Gemini Prompt Search Scraper

🌐 Overview

This Apify Actor allows you to programmatically collect detailed content from Gemini based on a list of search prompts. It simulates a search interaction by providing a prompt, then returns the structured output content, including the generated answer and associated metadata.

🚀 Why choose this actor?

Gemini is an emerging AI-powered search and content generation interface by Google. However, its results are not easily accessible in bulk. This Actor enables users to automate Gemini prompt queries and retrieve structured outputs — ideal for research, monitoring, or building LLM-ready datasets.

NO PROXIES ARE REQUIRED.
FREE USERS RECEIVE ONLY 10 RESULTS.
THE max_results FIELD WILL ROUND UP TO THE NEAREST MULTIPLE OF 10.

🧠 Use Cases

• Build datasets for prompt engineering or LLM fine-tuning
• Analyze Gemini-generated content by region or prompt variation
• Track evolution of AI-generated responses over time
• Academic or commercial NLP research

✨ Key Features

• Simple prompt-based configuration
• Fully structured and enriched output fields
• Easy country targeting
• Real-time scraping with accurate content snapshots
• Zero CAPTCHAs, login, or proxy handling needed

⚙️ How It Works

1. You provide a list of prompts and a country code.
2. The Actor simulates search queries on Gemini.
3. It returns the full generated content, source URL, metadata, and structured fields.
4. All results are stored in the default Apify dataset.

📝 Input Parameters

Field	Type	Description	Required	Example
prompts	array	List of prompts to query on Gemini	✅	["automation"]
country	string	Country code for localized results	✅	"US"

📤 Output (Full Example)

[
  {
    "url": "https://gemini.google.com/app/2ec4bc1a1e78eac6",
    "prompt": "automation",
    "answer_text": "Automation, in its broadest sense, is the use of technology...",
    "links_attached": [],
    "citations": [],
    "country": "US",
    "index": 1,
    "answer_text_markdown": "Automation, in its broadest sense, is the use of technology...",
    "timestamp": "2025-07-29T06:16:32.069Z",
    "input": {
      "url": "https://gemini.google.com/",
      "prompt": "automation",
      "country": "US",
      "index": 1
    }
  }
]

💲 Pricing

Tier	Price	Limits
Free User	$0	Up to 10 results
Pay-as-you-go	$3.5 / 1000 results	Minimum charge applies, auto-rounded

📜 Legal Disclaimer

This Actor is an independent project and is not officially affiliated with or endorsed by Google or Gemini. All trademarks belong to their respective owners. Use of this Actor is subject to Apify’s and Google’s terms of service.

🔄 Update Policy

We continuously monitor changes to the Gemini interface. If the output format or selectors change, updates are prioritized within 72 business hours to maintain functionality.

❓ FAQ

Does this Actor need a proxy or CAPTCHA solution?
No, it accesses public data without login or anti-bot systems.

How many results can I retrieve?
The number is determined by max_results, but it will be rounded up to the nearest multiple of 10.

Can I use this to train language models?
Yes. The structured JSON output is ideal for prompt engineering, LLM pretraining, or fine-tuning pipelines.

What happens if I set max_results to 35?
You’ll receive 40 results, since the system rounds to the next multiple of 10.