ChatGPT Search Scraper

ChatGPT answers with web search as rows: full answer text and markdown, every cited source with its domain, and shopping product cards with prices and merchants. For SEO and GEO teams, marketers, and researchers who track what ChatGPT says, which sites it cites, and which products it recommends.

• Price: $5.00 per 1,000 answers. No subscription; you pay only for answers saved. Failed inputs are free. Try it on Apify's free plan (up to 5 answers per run).
• Export: JSON, CSV, Excel, Google Sheets, or the API. Works with Make, Zapier, n8n, and AI agents (MCP).

Every run tells you plainly what worked and what did not: no silent empty runs.

What you can do with it

• GEO and AI search tracking: run the questions your customers ask and see which domains ChatGPT cites (citedDomains, sources).
• Product recommendations: for shopping questions, products lists the cards ChatGPT shows, with price, merchant, badge ("Best overall"), and offers.
• Content research: collect full answers (answerText, answerMarkdown) for a list of topics and compare them over time on a schedule.
• Local answers: pick Country to ask as a user in one of 13 countries; answers, sources, and prices are localized.

What you get

Field	What it is	Example
prompt	The prompt sent to ChatGPT.	best running shoes for flat feet under 150 dollars
type	answer, or error when the prompt could not be answered.	answer
engine	Engine ID.	chatgpt
engineName	Engine display name.	ChatGPT
country	Country the prompt was asked from. ChatGPT localizes answers to it.	United States
answerText	ChatGPT's full answer as plain text.	If you have flat feet and a budget of under $150 , I'd prioritize run…
answerMarkdown	The answer with headings, lists, and links as markdown. Empty when turned off or not provided.	- If you have flat feet and a budget of under $150, I'd prioritize ru…
answerWordCount	Number of words in the answer.	357
sources	Sites the answer cited or linked, in answer order: position, title, url, domain, publisher. Tracking parameters removed.	[{"position": 1, "title": "7 Best Running Shoes Fo…, …]
sourceCount	Number of distinct sources.	12
citedDomains	Distinct domains of the sources, in answer order.	[runrepeat.com, …]
products	Shopping product cards in the answer: title, price, currency, merchant, rating, badge, url, image, and offers. Empty when the answer shows none.	[{"position": 1, "title": "Brooks Men's Adrenaline…, …]
productCount	Number of product cards.	5
model	Model name, when the engine shows it.
checkedAt	When the answer was collected (UTC, ISO 8601).	2026-11-01T06:09:58+00:00

Examples come from a real run. Every row has every field; a value the page did not show is null, never guessed.

One prompt gives one answer row, usually with 8 to 16 sources; shopping questions also had 5 product cards in our tests.

How to use it

1. Click Try for free (or Start) on this page.
2. Enter one prompt per line in the first field. The form is prefilled with a working example.
3. Optional: set Max results and the other options.
4. Click Start. Open the Output tab, or export JSON, CSV, Excel, or HTML.

Example input

{
  "prompts": [
    "best running shoes for flat feet under 150 dollars"
  ]
}

Example output

One real row from a run on 1 November 2026 (long values shortened here):

{
  "prompt": "best running shoes for flat feet under 150 dollars",
  "type": "answer",
  "engine": "chatgpt",
  "engineName": "ChatGPT",
  "country": "United States",
  "answerText": "If you have flat feet and a budget of under $150 , I'd prioritize running shoes with good stability, arch support, a supportive heel, and a comfortable midso…",
  "answerMarkdown": "- If you have flat feet and a budget of under $150, I'd prioritize running shoes with good stability, arch support, a supportive heel, and a comfortable mids…",
  "answerWordCount": 357,
  "sources": [
    {
      "position": 1,
      "title": "7 Best Running Shoes For Flat Feet in 2026",
      "url": "https://runrepeat.com/guides/best-flat-feet-running-shoes",
      "domain": "runrepeat.com",
      "publisher": "RunRepeat"
    },
    {
      "position": 2,
      "title": "The 11 Best Stability Running Shoes of 2026",
      "url": "https://www.outsideonline.com/outdoor-gear/run/best-stability-shoes?scope=anon",
      "domain": "outsideonline.com",
      "publisher": "Outside Online"
    },
    {
      "position": 3,
      "title": "Best Running Shoes for Flat Feet 2026",
      "url": "https://www.michiganfootdoctors.com/best-running-shoes-for-flat-feet/",
      "domain": "michiganfootdoctors.com",
      "publisher": "DPM-Tested"
    },
    "…"
  ],
  "sourceCount": 12,
  "citedDomains": [
    "runrepeat.com",
    "outsideonline.com",
    "michiganfootdoctors.com",
    "…"
  ],
  "products": [
    {
      "position": 1,
      "title": "Brooks Men's Adrenaline GTS 25 Running Shoes",
      "price": 124.98,
      "currency": "USD",
      "priceText": "$124.98",
      "merchant": "DICK’S Sporting Goods",
      "rating": null,
      "badge": "Best overall",
      "url": "https://www.dickssportinggoods.com/p/brooks-mens-adrenaline-gts-25-running-shoes-25bromrunndrnlngtsfbc/25bromrunndrnlngtsfbc?color=Black%2FGrey%2FWhite&enteredSearchTerm=brooks+adreneline+mens+shoes&oppcref=58e24e8f-f414-4948-8a97-f5bc1288e2f2",
      "imageUrl": "https://images.openai.com/static-rsc-1/2u442zDSpeXzbv_bGGGdAz72DPfIW3eamXqXt1tOx2k-nOHW_jnuaPPwMan7jYM8ZQz1isN8JE2QIxaHIqSxYb5uOxEjtLtCpvsjhoA_mz6dEijdPF9bqV_MhjD0PJUOBcFrNRB_1RomwROSRLA8qQ",
      "offers": [
        {
          "merchant": "DICK’S Sporting Goods",
          "price": 124.98,
          "currency": "USD",
          "priceText": "$124.98",
          "availability": "In stock",
          "url": "https://www.dickssportinggoods.com/p/brooks-mens-adrenaline-gts-25-running-shoes-25bromrunndrnlngtsfbc/25bromrunndrnlngtsfbc?color=Black%2FGrey%2FWhite&enteredSearchTerm=brooks+adreneline+mens+shoes&oppcref=58e24e8f-f414-4948-8a97-f5bc1288e2f2"
        }
      ]
    },
    {
      "position": 2,
      "title": "ASICS Men's GT-2000 14 Running Shoes",
      "price": 139.99,
      "currency": "USD",
      "priceText": "$139.99",
      "merchant": "DICK’S Sporting Goods",
      "rating": null,
      "badge": "Best value",
      "url": "https://www.dickssportinggoods.com/p/asics-mens-gt-2000-14-running-shoes-25asimrunngt200014fec/25asimrunngt200014fec?color=Blue+Fade%2FTeal&enteredSearchTerm=asics+womens+gt-2000+14+running+shoes&oppcref=3cc8535f-2bbf-4344-8ac9-e3002a8e3483",
      "imageUrl": "https://images.openai.com/static-rsc-1/ql0hbpkoS7JFjXtZWFE4C8lmAdANzoWRg3dCfYmuizU7m-j9eob8KeCiKfVlPMGaE4EaF9dOT42JQ-al-YMtXhYczYvHRJJlQFthX0Evc0tTLrB-BuIgJSS9fYc5HlFB92AkG9IOfXOE62zkVKokNQ",
      "offers": [
        {
          "merchant": "DICK’S Sporting Goods",
          "price": 139.99,
          "currency": "USD",
          "priceText": "$139.99",
          "availability": "In stock",
          "url": "https://www.dickssportinggoods.com/p/asics-mens-gt-2000-14-running-shoes-25asimrunngt200014fec/25asimrunngt200014fec?color=Blue+Fade%2FTeal&enteredSearchTerm=asics+womens+gt-2000+14+running+shoes&oppcref=3cc8535f-2bbf-4344-8ac9-e3002a8e3483"
        }
      ]
    },
    {
      "position": 3,
      "title": "HOKA Arahi 7",
      "price": 102.97,
      "currency": "USD",
      "priceText": "$102.97",
      "merchant": "DICK’S Sporting Goods",
      "rating": null,
      "badge": null,
      "url": "https://www.dickssportinggoods.com/p/hoka-mens-arahi-7-running-shoes-23fhqmrh7blncdblnmns/23fhqmrh7blncdblnmns",
      "imageUrl": "https://images.openai.com/static-rsc-1/kFD0WfaJcnAET5cVb2UbvGb3CHJ5Qz8PoxpdXrN02OCMeoSZCymKSuxw4aq445oEtmzrYWizsiZneZ1p7_bzxZZjYymffhjUuwICbz5c-3efHdmnVA7ruUbQwloomXiJUE0sRoDUXI0mYFyjaFMbUA",
      "offers": [
        {
          "merchant": "DICK’S Sporting Goods",
          "price": 102.97,
          "currency": "USD",
          "priceText": "$102.97",
          "availability": "In stock",
          "url": "https://www.dickssportinggoods.com/p/hoka-mens-arahi-7-running-shoes-23fhqmrh7blncdblnmns/23fhqmrh7blncdblnmns"
        }
      ]
    },
    "…"
  ],
  "productCount": 5,
  "model": null,
  "checkedAt": "2026-11-01T06:09:58+00:00"
}

Pricing

Pay per result: $5.00 per 1,000 rows, plus $0.001 per run start. No subscription.

Event	When	Price
Actor start	Once per run (per GB of memory; the default 256 MB counts as one)	$0.001
Result row	Each row saved to the dataset	$0.005

Example	Rows	Cost
10 answers	10	$0.001 + $0.05 = $0.051
100 answers	100	$0.001 + $0.50 = $0.501
1,000 answers	1,000	$0.001 + $5.00 = $5.001

• Retries after a bot check or a temporary error cost you nothing. You pay only for rows saved.
• An input that fails after all retries saves one error row so you can see what failed and why. Error rows are free.
• On Apify's free plan a run stops at 5 rows. Any paid Apify plan removes this limit.
• Set Max total charge per run in the run options. The Actor stops cleanly at that limit and keeps every row saved so far.

What you can count on

• Same columns on every row. Missing values are null, so spreadsheets and databases never break.
• No silent failures. An input that fails gets an error row with errorCode and a plain-language errorMessage. The other inputs keep running.
• A clear run summary. The run status says how many results were saved, how many inputs failed, and why. The same numbers are saved as the RUN_SUMMARY record in the run's key-value store, for automations.
• Automatic retries. Bot checks and temporary errors are retried with a fresh request before an input counts as failed.
• Limits respected. Max results and your spending limit stop the run cleanly.

Use it from code, automations, and AI agents

API (returns the rows when the run finishes):

curl -X POST "https://api.apify.com/v2/acts/plumblinedata~chatgpt-search-scraper/run-sync-get-dataset-items?token=YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompts": ["best running shoes for flat feet under 150 dollars"]}'

Python (pip install apify-client):

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")
run = client.actor("plumblinedata/chatgpt-search-scraper").call(run_input={"prompts": ["best running shoes for flat feet under 150 dollars"]})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row)

JavaScript (npm install apify-client):

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_API_TOKEN' });
const run = await client.actor('plumblinedata/chatgpt-search-scraper').call({"prompts": ["best running shoes for flat feet under 150 dollars"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

No-code: connect the Actor in Make, Zapier, n8n, or Google Sheets through Apify's integrations, or add a webhook to get notified when a run finishes.

AI agents (MCP): add https://mcp.apify.com?tools=plumblinedata/chatgpt-search-scraper to Claude, Cursor, or any MCP client. The agent can call this Actor as a tool with the same input as above.

Limitations

• Each answer takes about 25 to 60 seconds; prompts run 8 at a time.
• ChatGPT's answers change from run to run, like in the app. Sources and products reflect that one answer.
• Product cards appear only when ChatGPT shows shopping results; rating is often empty because ChatGPT does not show one.
• Free-plan runs stop after 5 answers.

FAQ

Is this the same as asking in the ChatGPT app? It is ChatGPT with web search, signed out, asked from the country you pick. Signed-in features (memory, custom GPTs) are not used.

I want brand mentions and share of voice, not raw answers. Use AI Visibility Tracker: it asks ChatGPT, Gemini, and Google AI Mode and scores your brand against competitors.

What does an error row mean? It marks an input that failed after retries. errorCode is short (blocked, empty_result, not_available, http_404, or invalid_... for a bad ID or URL) and errorMessage says what to do. Remove error rows with a filter on type.

Can I run it on a schedule? Yes. Create a task with your input in Apify Console, then add a schedule (for example every day at 8:00).

Is it legal to collect this data? The Actor reads public pages that anyone can open without logging in. You are responsible for how you use the data, including copyright, personal data rules such as GDPR, and the site's terms. If you are not sure, ask a lawyer.

How do I scrape ChatGPT answers? Put your questions in Prompts (prompts), one per line. Each answer becomes a row with the full text, markdown, and every cited source.

How to see which websites ChatGPT cites Run your questions in Prompts (prompts). citedDomains and sources list every site the answer used.

How to get ChatGPT product recommendations for a search Ask a shopping question in Prompts (prompts). When ChatGPT shows product cards, products lists them with price and merchant.

Related Actors

• AI Visibility Tracker: See if ChatGPT, Gemini, and Google AI Mode mention and cite your brand.
• Google Search Scraper: Google search results with AI Overview and People Also Ask.

Support

Found a problem or need a field? Open an issue on the Issues tab. Include the run ID and one input that shows the problem. We read every issue.