Skip to content

Review Aggregator

Try for free

Give a business name and city and get its reviews from Google Maps, Yelp, Trustpilot, Tripadvisor and Facebook in one table, with an optional AI summary of what customers praise and complain about.

⭐ Review Aggregator

Type a business name and city and get its reviews from Google Maps, Yelp, Trustpilot, Tripadvisor and Facebook in one table, all in the same format: site, rating out of 5, date, text, author, owner reply and link. The business is found on each site for you, and its name and address are checked before any review is kept. An optional AI summary tells you the overall sentiment and what customers praise and complain about most, with counts and real quotes, and saves it as a Markdown report.

✨ Why use Review Aggregator?

  • 🔎 No link hunting: give a name and a city. The tool searches Google for the business's page on each site and checks that the name and city match before it reads the reviews. Paste a link yourself when you already have it.
  • 🧾 One format for five sites: every review has the same columns, so you can sort, filter and compare sites in one spreadsheet.
  • ✅ Wrong branches are left out: when a site returns another business or a branch in another city, the next search result is tried, and if none fits its reviews are skipped and the row says why, so a "Roscioli" in New York never mixes with Roscioli in Rome.
  • 🤖 AI summary: overall sentiment, the top 5 praised and top 5 complained-about topics with how many reviews mention them and a quote, overall and for each site.
  • 🔗 Works after other runs: point it at a Google Maps scrape or a lead list and it checks the reviews of every business in it.

🎯 Use cases

  • 📊 Reputation reports for a client or your own business, every month or week.
  • 🥊 Compare competitors: what customers love and hate about the places next to you.
  • 🧲 Lead qualification: find businesses with poor ratings or unanswered complaints and offer help.
  • 🏨 Hotels and restaurants: see what guests say on every site without opening five tabs.
  • 🛠️ Product and service feedback: spot repeated complaints early.

🚀 How to use

  1. Fill in Business name and City (the name, not the website). Add more businesses in More businesses, one per line as Name, City, or pick the results of another run in Dataset ID.
  2. Choose the Sites to read and Max reviews per site (newest first). Use Reviews from and Reviews until to keep a date range.
  3. Leave AI summary on to get the summary row and the Markdown report.
  4. Click Start. Download the table as JSON, CSV, Excel or HTML. The report link is in the summary row (reportUrl).

📥 Input example

{
    "businessName": "Prince Street Pizza",
    "city": "New York",
    "sources": ["google", "yelp", "trustpilot", "tripadvisor", "facebook"],
    "maxReviewsPerSource": 10,
    "aiSummary": true
}

Reviews for every business of a Google Maps run:

{
    "datasetId": "YOUR_DATASET_ID",
    "sources": ["google", "yelp", "tripadvisor"],
    "maxReviewsPerSource": 20,
    "aiSummary": false
}

📤 Output example

A review row:

{
    "type": "review",
    "businessName": "Prince Street Pizza",
    "city": "New York",
    "source": "yelp",
    "rating": 3,
    "recommended": null,
    "date": "2026-11-10T16:57:09.000Z",
    "visitDate": null,
    "text": "Took my wife here to re-visit the pizza place I had before. The pizza here wasn't thin crust just so you know. My wife didn't like the margherita slice though lol.\nThe 4-cheese slice was just alright.  My wife told me they had the option of 40% tip which was high on the payment pad. Be careful. The pizza was already more expensive than other places.",
    "author": "Tung D.",
    "ownerReply": "Thank you",
    "reviewUrl": "https://www.yelp.com/biz/prince-street-pizza-new-york-2?hrid=dZ4tigrU8JFUJaIEI7zUng",
    "businessUrl": "https://www.yelp.com/biz/prince-street-pizza-new-york-2",
    "error": null
}

The summary row (shortened):

{
    "type": "summary",
    "businessName": "Prince Street Pizza",
    "city": "New York",
    "source": "all",
    "rating": 4.6,
    "date": "2026-11-17T06:32:59.900Z",
    "text": "Reviewers overwhelmingly praise Prince Street Pizza's crispy, flavorful Sicilian square slices, especially the Naughty Pie and Spicy Vodka, along with its affordable prices and friendly staff. Common complaints involve long lines, cramped seating, occasional undercooked or burnt orders, and a high default tip prompt or non-cash surcharge.",
    "reviewsAnalyzed": 35,
    "sentiment": "very positive",
    "summary": {
        "sentiment": "very positive",
        "summary": "Reviewers overwhelmingly praise Prince Street Pizza's crispy, flavorful Sicilian square slices, especially the Naughty Pie and Spicy Vodka, along with its affordable prices and friendly staff. Common complaints involve long lines, cramped seating, occasional undercooked or burnt orders, and a high default tip prompt or non-cash surcharge.",
        "praised": [
            {
                "topic": "Crispy crust",
                "count": 13,
                "quote": "The slice was crispy and FULL of flavor."
            },
            {
                "topic": "Sicilian square slices",
                "count": 8,
                "quote": "the square pepperoni pizza, the sauce is out of this world!!!"
            }
        ],
        "complaints": [
            {
                "topic": "Long lines",
                "count": 6,
                "quote": "There is always a line down the block"
            },
            {
                "topic": "Cramped interior",
                "count": 2,
                "quote": "The interior is quite small."
            }
        ]
    },
    "reportUrl": "https://api-staging.scrape.ly/v2/key-value-stores/b2da88ad-718e-4b2b-b653-1b5a914aa6a2/records/report-prince-street-pizza.md",
    "bySource": [
        {
            "source": "Google Maps",
            "part": {
                "sentiment": "positive",
                "summary": "Google Maps reviewers praise the Sicilian slices and call it some of the best American pizza, though one reviewer reports a burnt, expensive order and another feels quality has slipped.",
                "praised": [
                    {
                        "topic": "Sicilian slices",
                        "count": 2,
                        "quote": "Favorite Sicilian slice."
                    }
                ],
                "complaints": [
                    {
                        "topic": "Burnt order",
                        "count": 1,
                        "quote": "it was two burnt pieces thrown in box"
                    }
                ]
            }
        }
    ]
}

A Tripadvisor restaurant review comes with the month of the visit instead of a posting date:

{
    "type": "review",
    "businessName": "Prince Street Pizza",
    "city": "New York",
    "source": "tripadvisor",
    "rating": 5,
    "recommended": null,
    "date": null,
    "visitDate": "2026-03",
    "text": "Absolutely unbelievable\n\nAbsolutely Unbelievable \n\nThe best pizza I have ever had we had three slices, a vodka, a spicy pepperoni and another type of pepperoni. \n\nThe server was an absolute gent such a lovely man. \n\nQuick and efficient and absolutely delicious.",
    "author": "Brudge21",
    "ownerReply": null,
    "reviewUrl": "https://www.tripadvisor.com/ShowUserReviews-g60763-d3322154-r1056100093-Prince_Street_Pizza-New_York_City_New_York.html",
    "businessUrl": "https://www.tripadvisor.com/Restaurant_Review-g60763-d3322154-Reviews-Prince_Street_Pizza-New_York_City_New_York.html",
    "error": null
}

When a site has no page for the business, or its page belongs to another business, you get one row with type source-error and the reason in error. These rows are not charged.

FieldWhat it isWhere it comes from
typereview, summary or source-error
businessName, cityThe business as you entered it (or as named in your dataset)Your input
sourcegoogle, yelp, trustpilot, tripadvisor or facebook
ratingStars out of 5. On the summary row, the average of the saved reviewsThe review site
recommendedFacebook only: true when the reviewer recommends the page, false when not. Facebook has no starsFacebook
dateWhen the review was posted (ISO date). Empty on Tripadvisor restaurant reviews, which show no posting dateThe review site
visitDateTripadvisor only: the month of the visit or stay, as YYYY-MMTripadvisor
textThe review text, with its title first when the site has titlesThe review site
authorThe reviewer's display nameThe review site
ownerReplyThe business's public answer, if any. On Facebook, the page's own comment under the reviewThe review site
reviewUrlLink to the reviewThe review site
businessUrlThe business's page on that siteGoogle search, or your link
sentiment, summary, bySource, reviewsAnalyzed, reportUrlSummary row only: overall sentiment, praised and complained-about topics with counts and quotes (overall and per site), how many reviews were read, and the Markdown report linkAI model
errorWhy a site gave no reviews

⚠️ Good to know

  • Each site reads the newest reviews first. Max reviews per site applies to each site and each business.
  • Date ranges: "Reviews from" makes each site stop at that date. Only Yelp can start at a "Reviews until" date, so with that date set the other sites read further back (up to 5 times Max reviews per site, at least 100) and keep the newest reviews in the range. Those extra reviews are read by the review site scrapers and count toward their charges, so a range far in the past can find fewer reviews than you asked for.
  • Tripadvisor restaurant pages give at most about 10 reviews in our tests; hotel and attraction pages give as many as you ask for.
  • Finding pages takes a search. Big and well-known places are found on most sites. Small businesses are often not on Tripadvisor or Facebook, and Trustpilot mostly lists companies with a website, not restaurants. Facebook pages are the hardest to find by search; paste the page link when you know it. Links you paste apply to the first business.
  • Chains: for a chain like a coffee brand, name the branch the way the sites do (for example "Tim Hortons Yonge Street") or paste its links, so the right branch is read.
  • Facebook pages without reviews: some pages have the reviews tab turned off. You get a source-error row for them.
  • Tripadvisor restaurant reviews have no posting date, only the month of the visit in visitDate (hotel and attraction reviews have both). With a date range set, they are kept or left out by that month: a review is left out when the visit was after "Reviews until"; for "Reviews from" they are kept, since a review is posted after the visit.
  • Owner replies depend on the business. Many places never answer; in our tests replies were on most Google and Tripadvisor hotel reviews, on most reviews of businesses that answer on Yelp, and on about a fifth of Facebook reviews of a large hotel.
  • The AI summary reads up to 400 reviews per business (the newest ones, up to 700 characters each), so each summary is one model request of a bounded size; all reviews are still saved as rows. Topic counts are the model's count over those reviews, so treat them as close estimates.
  • Login links: the report link opens with your Scrape.ly login or API token.
  • The review site scrapers run in your account. The reviews are read by the review site scrapers in the Scrape.ly store, and the Google search that finds each site's page is run by the Google Search scraper; all of them are started in your account, so their own charges are billed next to this Actor's. All of it counts toward the run's spending limit, and the run stops cleanly when the limit is reached. source-error rows and failed summaries are not charged.

❓ FAQ

Which countries work? Any. The Google search uses the country in Search country (us by default). City names in English and in the local language both work, for example Munich and München.

Why was a site left out for my business? The source-error row says why: no page found, the page belongs to another business, or the business is in another city. Paste the right link in that site's link field and run again.

Can I run it every month? Yes. Save your input as a task and schedule it, and use Reviews from with a relative value such as 30 days to get only new reviews.

Can I use another AI model? You can pick one of three small models in Summary model: Claude Haiku 5.5 (default), GPT-4o mini or Gemini 2.5 Flash Lite. If the chosen model gives an unusable answer, the summary is tried once more with the next one.

//From the blog\\

Latest articles

All articles

The internet is full of data.
Start owning yours.

Scrape.ly gives you the infrastructure, the tooling, and the team to extract, process, and operationalize web data at any scale. Setup takes minutes.

No credit card. No setup calls.