January 22, 2026

Google Maps to Google Sheets, clean leads ready to use

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Copying business details out of Google Maps looks simple. Then you do it for 40 listings, lose track of what you already captured, and your “prospect list” turns into a messy spreadsheet you don’t trust.

Sales reps feel it when they’re trying to hit daily outreach targets. Marketing teams feel it when they need localized lists for campaigns. And consultants building lead lists for clients end up doing the same repetitive work. This Maps lead automation turns Google Maps results into a clean Google Sheet you can actually use.

This workflow pulls listings, fills key fields, and even enriches missing info so you can sort, segment, and start outreach faster. You’ll see how it works, what you need, and what to watch for.

How This Automation Works

See how this solves the problem:

n8n Workflow Template: Google Maps to Google Sheets, clean leads ready to use

Click to explore

flowchart LR

    subgraph sg0["Trigger - When User Sends Message Flow"]
        direction LR
        n0@{ icon: "mdi:play-circle", form: "rounded", label: "Trigger - When User Sends Me..", pos: "b", h: 48 }
        n1@{ icon: "mdi:robot", form: "rounded", label: "AI Agent - Lead Collection", pos: "b", h: 48 }
        n2@{ icon: "mdi:brain", form: "rounded", label: "GPT-4o - Generate & Process ..", pos: "b", h: 48 }
        n3@{ icon: "mdi:memory", form: "rounded", label: "Memory - Track Recent Context", pos: "b", h: 48 }
        n4@{ icon: "mdi:wrench", form: "rounded", label: "Tool - Scrape Google Maps Bu..", pos: "b", h: 48 }
        n5@{ icon: "mdi:wrench", form: "rounded", label: "Fallback - Enrich with Googl..", pos: "b", h: 48 }
        n6@{ icon: "mdi:wrench", form: "rounded", label: "Tool - Crawl Business Website", pos: "b", h: 48 }
        n3 -.-> n1
        n6 -.-> n1
        n0 --> n1
        n5 -.-> n1
        n2 -.-> n1
        n4 -.-> n1
    end

    subgraph sg1["Trigger - On Subworkflow Start Flow"]
        direction LR
        n7@{ icon: "mdi:play-circle", form: "rounded", label: "Trigger - On Subworkflow Start", pos: "b", h: 48 }
        n8["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Scrape Google Maps (via Apify)"]
        n9@{ icon: "mdi:database", form: "rounded", label: "Save Extracted Data to Googl..", pos: "b", h: 48 }
        n10@{ icon: "mdi:cog", form: "rounded", label: "Aggregate Business Listings", pos: "b", h: 48 }
        n8 --> n9
        n7 --> n8
        n9 --> n10
    end

    subgraph sg2["Flow 3"]
        direction LR
        n11["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Scrape Website Content (via .."]
        n12@{ icon: "mdi:database", form: "rounded", label: "Save Website Data to Google ..", pos: "b", h: 48 }
        n13@{ icon: "mdi:cog", form: "rounded", label: "Aggregate Website Content", pos: "b", h: 48 }
        n12 --> n13
        n11 --> n12
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n0,n7 trigger
    class n1 ai
    class n2 aiModel
    class n4,n5,n6 ai
    class n3 ai
    class n9,n12 database
    class n8,n11 api
    classDef customIcon fill:none,stroke:none
    class n8,n11 customIcon

The Challenge: Turning Google Maps Results Into Usable Leads

Google Maps is great for discovery, but it’s terrible as a lead list. You search “dentists in Austin” (or whatever your niche is), click around, then start copying names, phone numbers, websites, and addresses into a sheet. Half the time the website is missing, emails aren’t obvious, and you end up opening five tabs just to confirm basic details. After an hour, you have a list… sort of. Then you realize you duplicated entries, missed a phone number, or pasted the address into the wrong column. Honestly, it’s draining.

It adds up fast. Here’s where it breaks down in real work.

Manual copy-paste turns a simple search into a multi-hour admin task.
Details are inconsistent across listings, so your spreadsheet columns end up half empty.
Duplicates creep in when multiple people build lists or you rerun the same search later.
Outreach gets delayed because you’re still “cleaning” the list instead of contacting anyone.

The Fix: Extract, Enrich, and Log Leads Automatically

This workflow automates the entire “Google Maps to spreadsheet” routine. You start by sending a request through a chat-style trigger (Telegram-style intake) describing what you want: the business category, location, and any filters you care about. From there, n8n calls a Google Maps scraping service (via HTTP request) to collect business listings and writes them straight into Google Sheets. If important fields are missing, it uses a search enrichment step (SerpAPI) to fill gaps. Then it can crawl each company’s website to capture extra context, and an OpenAI-powered agent helps process and standardize what comes back so the output stays structured. The result is a sheet that’s ready for sorting, outreach, or analysis, not a rough draft.

The workflow kicks off from a chat trigger, which means you can request new lead pulls without touching the n8n editor. It extracts Maps listings, appends them to Google Sheets, then optionally crawls websites and appends that enrichment as a second dataset. Clean in, clean out.

What Changes: Before vs. After

What This Eliminates

Impact You’ll See

Copying listings one-by-one from Google Maps into a spreadsheet.
Manually hunting for missing websites, phone numbers, and emails.
Opening every company site just to figure out what they actually do.
Reformatting rows because each person pasted data differently.

Most teams cut a half-day list-build down to about 30 minutes of oversight.
Cleaner columns in Google Sheets, which makes filtering and deduping easier.
More complete records thanks to search enrichment when Maps data is sparse.
Website context captured in a consistent place, ready for personalization.
A repeatable process you can rerun weekly without dreading it.

Real-World Impact

Say you need 100 local leads for a new outreach sprint. Manually, you might spend about 3 minutes per listing between copying details, checking a website, and fixing your sheet, which is roughly 5 hours. With this workflow, you send one request, let the Maps scrape run, and review what lands in Google Sheets. Even if you spend 20–30 minutes spot-checking and pruning, you still get most of that afternoon back.

Requirements

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Google Sheets for storing your lead list output.
Apify (Google Maps scraper + website crawler) to extract listings and site content.
SerpAPI key (get it from your SerpAPI dashboard) to fill missing business details.
OpenAI API key (get it from the OpenAI API keys page) for cleanup and enrichment.

Skill level: Intermediate. You’ll connect a few accounts, add API keys, and map columns in Google Sheets.

Need help implementing this? Talk to an automation expert (free 15-minute consultation).

The Workflow Flow

A chat message triggers the request. You describe the type of businesses and the location you want, and the workflow captures those parameters through the chat-based trigger and agent.

The request gets translated into structured inputs. An OpenAI chat model helps normalize the query (category, city, country code, limits) so the scraping tools receive consistent instructions.

Google Maps listings are scraped and logged. n8n sends an HTTP request to the Maps scraping service, then appends each listing into Google Sheets. It also compiles the batch so you get one cohesive “pull” instead of random rows scattered across runs.

Missing fields are enriched, then websites are crawled. If a record is incomplete, SerpAPI can be used as a fallback to find missing details. After that, the workflow crawls each business website and appends website content into Google Sheets in a second pass.

You can easily modify the search inputs to target a different niche or location based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Chat Trigger

This workflow starts when a chat message is received, then passes the conversation to the AI agent for lead capture.

Add or open Incoming Chat Trigger and confirm it is the trigger node for the workflow.
Connect Incoming Chat Trigger to Lead Capture Agent as shown in the execution flow.

Step 2: Connect Google Sheets

These nodes store scraped lead data and website content into Google Sheets.

Open Append Maps Data to Sheets and set Operation to append.
In Append Maps Data to Sheets, choose the target Document and Sheet (the documentId value is currently = and must be updated).
Credential Required: Connect your googleSheetsOAuth2Api credentials in Append Maps Data to Sheets.
Open Append Website Data to Sheets and keep Operation set to append.
Set Sheet Name to [YOUR_ID] and Document to [YOUR_ID] (replace placeholders with real IDs).
Credential Required: Connect your googleSheetsOAuth2Api credentials in Append Website Data to Sheets.

⚠️ Common Pitfall: The placeholders = and [YOUR_ID] in the Google Sheets nodes will cause failures unless replaced with real document and sheet IDs.

Step 3: Set Up the Lead Capture AI Agent

The AI agent orchestrates tool calls, memory, and language model responses for lead capture.

Open Lead Capture Agent and review the System Message prompt to ensure it matches your lead generation rules.
In LLM Request Processor, set the model to gpt-4o-mini.
Credential Required: Connect your openAiApi credentials in LLM Request Processor. This is the language model attached to Lead Capture Agent.
Open Context Window Memory and confirm Context Window Length is set to 50 to retain conversation context.
Ensure the tools Maps Data Extractor Tool, Search Enrichment Fallback, and Website Crawl Utility are connected as AI tools to Lead Capture Agent.
Credential Required: Connect your serpApi credentials in Search Enrichment Fallback (credentials are added on this tool node, but it is used by Lead Capture Agent).

Remember: AI tool sub-nodes like Context Window Memory, Maps Data Extractor Tool, and Website Crawl Utility are used by Lead Capture Agent. Ensure the parent agent has its language model set via LLM Request Processor.

Step 4: Configure the Google Maps Scrape Path

This path runs from a subworkflow trigger, scrapes Google Maps via Apify, then stores and aggregates results.

Open Subworkflow Start Trigger and verify Input Source is jsonExample with the provided sample JSON.
In Apify Maps Scrape Call, set URL to https://api.apify.com/v2/acts/2Mdma1N6Fd0y3QEjR/run-sync-get-dataset-items and Method to POST.
Set the JSON Body to the provided expression string, including {{ $json.city }}, {{ $json.countryCode }}, and {{ $json.search }}.
In Apify Maps Scrape Call headers, replace the Authorization value Bearer [CONFIGURE_YOUR_TOKEN] with your Apify token.
Confirm the flow: Subworkflow Start Trigger → Apify Maps Scrape Call → Append Maps Data to Sheets → Compile Business Listings.

⚠️ Common Pitfall: If the Apify token is missing or invalid in Apify Maps Scrape Call, the scrape will fail with an authorization error.

Step 5: Configure the Website Crawl Path

This path crawls websites with Apify and appends extracted content to Google Sheets, then aggregates the results.

Open Apify Website Crawl Call and set URL to https://api.apify.com/v2/acts/aYG0l9s7dbB7j3gbS/run-sync-get-dataset-items with Method set to POST.
Confirm the JSON Body includes the start URL expression {{ $json.query }} under startUrls.
Update the Authorization header from Bearer [CONFIGURE_YOUR_TOKEN] to your Apify token.
Ensure the flow: Apify Website Crawl Call → Append Website Data to Sheets → Compile Website Content.

Step 6: Test and Activate Your Workflow

Run a manual test to verify data flows through the AI agent, scraping calls, and Sheets outputs.

Click Execute Workflow and send a chat message through Incoming Chat Trigger to simulate a lead request.
Verify that Lead Capture Agent responds and that tool calls (scrape or fallback) are initiated as expected.
Check Google Sheets to confirm rows were appended by Append Maps Data to Sheets and Append Website Data to Sheets.
Confirm aggregation outputs in Compile Business Listings and Compile Website Content show combined item data.
When everything is working, toggle the workflow to Active for production use.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Watch Out For

Google Sheets credentials can expire or need specific permissions. If things break, check the n8n credentials screen and the target spreadsheet sharing settings first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.

Common Questions

How quickly can I implement this Maps lead automation?

About 30 minutes if your API keys are ready.

Can non-technical teams implement this lead capture?

Yes, but you’ll need someone comfortable connecting accounts in n8n. No coding, just careful setup and testing.

Is n8n free to use for this Maps lead automation workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI API usage and any scraping/search API costs (Apify and SerpAPI pricing depends on volume).

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

How do I adapt this Maps lead automation solution to my specific challenges?

You can change the inputs the agent collects (location, category, country code, result limit) and keep the rest the same. If you prefer a different data source, you can replace the Apify Maps scrape HTTP request with another Maps scraping provider and still write results to the same Google Sheets columns. Common tweaks include adding a “must have website” filter, enriching only when a field is blank, or writing into separate tabs per niche.

Why is my Google Sheets connection failing in this workflow?

Usually it’s expired Google authorization or the spreadsheet is in a different Google account than the one connected in n8n. Reconnect the Google Sheets credential, then confirm the file is shared with that account and the sheet name matches what the node expects. If it fails only on larger pulls, you may also be hitting API limits, so reduce batch size or run the scrape in smaller chunks.

What’s the capacity of this Maps lead automation solution?

If you self-host n8n, there’s no hard execution limit (it mainly depends on your server and your API quotas). On n8n Cloud, capacity depends on your plan’s monthly executions, and the real bottleneck is often the Maps scraper and website crawler limits rather than n8n itself.

Is this Maps lead automation automation better than using Zapier or Make?

Often, yes. This workflow leans on multi-step logic (scrape, append, enrich, crawl, append again) and benefits from n8n’s flexibility with HTTP requests, branching, and batching. You also get a realistic self-host option, which can matter once you’re pulling leads weekly. Zapier or Make can still work if you only need a basic “scrape once, write once” flow and you’re okay with fewer customization points. If you want a quick opinion on which tool fits your exact setup, Talk to an automation expert.

A clean lead sheet is only valuable if you trust it. Automate the extraction and enrichment once, then spend your time on targeting and outreach instead.

Need Help Setting This Up?

Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": null,
"meta": {
"instanceId": "82caa77296c1f5f2f5c116fcab53af16d0a8c0afb942a6eb5d5ec0274371b97f",
"templateId": null,
"templateCredsSetupCompleted": null
},
"name": "Automated Maps Lead Workflow",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-3443",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
30
],
"parameters": {
"color": 7,
"width": 1500,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "c5d63d91-ffcc-4c05-a1ee-d78ca955fc85",
"name": "Incoming Chat Trigger",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
1120,
210
],
"webhookId": "e5c0f357-c0a4-4ebc-9162-0382d8009539",
"parameters": {
"options": []
},
"typeVersion": 1.1
},
{
"id": "e422761f-a662-4fef-81fe-de42cdb350fc",
"name": "Lead Capture Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
760,
230
],
"parameters": {
"options": {
"systemMessage": "' UNIFIED AND OPTIMIZED PROMPT FOR DATA EXTRACTION VIA GOOGLE MAPS SCRAPER\n\n' --- 1. Task ---\n' - Collect high-quality professional leads from Google Maps, including:\n'   - Business name\n'   - Address\n'   - Phone number\n'   - Website\n'   - Email\n'   - Other relevant contact details\n' - Deliver organized, accurate, and actionable data.\n\n' --- 2. Context & Collaboration ---\n' - Tools & Sources:\n'   * Google Maps Scraper: Extracts data based on location, business type, and country code \n'     (ISO 3166 Alpha-2 in lowercase).\n'   * Website Scraper: Extracts data from provided URLs (the URL must be passed exactly as received, without quotation marks).\n'   * Google Sheets: Stores and retrieves previously extracted data.\n'   * Internet Search: Provides additional information if the scraping results are incomplete.\n' - Priorities: Accuracy and efficiency, avoiding unnecessary searches.\n\n' --- 3. Ethical Guidelines ---\n' - Only extract publicly accessible professional data.\n' - Do not collect or store personal/sensitive data.\n' - Adhere to scraping policies and data protection regulations.\n' - Error Handling:\n'   * In case of failure or incomplete results, suggest a retry, adjusted search parameters, or an alternative source.\n'   * If Google Sheets is unavailable, notify the user and propose workarounds.\n\n' --- 4. Constraints ---\n' - Country codes must follow the ISO 3166 Alpha-2 format in lowercase (e.g., \"fr\" for France).\n' - When using the Website Scraper, pass the URL exactly as provided, without quotation marks or modifications.\n' - Validate and correctly format all data (no duplicates or errors).\n' - Store results in Google Sheets in an organized and accessible manner.\n\n' --- 5. Final Requirements & Quality Checks ---\n' - Verification: Ensure the country code is always passed in lowercase to the Google Maps Scraper.\n' - URL: If a URL is provided, forward it directly to the Website Scraper without adding quotation marks.\n' - Existing Data: Check Google Sheets to see if the data is already available before performing new scraping.\n' - Supplementary: In case of partial results, propose using Internet Search to complete the information.\n\n' --- 6. Interaction ---\n' - If data already exists in Google Sheets, retrieve and present it to the user instead of launching a new scrape.\n' - If scraping fails or returns incomplete results, suggest alternative actions (e.g., web search, verifying the country code).\n\n' --- 7. Examples ---\n' BAD Example (Google Maps Scraper)\n'   User: \"Find coffee shops in Paris, France.\"\n'   AI: \"Extracting coffee shop data from Google Maps in France.\"\n'   > Issue: The country code \"fr\" was not provided.\n'\n' GOOD Example (Google Maps Scraper)\n'   User: \"Find coffee shops in Paris, France.\"\n'   AI:\n'     - \"Extracting coffee shop data from Google Maps in fr (France).\"\n'     - \"Scraped 50 businesses with names, addresses, phone numbers, and websites.\"\n'     - \"Storing results in Google Sheets under Lead_Generation_Paris_FR.\"\n'\n' BAD Example (Website Scraper)\n'   User: \"Scrape data from https://www.example.com/\"\n'   AI: \"Forwarding 'https://www.example.com/' to the Website Scraper.\"\n'   > Issue: Unnecessary quotation marks around the URL.\n'\n' GOOD Example (Website Scraper)\n'   User: \"Scrape data from https://www.example.com/\"\n'   AI:\n'     - \"Forwarding https://www.example.com to the Website Scraper.\"\n'     - \"Processing data extraction and storing results in Google Sheets.\"\n\n' --- 8. Output Format ---\n' - Responses should be concise and informative.\n' - Present data in a structured manner (e.g., business name, address, phone, website, etc.).\n' - If data already exists, clearly display the retrieved information from Google Sheets.\n\n' --- Additional Context & Details ---\n'\n' You interact with scraping APIs and databases to retrieve, update, and manage lead information.\n' Always pass country information using lowercase ISO 3166 Alpha-2 format when using the Google Maps Scraper.\n' If a URL is provided, it must be passed exactly as received, without quotation marks, to the Website Scraper.\n'\n' Known details:\n' You extract business names, addresses, phone numbers, websites, emails, and other relevant contact information.\n'\n' The URL must be passed exactly as provided (e.g., https://www.example.com/) without quotation marks or formatting changes.\n' Google Maps Scraper requires location, business type, and ISO 3166 Alpha-2 country codes to extract business listings.\n'\n' Context:\n' - System environment:\n'   You have direct integration with scraping tools, Internet search capabilities, and Google Sheets.\n'   You interact with scraping APIs and databases to retrieve, update, and manage lead information.\n'\n' Role:\n' You are a Lead Generation & Web Scraping Agent.\n' Your primary responsibility is to identify, collect, and organize relevant business leads by scraping websites, Google Maps, and performing Internet searches.\n' Ensure all extracted data is structured, accurate, and stored properly for easy access and analysis.\n' You have access to two scraping tools:\n'   1. Website Scraper \u2013 Requires only the raw URL to extract data from a specific website.\n'      - The URL must be passed exactly as provided (e.g., https://www.example.com/) without quotation marks or formatting changes.\n'   2. Google Maps Scraper \u2013 Requires location, business type, and ISO 3166 Alpha-2 country codes to extract business listings.\n\n' --- FINAL INSTRUCTIONS ---\n' 1. Adhere to all the directives and constraints above when extracting data from Google Maps (or other sources).\n' 2. Systematically check if data already exists in Google Sheets.\n' 3. In case of failure or partial results, propose an adjustment to the query or resort to Internet search.\n' 4. Ensure ethical compliance: only collect public data and do not store sensitive information.\n'\n' This prompt will guide the AI agent to efficiently extract and manage business data using Google Maps Scraper (and other mentioned tools)\n' while adhering to the structure, ISO country code standards, and ethical handling of information.\n"
}
},
"typeVersion": 1.8
},
{
"id": "8469f6f8-e56e-433f-8439-ac0f568b01b1",
"name": "LLM Request Processor",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1260,
130
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": []
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "8f89996c-f5d1-48e3-8023-9c5d4c8db12a",
"name": "Context Window Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
1400,
300
],
"parameters": {
"contextWindowLength": 50
},
"typeVersion": 1.3
},
{
"id": "ef32b577-47a2-489f-8b5a-3640126a0ff9",
"name": "Maps Data Extractor Tool",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
220,
230
],
"parameters": {
"name": "extract_google_maps",
"workflowId": {
"__rl": true,
"mode": "list",
"value": "9rD7iD6sbXqDX44S",
"cachedResultName": ""
},
"description": "Extract data from hundreds of places fast. Scrape Google Maps by keyword, category, location, URLs & other filters. Get addresses, contact info, opening hours, popular times, prices, menus & more. Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools.",
"workflowInputs": {
"value": {
"city": "={{ $fromAI('city', ``, 'string') }}",
"search": "={{ $fromAI('search', ``, 'string') }}",
"countryCode": "={{ $fromAI('countryCode', ``, 'string') }}",
"state/county": "={{ $fromAI('state_county', ``, 'string') }}"
},
"schema": [
{
"id": "search",
"type": "string",
"display": true,
"required": false,
"displayName": "search",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "city",
"type": "string",
"display": true,
"required": false,
"displayName": "city",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "state/county",
"type": "string",
"display": true,
"required": false,
"displayName": "state/county",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "countryCode",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "countryCode",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.1
},
{
"id": "86a6eafe-9ffc-4d58-85f7-eef7171eeb8e",
"name": "Search Enrichment Fallback",
"type": "@n8n/n8n-nodes-langchain.toolSerpApi",
"position": [
440,
290
],
"parameters": {
"options": []
},
"credentials": {
"serpApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "0b42dfae-49e6-4117-8a5d-d1f396f22dcb",
"name": "Website Crawl Utility",
"type": "@n8n/n8n-nodes-langchain.toolWorkflow",
"position": [
0,
170
],
"parameters": {
"name": "Website_Content_Crawler",
"workflowId": {
"__rl": true,
"mode": "list",
"value": "I7KceT8Mg1lW7BW4",
"cachedResultName": ""
},
"description": "Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with \ud83e\udd9c\ud83d\udd17 LangChain, LlamaIndex, and the wider LLM ecosystem.",
"workflowInputs": {
"value": [],
"schema": [],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
}
},
"typeVersion": 2.1
},
{
"id": "8a713b20-99e6-4df1-88ce-698ffc3c1e31",
"name": "Subworkflow Start Trigger",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
1120,
420
],
"parameters": {
"inputSource": "jsonExample",
"jsonExample": "{\n  \"search\": \"carpenter\",\n  \"city\": \"san francisco\",\n  \"state/county\": \"california\",\n  \"countryCode\": \"us\"\n}"
},
"typeVersion": 1.1
},
{
"id": "59af012d-de3f-4a44-b3ad-e587857b554d",
"name": "Apify Maps Scrape Call",
"type": "n8n-nodes-base.httpRequest",
"position": [
860,
450
],
"parameters": {
"url": "https://api.apify.com/v2/acts/2Mdma1N6Fd0y3QEjR/run-sync-get-dataset-items",
"method": "POST",
"options": [],
"jsonBody": "={\n    \"city\": \"{{ $json.city }}\",\n    \"countryCode\": \"{{ $json.countryCode }}\",\n    \"locationQuery\": \"{{ $json.city }}\",\n    \"maxCrawledPlacesPerSearch\": 5,\n    \"searchStringsArray\": [\n        \"{{ $json.search }}\"\n    ],\n    \"skipClosedPlaces\": false\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "b1c40871-aa57-4b15-9f19-34a07dc6c45f",
"name": "Append Maps Data to Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
600,
480
],
"parameters": {
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "",
"cachedResultName": ""
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "="
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
},
{
"id": "679f2af5-0024-4a71-8c04-dcbccc8f00c8",
"name": "Compile Business Listings",
"type": "n8n-nodes-base.aggregate",
"position": [
360,
510
],
"parameters": {
"options": [],
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "dd691f9c-15e2-4b4a-a6eb-8765905a2cb4",
"name": "Apify Website Crawl Call",
"type": "n8n-nodes-base.httpRequest",
"position": [
1120,
620
],
"parameters": {
"url": "https://api.apify.com/v2/acts/aYG0l9s7dbB7j3gbS/run-sync-get-dataset-items",
"method": "POST",
"options": [],
"jsonBody": "={\n    \"aggressivePrune\": false,\n    \"clickElementsCssSelector\": \"[aria-expanded=\\\"false\\\"]\",\n    \"clientSideMinChangePercentage\": 15,\n    \"crawlerType\": \"playwright:adaptive\",\n    \"debugLog\": false,\n    \"debugMode\": false,\n    \"expandIframes\": true,\n    \"ignoreCanonicalUrl\": false,\n    \"keepUrlFragments\": false,\n    \"proxyConfiguration\": {\n        \"useApifyProxy\": true\n    },\n    \"readableTextCharThreshold\": 100,\n    \"removeCookieWarnings\": true,\n    \"removeElementsCssSelector\": \"nav, footer, script, style, noscript, svg, img[src^='data:'],\\n[role=\\\"alert\\\"],\\n[role=\\\"banner\\\"],\\n[role=\\\"dialog\\\"],\\n[role=\\\"alertdialog\\\"],\\n[role=\\\"region\\\"][aria-label*=\\\"skip\\\" i],\\n[aria-modal=\\\"true\\\"]\",\n    \"renderingTypeDetectionPercentage\": 10,\n    \"saveFiles\": false,\n    \"saveHtml\": false,\n    \"saveHtmlAsFile\": false,\n    \"saveMarkdown\": true,\n    \"saveScreenshots\": false,\n    \"startUrls\": [\n        {\n            \"url\": \"{{ $json.query }}\",\n            \"method\": \"GET\"\n        }\n    ],\n    \"useSitemaps\": false\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "7cc813a7-e1a5-40fe-a76a-3e52438cf2f4",
"name": "Append Website Data to Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
840,
650
],
"parameters": {
"columns": {
"value": [],
"schema": [
{
"id": "url",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "crawl",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "crawl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "metadata",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "metadata",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "screenshotUrl",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "screenshotUrl",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "text",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "text",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "markdown",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "markdown",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "debug",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "debug",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "autoMapInputData",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": ""
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": ""
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
},
{
"id": "6c20b427-48e8-4ba1-885e-7db71406a0db",
"name": "Compile Website Content",
"type": "n8n-nodes-base.aggregate",
"position": [
560,
680
],
"parameters": {
"options": [],
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": null,
"connections": {
"Context Window Memory": {
"ai_memory": [
[
{
"node": "Lead Capture Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Website Crawl Utility": {
"ai_tool": [
[
{
"node": "Lead Capture Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Apify Maps Scrape Call": {
"main": [
[
{
"node": "Append Maps Data to Sheets",
"type": "main",
"index": 0
}
]
]
},
"Subworkflow Start Trigger": {
"main": [
[
{
"node": "Apify Maps Scrape Call",
"type": "main",
"index": 0
}
]
]
},
"Incoming Chat Trigger": {
"main": [
[
{
"node": "Lead Capture Agent",
"type": "main",
"index": 0
}
]
]
},
"Append Website Data to Sheets": {
"main": [
[
{
"node": "Compile Website Content",
"type": "main",
"index": 0
}
]
]
},
"Apify Website Crawl Call": {
"main": [
[
{
"node": "Append Website Data to Sheets",
"type": "main",
"index": 0
}
]
]
},
"Search Enrichment Fallback": {
"ai_tool": [
[
{
"node": "Lead Capture Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"LLM Request Processor": {
"ai_languageModel": [
[
{
"node": "Lead Capture Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Append Maps Data to Sheets": {
"main": [
[
{
"node": "Compile Business Listings",
"type": "main",
"index": 0
}
]
]
},
"Maps Data Extractor Tool": {
"ai_tool": [
[
{
"node": "Lead Capture Agent",
"type": "ai_tool",
"index": 0
}
]
]
}
}
}