# Google Autocomplete Scraper: Keywords, Questions, YouTube (`clearpull/google-autocomplete-scraper`) Actor

Google Autocomplete keyword suggestions for any country and language, from web search, YouTube, Shopping, Images or News. Expand keywords with A-Z, numbers, questions, prepositions and comparisons in 7 languages, with Google's relevance score. Long-tail ideas for SEO and ads. Duplicates are free.

- **URL**: https://apify.com/clearpull/google-autocomplete-scraper.md
- **Developed by:** [Clearpull](https://apify.com/clearpull) (community)
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $0.10 / 1,000 keyword suggestions

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?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Google Autocomplete Scraper: Keywords, Questions, YouTube

Get the keyword suggestions Google shows as people type, for any country and language. Turn one seed keyword into hundreds of long-tail keywords and real questions people ask: add A to Z, numbers, question words, prepositions and comparisons, and get each suggestion with Google's own relevance score. Works for Google web search, YouTube, Google Shopping, Google Images and Google News. Export to CSV, Excel or JSON, or call it through the API.

You only pay for new keywords. Duplicates and your own seed keywords are never charged.

### What you get

For each seed keyword and country:

- **Up to 15 suggestions per lookup**, in Google's order, with Google's relevance score.
- **Keyword expansion:** each expansion types more variations of your keyword into Google, the way keyword tools do:

| Expansion | What is typed | Extra lookups | Typical new keywords |
|---|---|---|---|
| A to Z | coffee maker a ... coffee maker z | 26 | 330–380 |
| 0 to 9 | coffee maker 0 ... coffee maker 9 | 10 | 75–145 |
| Questions | how / what / why / where / when / who / which / can / is / are / does / should / will coffee maker | 13 | 80–190 |
| Prepositions | coffee maker for / with / without / to / near / in / from / is / can | 9 | 50–100 |
| Comparisons | coffee maker vs / versus / or / and / like | 5 | 30–60 |
| Custom modifiers | your own words, such as "2026" or "best {keyword} for" | 1 each | |

The numbers are from real runs with English keywords in the US. With every expansion on, one keyword gives about 780 unique suggestions.

- **Questions and prepositions in your language:** English, German, French, Spanish, Portuguese, Italian and Dutch each have their own words (for example "wie", "warum" and "für" in German). Other languages use the English words.
- **Five Google search boxes:** web search, YouTube, Shopping, Images and News each suggest different keywords. YouTube suggestions are what people search for on YouTube; Shopping suggestions lean towards products and brands.
- **Any country and language:** suggestions differ by country, so `coffee maker` gives "coffee maker argos" in the UK and "coffee maker walmart" in the US. Look up several countries in one run.
- **No duplicates:** each suggestion appears once per country across the whole run, even when several of your keywords lead to it. Or choose **Per keyword** to get each keyword's complete list.
- **Compact output for AI agents:** one row per keyword with a plain list of suggestions.

### Who uses it

- **SEO and content teams:** long-tail keyword research, blog and FAQ ideas from real questions, content gaps.
- **YouTube creators:** video ideas and titles from what people type into YouTube.
- **Google Ads and e-commerce:** product and brand keywords from Google Shopping, negative keyword ideas, competitor comparisons ("vs").
- **International SEO:** the same keywords in several countries and languages, side by side.
- **AI agents and automations:** a quick, cheap list of what people search for around a topic.

### How to use it

1. Enter one or more keywords, one per line.
2. Choose the countries (for example `US`, `GB`, `DE`) and the language (`en`, `de`, `pt-BR`, `ja` ...).
3. Pick the Google service: web search, YouTube, Shopping, Images or News.
4. Turn on the expansions you want under **Keyword expansion**.
5. Run it, then download the keywords as CSV, Excel or JSON, or read them through the API.

Example input:

```json
{
  "keywords": ["coffee maker", "running shoes"],
  "countries": ["US", "GB"],
  "language": "en",
  "service": "web",
  "expandAlphabet": true,
  "expandQuestions": true,
  "expandPrepositions": true
}
```

### Output example

With **Output format** set to Full, you get one row per new suggestion:

```json
{
  "type": "suggestion",
  "seed": "coffee maker",
  "suggestion": "coffee maker and espresso machine",
  "position": 2,
  "relevance": 600,
  "expansion": "alphabet",
  "modifier": "a",
  "query": "coffee maker a",
  "country": "US",
  "language": "en",
  "service": "web",
  "scrapedAt": "2026-11-13T22:33:16.912Z"
}
```

- `position`: where Google listed the suggestion for that lookup, from 1 to 15.
- `relevance`: Google's own score for the suggestion; higher is stronger.
- `expansion` and `modifier`: what found it (`seed` is your keyword on its own).
- `query`: the exact text typed into Google.

With **Output format** set to Compact, you get one row per keyword and country:

```json
{
  "type": "seed",
  "status": "ok",
  "seed": "kaffeemaschine",
  "country": "DE",
  "language": "de",
  "service": "web",
  "suggestionCount": 591,
  "suggestions": ["kaffeemaschine mit mahlwerk", "kaffeemaschine mit thermoskanne", "wie kaffeemaschine entkalken", "..."],
  "lookups": 45,
  "failedLookups": 0,
  "expansions": ["seed", "alphabet", "questions", "prepositions"],
  "scrapedAt": "2026-11-13T22:40:01.204Z"
}
```

A keyword with nothing new also gets a `seed` row in either format, with `status` set to `no-suggestions`, `no-new-suggestions` or `failed` and a `note`. These rows are free.

### Use it from Python or JavaScript

Install the Apify client (`pip install apify-client` or `npm install apify-client`) and use your Apify API token.

Python:

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("clearpull/google-autocomplete-scraper").call(run_input={
    "keywords": ["coffee maker"],
    "countries": ["US"],
    "expandQuestions": True,
})
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item["suggestion"], item["relevance"])
```

JavaScript:

```javascript
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('clearpull/google-autocomplete-scraper').call({
    keywords: ['coffee maker'],
    countries: ['US'],
    expandQuestions: true,
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.map((i) => i.suggestion));
```

To send the keywords to Google Sheets, Make, Zapier, n8n or a webhook without code, use the Actor's **Integrations** tab. To refresh them every week, use **Schedules**.

### Use it from AI agents (MCP)

Give Claude, ChatGPT, Cursor or any MCP client live Google keyword suggestions through Apify's MCP server:

```json
{
  "mcpServers": {
    "google-autocomplete": { "url": "https://mcp.apify.com?tools=clearpull/google-autocomplete-scraper" }
  }
}
```

Set **Output format** to **Compact** for agents: each keyword comes back as one short list instead of hundreds of rows.

### Which of these keywords are growing?

Autocomplete tells you what people search for, not how much or whether interest is rising. Run the keywords you like through the [Google Trends Scraper](https://apify.com/clearpull/google-trends-scraper) to get their interest over time, trend direction and the regions where they're most popular, on one shared scale for up to 100 keywords.

### Pricing

You pay per new keyword suggestion: **$0.20 per 1,000**, less on higher Apify plans, plus Apify's tiny fee per run start. For example:

- one keyword with no expansion (15 suggestions): about $0.003;
- one keyword with every expansion (about 780 suggestions): about $0.16;
- 100 keywords with questions only (about 15,000 suggestions): about $3.

What's free:

- **Duplicates:** a suggestion already found in the run, and your own seed keywords.
- **Keywords with nothing new:** listed with a `no-suggestions` or `no-new-suggestions` status.
- **Failed lookups.**

**Spending cap:** set a maximum cost per run in the run options. The Actor stops cleanly when it reaches it, and never charges more than you allowed.

### Limits

- Up to 1,000 keywords, 25 countries and 50 custom modifiers per run, and up to 100,000 lookups in all.
- About 3 lookups a second, so about 12,000 lookups an hour. A run longer than an hour needs a longer timeout in the run options.
- Google returns up to 15 suggestions per lookup with this method; Google's own search box shows 10.
- Search volumes and competition aren't included: Google Autocomplete doesn't give them.

### FAQ

**Why are my results a bit different from what I see in my browser?**
Google personalises suggestions for signed-in users and uses your location for local ones. This Actor asks as a signed-out visitor in the country you choose, so you get the general suggestions for that country.

**How do I get local suggestions, such as city names?**
Google takes those from the IP address's location, not from the country setting. The default datacenter proxy has its own location. For local suggestions, choose residential proxies in the same country under **Proxy configuration**.

**What happens if Google limits requests?**
The Actor sends at most one request a second per IP address. If Google still asks it to slow down, it pauses for 15 seconds, then 45, then 90, and slows down. If Google keeps limiting after that, the run stops with what it has found so far and lists the rest in `ERRORS`. It never tries to get around a limit.

**Is there personal data in the results?**
No. Suggestions are search phrases that Google shows to everyone who types the same text.

**Why does Google suggest odd things for some keywords?**
Google always tries to complete what was typed, so a typo or a made-up word can bring back unrelated suggestions. They're returned as Google gave them.

# Actor input Schema

## `keywords` (type: `array`):

Seed keywords, one per line. Each one is typed into Google's search box the way a person would, and you get what Google suggests. Up to 1,000 per run.

## `countries` (type: `array`):

Two-letter country codes such as US, GB or DE. Suggestions differ by country; each keyword is looked up once per country. Up to 25.

## `language` (type: `string`):

The search language, for example en, de, es, pt-BR or ja. Question and preposition expansion has its own words for en, de, fr, es, pt, it and nl, and uses English words for other languages.

## `service` (type: `string`):

Which Google search box to ask. YouTube, Shopping, Images and News each suggest different keywords from web search.

## `expandAlphabet` (type: `boolean`):

Also look up the keyword followed by each letter: "coffee maker a" to "coffee maker z". 26 more lookups per keyword, usually 330 to 380 more suggestions.

## `expandNumbers` (type: `boolean`):

Also look up the keyword followed by each digit: "coffee maker 0" to "coffee maker 9". Good for models, sizes and years. 10 more lookups per keyword, usually 75 to 145 more suggestions.

## `expandQuestions` (type: `boolean`):

Also look up question words before the keyword: how, what, why, where, when, who, which, can, is, are, does, should and will (or the same words in your language). Great for FAQ and blog ideas.

## `expandPrepositions` (type: `boolean`):

Also look up the keyword followed by for, with, without, to, near, in, from, is and can (or the same words in your language).

## `expandComparisons` (type: `boolean`):

Also look up the keyword followed by vs, versus, or, and and like, to find the alternatives people compare it with.

## `customModifiers` (type: `array`):

Optional words of your own, one per line. Each is typed after the keyword ("2026" gives "coffee maker 2026"), or put {keyword} where the keyword goes ("best {keyword} for" gives "best coffee maker for"). Up to 50.

## `deduplicate` (type: `string`):

Across the run: each suggestion appears once per country, even if several of your keywords lead to it, and your own keywords are never returned. Per keyword: each keyword gets its complete list, so a suggestion can appear under more than one keyword.

## `outputFormat` (type: `string`):

Full gives one row per suggestion, with its position, Google's relevance score and the expansion that found it. Compact gives one row per keyword and country with a plain list of suggestions: small enough for AI agents.

## `proxyConfiguration` (type: `object`):

Apify's datacenter proxy works well and is the default. Google also uses the IP address's location for local suggestions (city names), so for local results pick residential proxies in the same country.

## `saveRawResponses` (type: `boolean`):

For troubleshooting: also store up to 300 of Google's raw answers in the key-value store, under RAW_RESPONSES.

## Actor input object example

```json
{
  "keywords": [
    "coffee maker",
    "running shoes"
  ],
  "countries": [
    "US"
  ],
  "language": "en",
  "service": "web",
  "expandAlphabet": false,
  "expandNumbers": false,
  "expandQuestions": false,
  "expandPrepositions": false,
  "expandComparisons": false,
  "deduplicate": "run",
  "outputFormat": "full",
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "saveRawResponses": false
}
```

# Actor output Schema

## `suggestions` (type: `string`):

One row per new keyword suggestion, with the seed keyword, position, relevance score and the expansion that found it.

## `keywords` (type: `string`):

One row per seed keyword and country: the compact list for AI agents, and keywords with no new suggestions.

# 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 = {
    "keywords": [
        "coffee maker",
        "running shoes"
    ],
    "countries": [
        "US"
    ],
    "language": "en",
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("clearpull/google-autocomplete-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 = {
    "keywords": [
        "coffee maker",
        "running shoes",
    ],
    "countries": ["US"],
    "language": "en",
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("clearpull/google-autocomplete-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 '{
  "keywords": [
    "coffee maker",
    "running shoes"
  ],
  "countries": [
    "US"
  ],
  "language": "en",
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call clearpull/google-autocomplete-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,clearpull/google-autocomplete-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/XVlf4Cqq80H0WkZrt/builds/ce4KohZjJIfgqSLqp/openapi.json
