Track competitor Trustpilot reviews weekly in Google Sheets with n8n

Reading competitors’ Trustpilot pages by hand each week is slow, and copying reviews into a sheet loses the history of their TrustScore.

arcadium/trustpilot-reviews remembers which reviews it already delivered under a state key, so a weekly run returns only the new ones and charges only for those. One free company row per competitor carries the TrustScore and review count for a weekly snapshot.

Cost of this example on the Apify Free plan: 300 × $0.00052 = $0.156 ($0.081 on the Apify Gold plan and higher), plus $0.005 per GB of memory when the run starts.

What you need

• An Apify account and API token.
• n8n (cloud or self-hosted) with Apify’s official node @apify/n8n-nodes-apify, and a Google Sheets credential in n8n.
• The website domains of the competitors you track, for example bestbuy.com.

Step 1: Run it in the Apify Store (no code)

1. Open arcadium/trustpilot-reviews on the Apify Store and sign in (a free Apify account works).
2. Enter the competitor domains (or their Trustpilot review page links) in Companies.
3. Set Max reviews per company to 100.
4. Turn on Only new reviews and set State key to a stable name such as competitors. Keep it the same on every run.
5. Optional: set a maximum cost per run in the run options as a hard cap.
6. Click Start. Rows appear in the Output tab; export them as JSON, CSV or Excel.

The same input as JSON (paste it in the JSON tab of the input form):

{
  "companies": [
    "bestbuy.com",
    "walmart.com",
    "target.com"
  ],
  "maxReviewsPerCompany": 100,
  "onlyNewReviews": true,
  "stateKey": "competitors",
  "includeCompanyInfo": true
}

Step 2: Call it over the Apify API

One HTTP call runs the actor and returns its rows. It suits runs up to about five minutes; for longer runs start the run asynchronously and read the dataset when it finishes.

curl -X POST "https://api.apify.com/v2/acts/arcadium~trustpilot-reviews/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"companies":["bestbuy.com","walmart.com","target.com"],"maxReviewsPerCompany":100,"onlyNewReviews":true,"stateKey":"competitors","includeCompanyInfo":true}'

Step 3: Run it from Python

With apify-client 3.x, call() returns a Run object: read the dataset id as run.default_dataset_id (older examples use run["defaultDatasetId"], which no longer works).

# pip install "apify-client>=3"
import os

from apify_client import ApifyClient

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("arcadium/trustpilot-reviews").call(run_input={
    "companies": ["bestbuy.com", "walmart.com", "target.com"],
    "maxReviewsPerCompany": 100,
    "onlyNewReviews": True,
    "stateKey": "competitors",
})
rows = list(client.dataset(run.default_dataset_id).iterate_items())  # apify-client 3.x Run object
for c in (r for r in rows if r.get("rowType") == "company"):
    print(c["name"], "TrustScore", c.get("trustScore"), "reviews", c.get("reviewCount"))
new = [r for r in rows if r.get("rowType") == "review"]
print(len(new), "new reviews")
for r in new[:5]:
    print(r["productName"], r["date"], r["ratingOverall"], (r.get("title") or "")[:80])

Step 4: Run it from JavaScript

// npm install apify-client
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('arcadium/trustpilot-reviews').call({
  "companies": [
    "bestbuy.com",
    "walmart.com",
    "target.com"
  ],
  "maxReviewsPerCompany": 100,
  "onlyNewReviews": true,
  "stateKey": "competitors",
  "includeCompanyInfo": true
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Step 5: Ask an AI assistant (MCP)

Apify’s hosted MCP server turns the actor into one tool. Add it to Claude, Cursor, VS Code or any MCP client:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?tools=arcadium/trustpilot-reviews",
      "headers": {
        "Authorization": "Bearer <APIFY_TOKEN>"
      }
    }
  }
}

Then ask, for example:

Use arcadium/trustpilot-reviews to get the 50 newest Trustpilot reviews of bestbuy.com and walmart.com, then compare the most common complaints in 1- and 2-star reviews.

More clients and the local setup on the MCP page.

Set it up in n8n

The workflow: a Schedule trigger (Monday 06:00), the Apify node with the operation Run actor and get dataset and the input above, then two Code nodes that split review rows from company rows, and two Google Sheets nodes that append them to a Reviews tab and a TrustScores tab. Set a maximum total charge for the run (maxTotalChargeUsd, for example $1) as a hard cost cap. Run it once by hand, check both tabs, then activate it.

Ready-made workflow: Weekly Trustpilot reviews of competitors to Google Sheets (import the file in n8n, Workflows, Import from File).

Without n8n: Google Sheets only

Schedule the input above as an Apify task (Console, Saved tasks, Schedule weekly), then load its last successful run into a sheet with Apps Script and a weekly time-driven trigger.

// Extensions > Apps Script. Project Settings > Script properties > APIFY_TOKEN.
function importNewReviews() {
  const token = PropertiesService.getScriptProperties().getProperty('APIFY_TOKEN');
  const url = 'https://api.apify.com/v2/acts/arcadium~trustpilot-reviews/runs/last/dataset/items?status=SUCCEEDED&clean=true';
  const rows = JSON.parse(UrlFetchApp.fetch(url, { headers: { Authorization: 'Bearer ' + token } }).getContentText());
  const reviews = rows.filter((r) => r.rowType === 'review');
  const keys = ['productName', 'date', 'ratingOverall', 'title', 'text', 'vendorResponse', 'language', 'reviewUrl'];
  if (reviews.length) SpreadsheetApp.getActiveSheet().getRange(SpreadsheetApp.getActiveSheet().getLastRow() + 1, 1, reviews.length, keys.length)
    .setValues(reviews.map((r) => keys.map((k) => r[k] ?? '')));
}

Ready-made workflow: Weekly Trustpilot reviews of competitors to Google Sheets (import the file in n8n, Workflows, Import from File).

Output fields

Every row has a rowType; filter on it first. Failed inputs come back as free rows with a code and message. The fields this tutorial uses, from the actor’s dataset schema:

All fields: Trustpilot Reviews Scraper guide.

Cost per run

Pay per event: you pay for the rows delivered, at the actor’s live Apify price on 2026-11-02. Error, coverage and summary rows are free.

Cost of this example on the Apify Free plan: 300 × $0.00052 = $0.156 ($0.081 on the Apify Gold plan and higher), plus $0.005 per GB of memory when the run starts. Higher Apify plans pay less per row. The Store page always has the current price.

Limitations

• The state key is what makes the weekly run return only new reviews. A new key starts over and delivers (and charges) everything again.
• The first run is the expensive one; later runs cost only the reviews published since the previous run.
• Trustpilot shows an anonymous visitor 10 pages per filter combination; reading further would need a login, which this actor never does. With splitFilters the actor reaches more reviews through other combinations, not all of them for very large profiles: the coverage row then says stopReason: "cap".
• With several languages or splitFilters, rows are not in one date order; sort on date if you need it.
• Category listings stop at 10,000 companies per category and country (Trustpilot's own limit, coverage stopReason: "cap"); list sub-categories to reach more. Trustpilot's TrustScore filter is not applied.
• Public data only. No login, no personal data, no contact details.

Links

• Trustpilot Reviews Scraper: fields, price table and sample output
• How to use Trustpilot Reviews Scraper: every input field, n8n, LangChain
• arcadium/trustpilot-reviews on the Apify Store
• All tutorials