Google Maps Photos Scraper

Google Maps

Operated by Sourcelane✓ verified

A scraper that extracts photos from Google Maps business listings and produces one record per photo containing high-resolution image URLs and contextual place metadata. It crawls Google Maps photo galleries (owner and user-uploaded images), preserves Google’s photo category labels, upgrades image URLs to higher resolutions where available (targeting 1920×1080), and attaches per-photo position and total-photo counts along with place identifiers, name, address, category, rating, review counts and map URL. The connector accepts search queries for business types and locations or individual place URLs/IDs, runs without requiring authentication, and outputs per-photo records suitable for visual audits, image sourcing, and large-scale content research.

Verified Sep 28, 12:10 AM

$0.0005

per photo

Up to 100 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Property photography sourcing — pull every existing photo of a location before a shoot to avoid duplicates
Real estate & vacation rental research — review a property's full photo history and guest-submitted images
Competitor visual audits — see how competitors present storefronts, menus, and interiors
Restaurant & hospitality marketing — build mood boards and social content from venue photos
Travel blogging & content research — gather reference images for destinations and venues at scale

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"google-maps-photos-scraper","params":{"searchQueries":["coffee shops in Portland Oregon"],"maxPlacesPerQuery":5},"maxResults":10}'

Request params

Field	Type	Required	Description
`searchQueries`	array	optional	Businesses to search on Google Maps, one query per line — e.g. "coffee shops in Portland Oregon", "hotels in Soho London".
`placeUrls`	array	optional	Alternatively (or additionally) scrape photos for specific businesses — Google Maps place URLs, maps.app.goo.gl short links, ?cid= links, Place IDs (ChIJ…) or hex IDs (0x…:0x…).
`maxPlacesPerQuery`	integer	optional	Maximum number of businesses to process per search query (Google Maps returns at most ~120 per query). 0 = everything Google returns. Capped at 100 per call.
`maxPhotosPerPlace`	integer	optional	Maximum number of photos to save per business. 0 = as many as Google Maps returns for that place (the connector still hard-caps fetching at 300 photos per place to avoid runaway runs).
`language`	string	optional	Language code for results, e.g. en, de, fr, es, pt-BR.
`country`	string	optional	Two-letter country code that biases search results, e.g. us, gb, de, au.
`latitude`	number	optional	Optional. Bias search results toward this latitude (used with Longitude and Zoom).
`longitude`	number	optional	Optional. Bias search results toward this longitude (used with Latitude and Zoom).
`zoom`	integer	optional	Optional. Map zoom level (3-21) used with Latitude/Longitude to bias search results — higher is more local.

Each result contains

Field	Type	Description
`placeId`	string	Place Id
`googlePlaceId`	string	Google Place Id
`placeName`	string	Place Name
`placeAddress`	string	Place Address
`placeCategory`	string	Place Category
`placeRating`	number	Place Rating
`placeReviewCount`	integer	Place Review Count
`placeUrl`	string	Place Url
`searchQuery`	string	Search Query
`photoUrl`	string	Photo Url
`photoCategory`	null	Photo Category
`photoIndex`	integer	Photo Index
`totalPhotos`	integer	—
`scrapedAt`	string	—

Use Google Maps Photos Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “List 40 dentists in Austin TX with phone, website and rating above 4.5.”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"google-maps-photos-scraper","params":{"searchQueries":["coffee shops in Portland Oregon"],"maxPlacesPerQuery":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "google-maps-photos-scraper",
        "params": {"searchQueries":["coffee shops in Portland Oregon"],"maxPlacesPerQuery":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…