# Trustpilot Reviews Scraper + AI Analysis (`lizzyyy2/trustpilot-reviews-scraper-ai`) Actor Scrape Trustpilot business profiles and reviews, then optionally enrich them with AI sentiment, themes, complaints, praises and fake-review detection. - **URL**: https://apify.com/lizzyyy2/trustpilot-reviews-scraper-ai.md - **Developed by:** [Lizzy](https://apify.com/lizzyyy2) (community) - **Categories:** AI, Lead generation, E-commerce - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing from $1.00 / 1,000 review scrapeds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. 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. Actors are written with capital "A". ## 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. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Trustpilot Reviews Scraper + AI Analysis Scrape any company's **Trustpilot profile and reviews** — TrustScore, star average, review count, categories, the full review list with author, country, dates, verification status and the brand's replies. Then, optionally, run an **AI layer** that turns those raw reviews into **reputation summaries, recurring complaints & praises, per-review sentiment, fake-review flags and ready-to-post reply drafts**. No Trustpilot API key, no quota, no login. Most Trustpilot scrapers stop at "here's the company and its reviews." This one adds the layer that actually saves you hours: an **AI enrichment pass** built for reputation managers, agencies and analysts. --- ### What it does - 🔎 **Find companies** by keyword search (e.g. `web hosting`, `vpn`, `car insurance`) or scrape **specific companies** by Trustpilot URL or bare domain. - ⭐ **Company profile**: name, domain, TrustScore, star average, total reviews, categories, website, verified/claimed status, country. - 💬 **Full review list**: title, text, star rating, author name + country + review count, published & experienced dates, verification, likes and the **company's reply**. - 🎛️ **Filters**: sort by recency or relevance, filter by language and by star rating. - 🤖 **Optional AI insights** (billed only when you enable them): - **Company insights** — reputation summary, top complaints, top praises, overall sentiment. - **Review analysis** — per-review sentiment, theme tags and a one-line summary. - **Fake-review detection** — a suspicion score, a likely-fake flag and reasons. - **Response suggestions** — a professional reply draft for recent negative reviews. Built for reliability: rotates proxies, retries on rate limits and anti-bot responses, paginates the review list, and degrades gracefully when a company has no public profile. --- ### Who it's for - **Reputation & brand managers** — track what customers complain about and praise, and draft replies in seconds. - **Agencies & consultants** — pull a competitor's review themes and sentiment for a pitch or audit. - **Market & product researchers** — build sentiment-tagged datasets across a whole category. - **Trust & safety / fraud teams** — surface reviews that look incentivised or fake. --- ### Input | Field | Description | |---|---| | **Company URLs / domains** | Trustpilot review URLs or bare domains (e.g. `amazon.com`). | | **Search terms** | Keywords to discover companies on Trustpilot. | | **Max companies (total)** | Hard cap across all sources. | | **Max companies per search term** | Cap per keyword. | | **Scrape reviews** + **Max reviews per company** | Fetch the review list (up to 2000). | | **Review sort / language / star ratings** | Order and filter the reviews. | | **Enable AI insights** | Master switch, then pick the AI features you want. | | **AI output language** | Language for AI text. | | **Proxy configuration** | Apify proxy recommended (Trustpilot is behind a WAF). | #### Example input ```json { "companyUrls": ["amazon.com", "https://www.trustpilot.com/review/booking.com"], "searchTerms": ["web hosting"], "maxCompanies": 10, "includeReviews": true, "maxReviewsPerCompany": 100, "reviewSort": "recency", "aiEnrichment": true, "aiCompanyInsights": true, "aiReviewAnalysis": true } ```` *** ### Output Each record is one company with its reviews and (optional) AI fields: ```json { "recordType": "company", "companyName": "Example Hosting", "domain": "examplehosting.com", "trustScore": 4.3, "starsAverage": 4.3, "reviewsCount": 12840, "categories": ["Web Hosting Company"], "websiteUrl": "https://examplehosting.com", "trustpilotUrl": "https://www.trustpilot.com/review/examplehosting.com", "reviewsFetched": 100, "reviews": [ { "id": "abc123", "title": "Fast and reliable", "text": "Migrated my sites with zero downtime...", "stars": 5, "publishedDate": "2026-05-20T09:12:00Z", "consumerName": "Jane D.", "consumerCountry": "US", "isVerified": true, "companyReply": { "message": "Thanks Jane!", "publishedDate": "2026-05-21T08:00:00Z" }, "aiSentiment": "positive", "aiThemes": ["uptime", "migration", "support"], "aiSummary": "Praises smooth migration and reliability." } ], "aiReputationSummary": "Customers consistently praise uptime and support...", "aiTopComplaints": ["slow ticket response on weekends", "renewal pricing"], "aiTopPraises": ["uptime", "easy migration", "friendly support"], "aiOverallSentiment": "positive" } ``` *** ### How it works (and why it's reliable) - Reads each company's **public Trustpilot review page** and parses the structured data the page already ships with — so fields stay accurate. - **Paginates** the review list to fetch the back catalogue, not just the first page. - Rotates proxies and **retries on rate limits / anti-bot** responses. - The AI pass uses a **token-capped** model call per insight, so cost stays predictable. ### Notes - AI features are **off by default** and billed per insight, so a plain scrape stays cheap. - Star average, TrustScore and review counts are taken directly from the public profile. - This actor scrapes **publicly available** review data. Respect Trustpilot's terms and applicable laws when using it. AI-generated summaries and fake-review flags are heuristic aids, not definitive judgements. # Actor input Schema ## `companyUrls` (type: `array`): Trustpilot review URLs (e.g. https://www.trustpilot.com/review/amazon.com) or bare company domains (e.g. amazon.com). Both work. ## `searchTerms` (type: `array`): Keywords to find companies on Trustpilot (e.g. "web hosting", "car insurance"). Each term returns the matching businesses. ## `maxCompanies` (type: `integer`): Hard cap on how many companies to scrape across all URLs and search terms. ## `maxCompaniesPerSearch` (type: `integer`): How many companies to take from each search term. ## `includeReviews` (type: `boolean`): Fetch the review list for each company. Turn off for a company-profile-only scrape. ## `maxReviewsPerCompany` (type: `integer`): Newest/most-relevant reviews per company. Trustpilot serves 20 reviews per page. ## `reviewSort` (type: `string`): How to order reviews before taking the cap. ## `reviewLanguage` (type: `string`): Language of reviews to fetch. "all" returns every language. ## `starRatings` (type: `array`): Only keep reviews with these star ratings. Leave empty for all ratings. ## `aiEnrichment` (type: `boolean`): Master switch for the AI features below. AI is billed per insight (pay-per-event), so a plain scrape stays cheap. ## `aiCompanyInsights` (type: `boolean`): A reputation summary, the top recurring complaints and the top praises for each company, mined from its reviews. ## `aiReviewAnalysis` (type: `boolean`): Per-review sentiment, theme tags and a one-line summary for recent reviews. ## `aiFakeReviewDetection` (type: `boolean`): Flags reviews that look fake/incentivised with a suspicion score and reasons. ## `aiResponseSuggestions` (type: `boolean`): Drafts a professional reply a brand could post to recent negative reviews. ## `aiLanguage` (type: `string`): Language for the AI-generated text (summaries, suggestions, etc.). ## `proxyConfiguration` (type: `object`): Proxy used for all requests. Trustpilot is behind a WAF; the default Apify proxy is recommended. ## Actor input object example ```json { "companyUrls": [ "https://www.trustpilot.com/review/amazon.com", "booking.com" ], "searchTerms": [ "web hosting", "vpn" ], "maxCompanies": 10, "maxCompaniesPerSearch": 10, "includeReviews": true, "maxReviewsPerCompany": 100, "reviewSort": "recency", "reviewLanguage": "all", "starRatings": [], "aiEnrichment": false, "aiCompanyInsights": false, "aiReviewAnalysis": false, "aiFakeReviewDetection": false, "aiResponseSuggestions": false, "aiLanguage": "English", "proxyConfiguration": { "useApifyProxy": true } } ``` # Actor output Schema ## `companies` (type: `string`): Company records (with reviews and optional AI insights) in the default dataset. # 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 '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "companyUrls": [ "amazon.com" ], "proxyConfiguration": { "useApifyProxy": true } }; // Run the Actor and wait for it to finish const run = await client.actor("lizzyyy2/trustpilot-reviews-scraper-ai").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 '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "companyUrls": ["amazon.com"], "proxyConfiguration": { "useApifyProxy": True }, } # Run the Actor and wait for it to finish run = client.actor("lizzyyy2/trustpilot-reviews-scraper-ai").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "companyUrls": [ "amazon.com" ], "proxyConfiguration": { "useApifyProxy": true } }' | apify call lizzyyy2/trustpilot-reviews-scraper-ai --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=lizzyyy2/trustpilot-reviews-scraper-ai", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Trustpilot Reviews Scraper + AI Analysis", "description": "Scrape Trustpilot business profiles and reviews, then optionally enrich them with AI sentiment, themes, complaints, praises and fake-review detection.", "version": "0.1", "x-build-id": "WuC6px5JNXgsYMpHL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lizzyyy2~trustpilot-reviews-scraper-ai/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lizzyyy2-trustpilot-reviews-scraper-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lizzyyy2~trustpilot-reviews-scraper-ai/runs": { "post": { "operationId": "runs-sync-lizzyyy2-trustpilot-reviews-scraper-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lizzyyy2~trustpilot-reviews-scraper-ai/run-sync": { "post": { "operationId": "run-sync-lizzyyy2-trustpilot-reviews-scraper-ai", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "companyUrls": { "title": "Company URLs / domains", "type": "array", "description": "Trustpilot review URLs (e.g. https://www.trustpilot.com/review/amazon.com) or bare company domains (e.g. amazon.com). Both work.", "items": { "type": "string" } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Keywords to find companies on Trustpilot (e.g. \"web hosting\", \"car insurance\"). Each term returns the matching businesses.", "items": { "type": "string" } }, "maxCompanies": { "title": "Max companies (total)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Hard cap on how many companies to scrape across all URLs and search terms.", "default": 10 }, "maxCompaniesPerSearch": { "title": "Max companies per search term", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many companies to take from each search term.", "default": 10 }, "includeReviews": { "title": "Scrape reviews", "type": "boolean", "description": "Fetch the review list for each company. Turn off for a company-profile-only scrape.", "default": true }, "maxReviewsPerCompany": { "title": "Max reviews per company", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Newest/most-relevant reviews per company. Trustpilot serves 20 reviews per page.", "default": 100 }, "reviewSort": { "title": "Review sort order", "enum": [ "recency", "relevance" ], "type": "string", "description": "How to order reviews before taking the cap.", "default": "recency" }, "reviewLanguage": { "title": "Review language", "enum": [ "all", "en", "de", "fr", "es", "it", "nl", "da", "sv", "no", "fi", "pt" ], "type": "string", "description": "Language of reviews to fetch. \"all\" returns every language.", "default": "all" }, "starRatings": { "title": "Star ratings filter", "type": "array", "description": "Only keep reviews with these star ratings. Leave empty for all ratings.", "items": { "type": "string", "enum": [ "1", "2", "3", "4", "5" ], "enumTitles": [ "1 star", "2 stars", "3 stars", "4 stars", "5 stars" ] }, "default": [] }, "aiEnrichment": { "title": "Enable AI insights", "type": "boolean", "description": "Master switch for the AI features below. AI is billed per insight (pay-per-event), so a plain scrape stays cheap.", "default": false }, "aiCompanyInsights": { "title": "AI company insights", "type": "boolean", "description": "A reputation summary, the top recurring complaints and the top praises for each company, mined from its reviews.", "default": false }, "aiReviewAnalysis": { "title": "AI review analysis", "type": "boolean", "description": "Per-review sentiment, theme tags and a one-line summary for recent reviews.", "default": false }, "aiFakeReviewDetection": { "title": "AI fake-review detection", "type": "boolean", "description": "Flags reviews that look fake/incentivised with a suspicion score and reasons.", "default": false }, "aiResponseSuggestions": { "title": "AI response suggestions", "type": "boolean", "description": "Drafts a professional reply a brand could post to recent negative reviews.", "default": false }, "aiLanguage": { "title": "AI output language", "type": "string", "description": "Language for the AI-generated text (summaries, suggestions, etc.).", "default": "English" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used for all requests. Trustpilot is behind a WAF; the default Apify proxy is recommended.", "default": { "useApifyProxy": true } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```