper`) Actor

Ask ChatGPT any prompt at scale and get the answer, its markdown, every citation and the source domains behind it as structured JSON. Built for answer-engine optimisation, AI search monitoring and research.

- **URL**: https://apify.com/scrape.badger/chatgpt-scraper.md
- **Developed by:** [ScrapeBadger](https://apify.com/scrape.badger) (community)
- **Categories:** AI, SEO tools
- **Stats:** 2 total users, 1 monthly users, 85.7% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $6.40 / 1,000 premium calls

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

### What does ChatGPT Scraper do?

**ChatGPT Scraper** extracts structured data from [ChatGPT](https://chatgpt.com) and delivers it as clean JSON — no proxies, browsers or anti-bot handling on your side. It is a practical **ChatGPT API** alternative for teams who need ChatGPT data on a schedule rather than a one-off export.

It covers 2 different ChatGPT surfaces behind a single **Mode** dropdown, so one Actor replaces a rack of single-purpose scrapers.

### Why scrape ChatGPT?

- **Every surface in one place** — pick a mode, fill two fields, run.
- **Anti-bot handled upstream** — residential proxy rotation, TLS and browser fingerprinting, and CAPTCHA solving happen inside the ScrapeBadger API.
- **Pay per call, not per row** — a page of results costs the same as one lookup, so bulk work stays cheap.
- **Runs on the Apify platform** — scheduling, monitoring, webhooks, the [API](https://docs.apify.com/api/v2), and integrations with Make, Zapier, Google Sheets, Slack and Airtable all work out of the box.
- **Partial results are kept** — a transient upstream failure ends the run cleanly instead of discarding what you already paid for.

### What data can ChatGPT Scraper extract?

Every record is pushed to the dataset as its own row. The most useful fields are below; the full record carries considerably more.

| Field | Type | Description |
| --- | --- | --- |
| `prompt` | string | The prompt that was sent |
| `answer` | string | The full answer text returned by the model |
| `citation_count` | number | How many sources the answer cited |
| `web_search_triggered` | boolean | Web search triggered |
| `model` | string | Model that produced the answer |
| `latency_ms` | number | How long the upstream call took |

### ChatGPT scraping modes

Pick one **Mode**; the input form marks the fields it needs.

| Mode | What it returns | Charged as |
| --- | --- | --- |
| **Ask** | One ChatGPT answer with citations, source domains and search results. | `premium-call` |
| **List Models** | Models currently reachable, per country. | `basic-call` |

### How to scrape ChatGPT

1. Click **Try for free** and sign in to Apify.
2. Open **Settings → Environment variables** and add `SCRAPEBADGER_API_KEY` with your key from [scrapebadger.com](https://scrapebadger.com), ticking **Secret**.
3. Choose a **Mode** from the dropdown.
4. Fill in the fields that mode needs — the description on each field says which modes use it.
5. Set **Max items** to cap the run.
6. Press **Start** and watch the dataset fill up.
7. Export as JSON, CSV, Excel or XML, or pull it from the **API** tab.

### How much will it cost to scrape ChatGPT?

This Actor is **pay per event**: one event per API call, whatever that call returns. Fetching a page of 100 records costs the same as fetching one record, so larger pages are cheaper per row.

| Event | Price per event | What triggers it |
| --- | --- | --- |
| `basic-call` | $0.0010 | A cheap call — autocomplete, reference data, single lookups. |
| `premium-call` | $0.0080 | A premium call — an LLM answer or brand-visibility measurement. |

Apify also charges its standard **$0.001 actor start fee** per run. ScrapeBadger credits are consumed on your own account on top of this.

### Input

See the **Input** tab for every option with inline documentation. A minimal run looks like this:

```json
{
  "mode": "Ask",
  "prompt": "What are the best web scraping APIs in 2026?",
  "country": "US",
  "max_items": 100
}
```

**Max items** caps the run; the Actor pages until it reaches that number or ChatGPT runs out of results.

### Output

You can download the dataset in various formats such as JSON, HTML, CSV, or Excel, or read it straight from the Apify API. Each record is one row:

```json
{
  "prompt": "<prompt>",
  "answer": "<answer>",
  "citation_count": 1234,
  "web_search_triggered": true,
  "model": "<model>",
  "latency_ms": 1234
}
```

### What can you do with ChatGPT data?

A few things teams actually build with this Actor.

#### Measure how ChatGPT describes your category

Ask the questions your buyers ask and record the answers over time. When the answer changes, something in ChatGPT's retrieval changed — usually a source page that now ranks differently. That is the earliest signal you get.

#### Audit which sources ChatGPT actually cites

Every answer comes back with its citations and source domains. Aggregating those across a few hundred prompts tells you which publishers ChatGPT trusts in your category — and therefore where a placement is worth paying for.

#### Build an answer-engine content strategy

If ChatGPT keeps citing comparison pages and never your product pages, that is a content brief. Scrape the answers, cluster the cited URLs by page type, and write what the model is already looking for.

#### Generate evaluation sets for your own model

The answers, citations and source domains make a clean reference set for benchmarking an internal RAG system against what a frontier model with live web access produces.

### Tips for faster, cheaper runs

- Raise the page-size field (`count`, `limit`, `per_page` — whichever the mode exposes) before raising **Max items**. Fewer, bigger calls cost less.
- Use the cheap reference and autocomplete modes to resolve IDs before spending on the expensive detail modes.
- Schedule incremental runs with a low **Max items** rather than one huge sweep; you get fresher data and a smaller bill.
- Chain Actors with webhooks to push new rows straight into your warehouse.

### Requirements

This Actor calls the ScrapeBadger API on your behalf, so it needs your key:

1. Get one at [scrapebadger.com](https://scrapebadger.com) — there is a free tier.
2. In **Settings → Environment variables**, add `SCRAPEBADGER_API_KEY` with your `sb_live_…` key and tick **Secret**.

Credits are consumed on your ScrapeBadger account in addition to the Apify event price.

### Frequently asked questions

#### Is it legal to scrape ChatGPT?

Scraping publicly available data from ChatGPT is generally legal, and this Actor only ever reads pages a logged-out visitor could see. What you then do with the data is what matters — read the disclaimer below before collecting anything that could be personal data.

#### Do I need my own proxies?

No. Proxy rotation, browser fingerprinting and anti-bot handling all happen upstream in the ScrapeBadger API, so there is nothing to configure here.

#### Do I need a ScrapeBadger account?

Yes. The Actor calls the ScrapeBadger API on your behalf, so it needs your API key in the `SCRAPEBADGER_API_KEY` environment variable. There is a free tier at [scrapebadger.com](https://scrapebadger.com) — see Requirements below.

#### How many results can I get in one run?

Set **Max items** to whatever you need. The Actor keeps paging until it hits that number or ChatGPT runs out of results, and stops cleanly either way.

#### How much does one run cost?

Events start at $0.0010 and are charged once per API call, not per row — so a page of 100 results costs the same as a single lookup. Apify adds its standard $0.001 actor start fee per run.

#### What happens if the run fails halfway through?

Whatever was already scraped stays in the dataset. The run ends with a status message explaining where it stopped instead of throwing your results away.

#### Can I run this on a schedule or from my own code?

Yes. Use the **Schedules** tab for recurring runs, or the **API** tab to start runs and read the dataset from your own application.

#### Does this use the official API?

No — and that is the point. It reads the answer the public web interface gives a normal visitor, which is what your customers actually see. API answers differ from web answers because the web product runs its own retrieval and grounding.

#### Will the same prompt give the same answer twice?

No. These models are non-deterministic and their retrieval changes constantly. That is why the useful pattern is to run the same prompt on a schedule and track the trend, rather than reading a single answer as fact.

### Is scraping ChatGPT reliable?

Anti-bot interstitials are a fact of life on ChatGPT. A blocked call is retried four times with exponential backoff against fresh exits, and if a run dies partway it keeps everything already scraped rather than throwing the dataset away. Upstream availability is monitored continuously.

### Your feedback and support

Found a bug, missing a field, or need a mode that is not here? Open a ticket on the **Issues** tab, or email <support@scrapebadger.com>. The **API** tab has everything you need to run this Actor programmatically.

### Disclaimer

Our Actors are ethical and do not extract any private user data, such as email addresses, gender, or location. They only extract what the user has chosen to share publicly. We therefore believe that our Actors, when used for ethical purposes by Apify users, are safe. However, you should be aware that your results could contain personal data. Personal data is protected by the GDPR in the European Union and by other regulations around the world. You should not scrape personal data unless you have a legitimate reason to do so. If you're unsure whether your reason is legitimate, consult your lawyers.

# Actor input Schema

## `mode` (type: `string`):

Which ChatGPT call to run. Each mode uses a different subset of the fields below — the run tells you if a required one is missing.

## `prompt` (type: `string`):

The prompt to send. Maximum 4096 characters. <b>Required for:</b> Ask.

## `country` (type: `string`):

ISO-3166 alpha-2 egress country. Defaults to "US".

## `web_search` (type: `string`):

Whether ChatGPT should browse — "auto", "force", or "off". Defaults to "auto". <b>Used by:</b> Ask.

## `max_items` (type: `integer`):

Stop after this many records. The actor keeps paging until it hits this number or the site runs out of results. Each page is one charged event.

## Actor input object example

```json
{
  "mode": "Ask",
  "prompt": "What are the best web scraping APIs in 2026?",
  "country": "US",
  "web_search": "auto",
  "max_items": 100
}
```

# Actor output Schema

## `dataset` (type: `string`):

No description

# 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 = {
    "prompt": "What are the best web scraping APIs in 2026?",
    "country": "US"
};

// Run the Actor and wait for it to finish
const run = await client.actor("scrape.badger/chatgpt-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 = {
    "prompt": "What are the best web scraping APIs in 2026?",
    "country": "US",
}

# Run the Actor and wait for it to finish
run = client.actor("scrape.badger/chatgpt-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 '{
  "prompt": "What are the best web scraping APIs in 2026?",
  "country": "US"
}' |
apify call scrape.badger/chatgpt-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,scrape.badger/chatgpt-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/GA0NxIaAZTk2BaqJQ/builds/5FTHXMjCnDHNakFVz/openapi.json