Scrape & enrich Google Maps leads with Decodo API and Gemini 2.5 Flash
Ready for 3.0What this workflow does
This AI workflow has 16 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Sheets, Google Gemini Chat Model and Telegram. It also calls scraper-api.decodo.com over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Set Search Parameters (Edit Fields (Set)): sets 4 fields: searchQuery, targetLanguage, country…
- Format Error Message (Code): runs custom JavaScript code
- Decodo Maps Scraper (HTTP Request): calls scraper-api.decodo.com (POST)
- Send Error Notification (Telegram): uses Telegram
- Parse & Normalize Data (Code): runs custom JavaScript code
- Split Into Batches (Loop Over Items (Split in Batches)): loops over the items in batches
- Lead Enrichment (Basic LLM Chain): sends a prompt to an LLM, with model: 2.5 Flash; output parser: Result Parser
- Merge Enrichment Data (Edit Fields (Set)): sets 17 fields: id, businessName, category…
- Save to Google Sheets (Google Sheets): append or update
- Filter Hot Leads (If): checks a condition and branches into true / false
…plus 2 more steps. See the full node list below.
Services it uses
HTTP calls to: scraper-api.decodo.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (12)
- Code
n8n-nodes-base.code - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Sheets
n8n-nodes-base.googleSheets - If
n8n-nodes-base.if - Error Trigger
n8n-nodes-base.errorTrigger - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Telegram
n8n-nodes-base.telegram - Manual Trigger
n8n-nodes-base.manualTrigger
From the author
Turn Google Maps into a lead machine. This workflow scrapes listings with the Decodo API, scores each business with Google Gemini, and writes ready-to-send outreach emails. Research that took 20 minutes per lead now runs 100 leads in under an hour. Last…