Google Maps Reviews Scraper + AI Fix List
Pricing
from $3.00 / 1,000 analysed reviews
Google Maps Reviews Scraper + AI Fix List
Scrape Google Maps reviews of any place or search, then get an AI fix list: ranked complaints, trends, quotes and reply drafts. No reviewer personal data.
Pricing
from $3.00 / 1,000 analysed reviews
Rating
0.0
(0)
Developer
Seasons AI
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
20 days ago
Last modified
Features
Share
Google Maps reviews scraper with AI review analysis: give it places or a Maps search, get every review plus a ranked fix list of what customers complain about, with trends, quotes and reply drafts. No reviewer names or profiles are collected.
- Collect Google Maps reviews for any place: a Google Maps link, a place ID or just "Business name, City". Or take the top places of a Maps search ("pizza in Brooklyn") to compare competitors.
- What to fix first: the top complaint themes, each with a concrete action and the evidence behind it, ranked by how many stars they cost you
- Complaint and praise themes: how many reviews mention each one, their average stars, and whether the theme is rising or falling compared with the previous period
- Example quotes, copied word for word from the reviews
- Escalate now: reviews that mention food safety, injury, security, discrimination or legal threats
- Reply drafts (optional): a polite reply to each review that mentions the specific points the customer raised. The Actor never posts anything. You read the drafts and post the ones you want yourself.
Output is one row per review (full text, stars, date, language, themes, sentiment, reply draft) and one summary row per place, plus a Markdown report and CSV files in the key-value store.
Already have reviews? The Actor also reads datasets of Google Maps, TripAdvisor, Booking.com, App Store and Google Play review scrapers, or your own CSV/JSON file (see Or use your own reviews).
How to use it
- Add one or more places in Google Maps places: a link from Google Maps, a place ID (
ChIJ...) or "Business name, City". Or type a Google Maps search such asdentist in Austin, TXand how many of the top places to take. - Choose how many reviews per place (default 50, up to 2,000), which ones (newest, most relevant, lowest or highest rating first) and, optionally, a start date.
- Pick who should get reply drafts, add an optional sign-off, and start the run.
{"places": ["Pod Times Square, New York", "https://www.google.com/maps/place/Katz's+Delicatessen/@40.7222,-73.9873,17z/"],"maxReviewsPerPlace": 200,"reviewsSort": "newest","reviewsSince": "6 months","replyTo": "negative","replySignature": "— The front desk team"}
Compare competitors:
{ "searchQuery": "pizza in Brooklyn", "maxPlaces": 5, "maxReviewsPerPlace": 100, "replyTo": "none" }
Input
| Field | Default | Description |
|---|---|---|
places | – | Google Maps links, place IDs (ChIJ...) or "Business name, City", one per line. Up to 100. |
searchQuery | – | A Google Maps search; the top maxPlaces places are added. |
maxPlaces | 5 | Places taken from the search, 1–50. |
maxReviewsPerPlace | 50 | Reviews collected per place, 1–2,000. Rating-only reviews (no text) are included and free. |
reviewsSort | newest | newest, relevant, lowest or highest: the first N reviews in this order are collected. |
reviewsSince | – | Only reviews from this date on: 2026-01-31 or a period such as 3 months. Reviews are then read newest first. |
language | en | Google language code for place names and categories. Reviews keep the language they were written in. |
proxyConfiguration | Apify Proxy | Datacenter Apify Proxy by default; the Actor connects directly if the proxy isn't available. |
maxReviews | 1000 | Maximum number of reviews with text analysed (and charged) per run, from 1 to 5,000. The newest reviews of each place are taken first. |
periodDays | 30 | Length of the trend window: the last N days are compared with the N days before. The window ends at the newest review of each place. |
themeTaxonomy | – | Theme names from an earlier run (the taxonomy field of a place row). New reviews are grouped into these names, so you can compare runs one to one. |
allowNewThemes | true | With themeTaxonomy: whether new themes may be added. |
businessContext | – | One or two sentences about the business, such as opening hours or a contact email. Used in the analysis and in the replies. |
replyTo | unanswered | none, negative (3 stars or less, no owner reply yet), unanswered (no reply yet) or all. |
replyLanguage | auto | auto replies in the language of each review. Or name a language. |
replySignature | – | Sign-off line added to every reply. |
datasetId, reviewsUrl, items | – | Your own reviews instead of collecting them, see below. When one of these is set, places and searchQuery are ignored (the log says so). |
defaultPlaceName | My business | Place name for rows of your own data that don't have one. |
Output
Real output of the prefill run (30 newest reviews of Pod Times Square, New York: 20 with text, 10 rating-only), trimmed.
Place row (rowType: "place-summary"):
{"rowType": "place-summary","source": "google-maps","placeName": "Pod Times Square","placeId": "ChIJnzd-8lJYwokRoEmCF0KSNQc","placeUrl": "https://www.google.com/maps/search/?api=1&query=Pod%20Times%20Square&query_place_id=ChIJnzd-8lJYwokRoEmCF0KSNQc","placeAddress": "400 W 42nd St, New York, NY 10036","placeCategory": "Hotel","placeRating": 4.1,"placeReviewsCount": 3379,"reviewsAnalyzed": 20,"ratingOnlyReviews": 10,"avgStars": 4.53,"sentiment": { "positive": 15, "neutral": 0, "mixed": 5, "negative": 0 },"summary": "The hotel maintains a strong average star rating, with location, cleanliness, and value being significant strengths. However, room size is the most prominent issue impacting guest experience.","fixFirst": [{ "rank": 1, "theme": "Room Size", "action": "Review room layouts and consider minor furniture adjustments to maximize perceived space.", "why": "5 mentions, 25% of reviews, avg 4.4 stars, with quotes about rooms being small.", "mentions": 5, "avgStars": 4.4, "priorityScore": 4.5, "trend": "insufficient_data" },{ "rank": 2, "theme": "Check-in/Check-out Policy", "action": "Evaluate the feasibility of offering earlier check-in or a secure luggage storage option.", "mentions": 1, "avgStars": 3, "priorityScore": 2 }],"complaints": [{ "theme": "Room Size", "mentions": 5, "sharePct": 25, "avgStars": 4.4, "priorityScore": 4.5,"exampleQuotes": ["The room was a lil small but this is New York so that was expected."] }],"unansweredNegative": 2,"taxonomy": { "issues": ["Room Size", "Check-in/Check-out Policy", "Noise", "Bar Service", "Surrounding Area", "Building Issues"], "praise": ["Location", "Cleanliness", "Value", "Staff Friendliness", "..."] }}
Review row (rowType: "review"):
{"rowType": "review","source": "google-maps","placeName": "Pod Times Square","reviewId": "Ci9DQUlRQUNvZENodHljRjlvT21KT2JrbGpPVVpKYmtkbVdGbzVOVGRMZURkdWRWRRAB","publishedAt": "2026-10-29T02:52:51.017Z","stars": 4,"language": "en","text": "LOUD VENTILATION in rooms. Sometimes the windows work. Great location if you like being Times Square adjacent. Very good service in the lobby.","status": "analyzed","sentiment": "mixed","severity": "medium","issueThemes": ["Noise"],"praiseThemes": ["Service", "Location"],"issues": [{ "label": "loud ventilation", "theme": "Noise", "severity": "medium", "quote": "LOUD VENTILATION in rooms. Sometimes the windows work." }],"needsEscalation": false,"hasOwnerResponse": false,"replyDraft": "Thank you for your review. We appreciate you highlighting our great location and the good service in the lobby. We are sorry to hear about the loud ventilation in your room and will look into this. We hope to welcome you back again soon. The team.","charged": true}
Rating-only reviews get a review row with status: "rating_only" and count in the star stats.
App row (rowType: "app-summary", reportType: "app", trimmed): the same fields as a place row, with product feedback themes.
{"rowType": "app-summary","reportType": "app","source": "app-store","placeName": "Duolingo: Learn Languages","placeId": "570060128","placeCategory": "Education","reviewsAnalyzed": 10,"avgStars": 4,"fixFirst": [{ "rank": 1, "theme": "Missing Features", "action": "Have the product team investigate and document user requests for missing features, prioritizing based on user impact.", "mentions": 1, "avgStars": 1, "trend": "n/a" }],"taxonomy": { "issues": ["Missing Features", "Customer Support", "Pricing", "AI Errors", "Gamification"], "praise": ["Language Variety", "Learning Effectiveness"] }}
The key-value store also holds:
REPORT.md: the full report for all places and appsfix-list.csv: one row per complaint theme and place or app, with rank, mentions, average stars, priority, trend, action and quotesreviews.csv: one row per review, with themes, sentiment and the reply draftOUTPUT: run summary with links to the files
How themes are built. Each review is tagged with short topic labels. Labels from all reviews of a place or app are then grouped into a small, stable set of themes for it: at most 12 complaint themes and 8 praise themes. Priority is the number of mentions × star impact, where each mention scores the stars it lost compared with a 5-star visit, with a minimum of 0.5. When a review has no star rating, the issue's severity is used instead. Trend compares the share of reviews that mention a theme in the last period with the period before. It is shown as n/a when either period has fewer than 3 reviews.
How themes are built. Each review is tagged with short topic labels. Labels from all reviews of a place or app are then grouped into a small, stable set of themes for it: at most 12 complaint themes and 8 praise themes. Priority is the number of mentions × star impact, where each mention scores the stars it lost compared with a 5-star visit, with a minimum of 0.5. When a review has no star rating, the issue's severity is used instead. Trend compares the share of reviews that mention a theme in the last period with the period before. It is shown as n/a when either period has fewer than 3 reviews.
What is collected from Google Maps
| Collected | Not collected |
|---|---|
| Place: name, place ID, address, category, rating, review count, Google Maps link | Reviewer name, profile link, photo, reviewer ID, number of reviews by the reviewer, Local Guide status |
| Review: review ID, stars, full text, language, date, whether the owner replied | Review photos, likes, the text of the owner's reply, review URL, per-aspect ratings (rooms/service/location) |
Other limits compared with a plain reviews scraper: no keyword filter on review text, no machine translation of reviews, and a bare place ID gives no place name (the place is then called "Google Maps place ChIJ…"; use a link or "Business name, City" to get the name). A Google Maps search returns at most about 120 places per query.
Or use your own reviews
Already ran a review scraper? Pick its dataset in Reviews dataset (or pass a public file link in reviewsUrl, or paste a JSON array in items). The source is detected item by item, so you don't need to say which scraper you ran. If the scraper has a "Personal data" or "Scrape reviewer info" option, you can turn it off, because this Actor doesn't use reviewer data.
Supported scrapers
The source is detected item by item, so you don't need to say which scraper you ran.
| Scraper | Report | What is read |
|---|---|---|
| Google Maps Reviews Scraper | place report | text, stars, date, place name and ID, owner reply yes/no |
| Tripadvisor Reviews Scraper | place report | title, text, rating, date, language, place name, ID and address, owner reply yes/no |
| Booking Reviews Scraper | place report | title, liked and disliked text, score (1–10, mapped to 1–5 stars: 1 → 1, 10 → 5), date, language, hotel ID, property reply yes/no. The hotel name is taken from the hotel's Booking.com link. |
| App Store Reviews Scraper | app report | title, text, stars, date, app ID, app version. The app name, category and overall rating are looked up in the public App Store listing. |
| Google Play Reviews Scraper | app report | text, stars, date, language, app ID, app version, developer reply yes/no. The app name is looked up in the public Google Play listing. |
TripAdvisor and Booking.com datasets are mapped from the fields those scrapers publish and have been tested less than Google Maps, App Store and Google Play. If a field comes out empty or wrong, open an issue on the Actor page.
App reports are written for a product team: themes are product feedback (crashes, bugs, login and account, missing features, pricing and subscription, ads, UX, performance, customer support), the fix list suggests product, engineering or support actions, and it names the app versions that get the most 1–3 star reviews. If an app name can't be looked up, the app ID is used as the name.
Exports of the scrapers above work as is. For other files, columns are matched by common names: text/review/content, stars/rating/score (4, 4.2/5, 8/10 and ★★★★ all work), publishedAtDate/date, title/placeName/place (the place name), reviewTitle (the review headline), appId (makes it an app review) and reviewId/id. A file must be downloadable without a login; private Apify dataset links don't work as reviewsUrl, pick the dataset instead.
Privacy
This tool works at business and app level only. It does not collect, use or output reviewer names, usernames, reviewer IDs, avatars, profile links, photos, reviewer locations or the owner's earlier replies. Names found in the review text are replaced: in quotes, excerpts and full texts, staff names are replaced with [staff member] and other names with [name]; emails and phone numbers become [email] / [phone]; themes, the fix list and summaries refer to staff by role ("the cashier", "a staff member"); reply drafts don't name the reviewer or staff ("our team member"). Your business name, address and sign-off are kept as is, even when they contain a first name ("Joe's Pizza"). Name detection is automatic, works best for English reviews and can miss a name, so read quotes and drafts before you share them.
Reply drafts
- Polite and specific, 40–90 words (apps: 30–80 words), written in the review's language unless you choose one.
- Store limits: Google Play developer replies can't be longer than 350 characters, so Google Play drafts are written short, sign-off included. A longer draft is cut at the last full sentence that fits (flag
reply_shortened); if too little would be left, it is dropped, flaggedreply_dropped_too_long, and not charged. App Store drafts stay far below Apple's 5,970-character limit. - App replies ask the user to contact support with their device and app version, and never promise a fix date or a new feature.
- Drafts never promise refunds, discounts, vouchers, free items or other compensation, and never admit liability for health or safety claims. If a draft still mentions compensation, it is dropped, flagged
reply_dropped_compensation, and not charged. - A draft with a leftover placeholder such as
[date]is flaggedhas_placeholder. - The Actor does not post replies. Read every draft before you post it.
Pricing
Pay per event. Collecting the reviews is included in the analysis price. Reviews or reports that fail are free. Rating-only reviews (no text) are collected and counted in the stats for free.
| Event | Price |
|---|---|
| Review collected and analysed (themes, sentiment, severity) | $0.003 |
| Reply draft written | $0.002 |
| Place or app report (taxonomy, ranking, trend, fix list) | $0.02 per place or app |
Examples:
- The prefill run (30 newest reviews of one hotel, 20 with text, replies to all unanswered): 20 × $0.003 + 20 × $0.002 + $0.02 = $0.12.
- 200 reviews of one place with replies to 60 unanswered negative reviews: 200 × $0.003 + 60 × $0.002 + $0.02 = $0.74.
- 5 competitors from a search, 100 reviews each, no replies: 500 × $0.003 + 5 × $0.02 = $1.60 (less when some reviews are rating-only).
Before it starts, the Actor works out the most the run can cost. If that is above the run's maximum cost, it stops without charging and tells you the amount to set.
Limits
- Collection: up to 2,000 reviews per place, 100 places and 10,000 reviews per run. Google answers about 10 reviews per request; the Actor sends at most 2 requests per second, so 1,000 reviews take about 2 minutes.
- Analysis: up to 5,000 reviews with text per run (
maxReviews), from up to 100 places and apps. A dataset is read up to its first 20,000 items. - Each review is analysed up to its first 4,000 characters (title included).
businessContextis capped at 600 characters. - Up to 400 distinct topic labels per place or app go into theme grouping. Rarer labels join the closest theme, or "Other issues" / "Other praise".
- Themes, actions and quotes are AI-generated from the review text. Quotes are checked word for word against the review, and a quote that doesn't match is removed. Small samples (a few reviews per place) give rough themes. Treat the ranking as a guide, not a measurement.
- If Google answers with a CAPTCHA or another bot check, the Actor stops collecting (it never tries to get around it) and analyses the reviews collected so far.
Good to know
- On the free Apify plan the Actor runs a free preview: 1 place and up to 20 reviews, with the full analysis, and nothing is charged. The last row (
rowType: "preview") says so. Upgrade to a paid Apify plan to run the full input. - Reviews come from Google's public review pages, without a login or a browser.