Gemini Scraper | Answers, Citations & Brand Tracking
Pricing
from $2.00 / 1,000 prompt checked, 1 or 2 captures
Gemini Scraper | Answers, Citations & Brand Tracking
Send prompts to Google Gemini and get the full answer, every cited source (duplicate links merged) and the model that answered. Ask each prompt up to 5 times for citation rates, track your domains and brands, and see what changed since your last run.
Pricing
from $2.00 / 1,000 prompt checked, 1 or 2 captures
Rating
0.0
(0)
Developer
Alexis Morain
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
1
Monthly active users
4 days ago
Last modified
Features
Share
What does Gemini Scraper do?
Gemini Scraper sends your prompts to Google Gemini and returns what it answers: the full answer, every source it cites, and the model that answered. You give it prompts like best crm for startups. For each one you get a citation rate per domain and a mention rate and rank for your brands, measured over 1, 3 or 5 answers to the same prompt.
Use it to see whether Gemini recommends your brand and cites your site, which sites it trusts in your market, and how that moves from week to week. It works as a Gemini API for SEO, GEO (generative engine optimization) and brand reporting. No Google account, no browser on your side.
It covers Gemini only. For ChatGPT, Google AI Mode, Google AI Overviews or Perplexity, see our other Actors.
Why use Gemini Scraper?
Gemini changes its sources a lot. We asked best crm software for startups three times in a row on November 9, 2026, from the United States. The three answers cited 14 domains in total, and only 2 of them appeared in all three. A single answer would have reported 12 domains as "cited" or "not cited" by luck. This Actor asks each prompt 1, 3 or 5 times and gives every domain and brand a rate: 0.67 means it showed up in 2 answers out of 3.
The second reason is duplicate links. Gemini often links the same page several times, each time with a different #:~:text= highlight at the end of the URL. In one of our test answers, 16 links pointed to only 8 pages. Counted raw, a page that Gemini quoted three times looks like three sources. This Actor strips the highlight and counts each page once, so the source list and the positions mean something.
What you get on top:
- Tracked domains: citation rate and best position for your site and your competitors. A tracked domain also counts its subdomains.
- Tracked brands: how often each brand name appears in the answer, and its rank (first brand named, second, and so on).
- Model name: which Gemini model answered (for example
3.6 Flashor3.5 Flash-Lite), so you can tell when Google switches. - Compare mode: domains and brands gained or lost since the previous run, with old and new rates.
- 214 countries and 95 languages.
- Scheduling, API access, webhooks and integrations (Make, Zapier, n8n, Google Sheets) from the Apify platform.
What data can Gemini Scraper extract?
One result per prompt:
| Field | Type | Description |
|---|---|---|
prompt | string | The prompt as you wrote it |
model | string | Gemini model that answered |
status | string | answered or failed |
capturesSucceeded | integer | Answers received. Every rate is divided by this number |
answerText | string | Full answer in Markdown (the longest of the captures) |
citedDomains | array | Each cited domain with its captures, rate and best position |
sources | array | Each cited page, counted once: URL, title, rate, best position |
brandMentions | array | Your brands found in the answer, with rate and best rank |
trackedDomains | array | Your domains: citation rate and best position |
trackedBrands | array | Your brands: mention rate and best rank |
changes | object | Compare mode: gained and lost domains and brands, tracked rates before and after |
How to scrape Gemini
- Open the Actor and type your prompts, one per line.
- Pick the country and language, for example
usanden, oresandes. - Keep 1 capture for a snapshot, or pick 3 or 5 to get rates you can compare between runs.
- Add your domain and competitor domains in Domains to track, and brand names in Brands to track.
- Switch on Compare with previous run if you plan to run it on a schedule.
- Press Start, then download the results as JSON, CSV or Excel, or read them through the API.
Answers come back in batches, not instantly: the prompts are queued and Gemini answers them in the background. In our tests a run of 200 prompts with 1 capture finished in under 5 minutes.
How much does it cost to scrape Gemini?
You pay per prompt answered, plus a start fee of $0.001 per run:
| Captures per prompt | Free plan | Bronze | Silver | Gold and above |
|---|---|---|---|---|
| 1 (snapshot) | $0.003 | $0.003 | $0.0025 | $0.002 |
| 3 (rates) | $0.009 | $0.009 | $0.0075 | $0.006 |
| 5 (most reliable) | $0.015 | $0.015 | $0.0125 | $0.010 |
1,000 prompts with 1 capture cost $3 on the Free plan and $2 on Gold. Platform usage is included.
A prompt is charged only when at least one answer came back. If some captures fail, the prompt is charged at the level it reached: 3 asked and 2 received is charged as 1 capture. A prompt with no answer comes back with status: failed and is not charged. The run stops before it would go over the maximum cost you set.
Free Apify plan: up to 0.15 USD of DataForSEO data per day; paid plans unlimited.
Input
See the Input tab for every option. The only required field is the list of prompts, up to 1,000 per run and 2,000 characters each.
{"prompts": ["best crm for startups", "best email marketing tool for ecommerce"],"countryCode": "us","languageCode": "en","capturesPerPrompt": "3","trackDomains": ["hubspot.com", "mailchimp.com"],"trackBrands": ["HubSpot", "Mailchimp"],"compareWithPreviousRun": true,"historyKey": "crm-weekly"}
Output
You can download the dataset in various formats such as JSON, HTML, CSV, or Excel. Example from a real run, shortened:
{"prompt": "best email marketing tool for remote teams","engine": "gemini","model": "3.5 Flash-Lite","countryCode": "us","languageCode": "en","status": "answered","capturesRequested": 1,"capturesSucceeded": 1,"answerText": "For remote teams, the best email marketing tool depends on whether your priority is collaborative drafting, powerful automation, or multi-channel...","citedDomains": [{"domain": "thedigitalprojectmanager.com", "captures": 1, "rate": 1.0, "bestPosition": 1},{"domain": "pcmag.com", "captures": 1, "rate": 1.0, "bestPosition": 2},{"domain": "gartner.com", "captures": 1, "rate": 1.0, "bestPosition": 3}],"sources": [{"domain": "thedigitalprojectmanager.com", "url": "https://thedigitalprojectmanager.com/tools/email-collaboration-software/", "title": "10 Best Email Collaboration Software Reviewed In 2026", "captures": 1, "rate": 1.0, "bestPosition": 1}],"trackedDomains": [{"domain": "hubspot.com", "citedCaptures": 0, "citationRate": 0.0, "bestPosition": null}],"trackedBrands": [{"brand": "HubSpot", "mentionedCaptures": 0, "mentionRate": 0.0, "bestRank": null}],"changes": null}
changes is null on the first run of a prompt: that run becomes the baseline for the next one.
Tips
- Use 3 or 5 captures for monitoring. Gemini rotates its sources, so 1 capture is only a snapshot.
- Give each client or project its own History name, so compare mode keeps their histories apart.
- Brand names are matched as whole words, case ignored. Add the spellings people use (
Zoho CRMandZoho).
FAQ, limits and support
Which Gemini does it ask?
The Gemini that Google serves to the public for that country and language. The model field tells you which one answered. On our 200-prompt test run, answers came from 3.6 Flash and 3.5 Flash-Lite.
Why does an answer have no sources?
Gemini sometimes answers from general knowledge without citing anything (2 answers out of 200 in our test run). The answer is still returned and counted.
Is it legal?
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.
Something is wrong or missing?
Open an issue in the Issues tab. To call the Actor from your own code, see the API tab.
Guide and use cases
Use cases for outbound and automation, the output fields, pricing and common questions are on the Gemini Scraper page of my site. The AI search visibility family page puts it side by side with the other scrapers of the same family.