We hear almost every day about new advancements in model intelligence and agentic capabilities, like the new Astra model or Fable 5.1, and open source is catching up faster than we thought.
While almost all of them can do powerful research and dive into the web, one thing they can't do well is pull complete data out of platforms like Google Maps, LinkedIn or Instagram.
Take an example: say you run a small web agency and want a list of local businesses that could use your help: every dentist in your city, with their rating, number of reviews, phone number and whether they even have a website. The AI basically has a few core options:
- Use web search, which is based on indexed data (e.g. from the ChatGPT crawler). You get "best dentists in Austin" lists and directory pages, usually the 10 to 20 practices with the biggest marketing budgets. Exactly the ones that don't need you.
- Use agentic web browsing (a Chrome extension like I talked about in a previous post, or computer use). This emulates you clicking through Google Maps one listing at a time. It works, but for a few hundred businesses it is slow and expensive.
With a handful of businesses you can certainly do that by hand. But if you want the whole market, this is a dead end.
What you need instead is a Google Maps scraper: a tool that reads every listing for a search and hands you the data as a table.
Luckily there is a way to do this without writing any code, using a data scraping platform called Apify. If you don't know Apify, check them out here.
In a nutshell, they offer ready-made scrapers for almost the entire web, including an official Google Maps Scraper, and provide them through a single interface, which you can even connect to your AI.
I have already talked about this in many posts in the past, but frankly it was always still too difficult for some folks who are not very tech-savvy to understand the concept and connect Apify to their AI.
But recently Apify decided to go their own way and not just offer a connector (MCP) but provide their own AI, which knows, given a simple or complex question, how to:
- select the scrapers that can help
- configure these scrapers automatically
- run and monitor them
- efficiently sift through the scraped data to answer the question
The interface is as simple as ChatGPT or Claude, with one huge difference: access to almost the entire web.
And if you don't consume too many scrapes, you can even use it entirely for free (if you stay within the $5 monthly free scraping credit) (apify.com).
Let's take the example. Say I run a small web agency and want to find dentists in Austin who could use a better online presence.
Once you have signed up, simply head to https://console.apify.com/ and open the Dashboard.
By default it will do what most other AIs do: it will search the web.
The result is what you would expect: "best dentists" lists and directory sites like Yelp and Healthgrades. Useful if you need a dentist. Useless if you want the full list: you would still be copying names and phone numbers into a sheet by hand, and directories rarely tell you whether a practice has a website at all.
So you ask the same AI to go to the source: scrape Google Maps directly and check the reviews. You can also give it a budget so it never goes over the free tier.
Under the hood it picks the right scrapers from the Apify Store, the official Google Maps Scraper and Google Maps Reviews Scraper, runs them, waits for them to finish, and evaluates the results. One of them, the email extractor, came back empty; that happens, and the AI simply works with what the others found.
And after a few minutes the picture is completely different. Instead of 10 "top" practices, it has all 187 dental practices Google Maps lists for Austin, and it can filter them the way a sales person would: which ones have no website, which ones have a low rating, which ones barely have any reviews. It even scanned the reviews and summarised what patients complain about most, which is a perfect opening line for a sales call.
(Practice names in the screenshot are changed and phone numbers hidden.)
What did it cost? The Google Maps Scraper is priced per place (about $0.004 per place on the free tier, per the Apify Store) and the Reviews Scraper per review, so a run like this stays well inside the $5 of free monthly credit.
Before you call anyone: stick to public business listings, respect local rules on cold calls and emails, and double-check a lead before you pitch it. "No website" on Google Maps sometimes just means the owner never added the link.
This was of course just one example. Swap "dentists in Austin" for "plumbers in Leeds", "restaurants without online ordering in Munich" or "gyms with bad reviews near me"; the technique is the same. The point is: web search gives you the best-marketed businesses; a Google Maps scraper gives you the whole market.
Top comments (0)