Gemini Search Scraper: Answers, Sources, Model ($5/1K) avatar

Gemini Search Scraper: Answers, Sources, Model ($5/1K)

Pricing

from $4.00 / 1,000 answers

Go to Apify Store
Gemini Search Scraper: Answers, Sources, Model ($5/1K)

Gemini Search Scraper: Answers, Sources, Model ($5/1K)

$5 per 1,000 answers, failed inputs free. Google Gemini answers as rows: full answer text and markdown, every cited source with its domain, and the model that answered.

Pricing

from $4.00 / 1,000 answers

Rating

0.0

(0)

Developer

Plumbline

Plumbline

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

a day ago

Last modified

Security

Limited permissions

Share

Gemini Search Scraper

Google Gemini answers as rows: full answer text and markdown, every cited source with its domain, and the model that answered. For SEO and GEO teams, marketers, and researchers who track what Gemini says about their topics and which sites it relies on.

  • 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 tracking: see which domains Gemini cites for the questions your customers ask (citedDomains, sources).
  • Answer monitoring: schedule the same prompts and compare answerText and sources over time.
  • Model tracking: model shows which Gemini model answered.
  • Local answers: pick Country to ask as a user in one of 13 countries.

What you get

FieldWhat it isExample
promptThe prompt sent to Gemini.best budget noise cancelling headphones
typeanswer, or error when the prompt could not be answered.answer
engineEngine ID.gemini
engineNameEngine display name.Gemini
countryCountry the prompt was asked from. Gemini localizes answers to it.United States
answerTextGemini's full answer as plain text.When looking for the best budget noise-cancelling headphones, you no …
answerMarkdownThe answer with headings, lists, and links as markdown. Empty when turned off or not provided.When looking for the best budget noise-cancelling headphones, you no …
answerWordCountNumber of words in the answer.407
sourcesSites the answer cited or linked, in answer order: position, title, url, domain, publisher. Tracking parameters removed.[{"position": 1, "title": "Best budget noise cance…, …]
sourceCountNumber of distinct sources.8
citedDomainsDistinct domains of the sources, in answer order.[soundguys.com, …]
modelModel name, when the engine shows it.3.5 Flash-Lite
checkedAtWhen the answer was collected (UTC, ISO 8601).2026-11-01T06:08:32+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, with 7 to 8 sources 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 budget noise cancelling headphones"
]
}

Example output

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

{
"prompt": "best budget noise cancelling headphones",
"type": "answer",
"engine": "gemini",
"engineName": "Gemini",
"country": "United States",
"answerText": "When looking for the best budget noise-cancelling headphones, you no longer have to spend $300+ to get solid active noise cancellation (ANC), great battery l…",
"answerMarkdown": "When looking for the best budget noise-cancelling headphones, you no longer have to spend $300+ to get solid active noise cancellation (ANC), great battery l…",
"answerWordCount": 407,
"sources": [
{
"position": 1,
"title": "Best budget noise canceling headphones under $150 in 2026",
"url": "https://www.soundguys.com/best-budget-noise-cancelling-headphones-7142/",
"domain": "soundguys.com",
"publisher": null
},
{
"position": 2,
"title": "Best Noise Cancelling Over-Ear Headphones under $100 (2026)",
"url": "https://recordingnow.com/blog/best-noise-cancelling-headphones-under-100/",
"domain": "recordingnow.com",
"publisher": null
},
{
"position": 3,
"title": "11 Best Budget Noise Cancelling Headphones in 2026 (<$80)",
"url": "https://headphonesaddict.com/best-budget-noise-cancelling-headphones/",
"domain": "headphonesaddict.com",
"publisher": null
},
"…"
],
"sourceCount": 8,
"citedDomains": [
"soundguys.com",
"recordingnow.com",
"headphonesaddict.com",
"…"
],
"model": "3.5 Flash-Lite",
"checkedAt": "2026-11-01T06:08:32+00:00"
}

Pricing

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

EventWhenPrice
Actor startOnce per run (per GB of memory; the default 256 MB counts as one)$0.001
Result rowEach row saved to the dataset$0.005
ExampleRowsCost
10 answers10$0.001 + $0.05 = $0.051
100 answers100$0.001 + $0.50 = $0.501
1,000 answers1,000$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~gemini-search-scraper/run-sync-get-dataset-items?token=YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"prompts": ["best budget noise cancelling headphones"]}'

Python (pip install apify-client):

from apify_client import ApifyClient
client = ApifyClient("YOUR_API_TOKEN")
run = client.actor("plumblinedata/gemini-search-scraper").call(run_input={"prompts": ["best budget noise cancelling headphones"]})
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/gemini-search-scraper').call({"prompts": ["best budget noise cancelling headphones"]});
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/gemini-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 20 to 65 seconds; prompts run 8 at a time.
  • Gemini's answers change from run to run. Sources reflect that one answer.
  • Gemini does not show shopping product cards here, so there is no products field.
  • Free-plan runs stop after 5 answers.

FAQ

Is this signed-in Gemini? No. It is Gemini signed out, asked from the country you pick, so personal context and extensions are not used.

I want brand mentions and share of voice. Use AI Visibility Tracker: it scores your brand against competitors across ChatGPT, Gemini, and Google AI Mode.

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 Google Gemini answers? Put your questions in Prompts (prompts), one per line. Each answer becomes a row with the full text, markdown, cited sources, and the model that answered.

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

How to compare Gemini answers across countries Run the same Prompts (prompts) once per Country (country) and compare answerText and citedDomains.

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.