Scrape local business directories with Bright Data & OpenAI for lead generation

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

This workflow contains community nodes that are only compatible with the self hosted version of n8n. This workflow automatically scrapes local business directories (Yelp, Yellow Pages, Google Maps,...

Best for

Lead Generation automation workflows
AI Summarization automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.manualtrigger, n8n-nodes-base.set, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenai, n8n-nodes-mcp.mcpclienttool, n8n-nodes-base.gmail, n8n-nodes-base.stickynote, @n8n/n8n-nodes-langchain.outputparserautofixing

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Yaron Been.

Original n8n.io source

1.1 Workflow description

Title: Scrape local business directories with Bright Data & OpenAI for lead generation
Workflow name: Scrape local business directories with Bright Data & OpenAI for lead generation

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

This workflow automatically scrapes local business directories (Yelp, Yellow Pages, Google Maps, etc.) to build a structured database of prospects. Stop copying listings by hand—get fresh leads delivered straight to Google Sheets.

Overview

Using Bright Data, the automation fetches business names, contact details, ratings, and categories for a given city or ZIP code. OpenAI cleans and normalizes the data, while duplicate detection ensures each business appears only once. The result is emailed as a CSV and stored in Sheets for easy filtering.

Tools Used

n8n – Workflow orchestration
Bright Data – Handles large-scale directory scraping
OpenAI – Performs entity cleanup and deduplication
Google Sheets – Houses the resulting lead list
Gmail – Sends the CSV file to your inbox

How to Install

Import the Workflow: Load the .json into n8n.
Configure Bright Data: Add your credentials.
Set Up OpenAI: Enter your API key.
Connect Google Sheets & Gmail: Authorize both integrations.
Customize Locations & Categories: Adjust parameters in the Start node.

Use Cases

Local Lead Generation: Build outreach lists for agencies or SaaS.
Market Research: Analyze density of businesses in a region.
Franchise Expansion: Identify potential partners within a territory.
Startup Sales: Discover SMBs that match your ICP.

Connect with Me

Website: https://www.nofluff.online
YouTube: https://www.youtube.com/@YaronBeen/videos
LinkedIn: https://www.linkedin.com/in/yaronbeen/
Get Bright Data: https://get.brightdata.com/1tndi4600b25 (Using this link supports my free workflows with a small commission)

#n8n #automation #webscraping #localbusiness #brightdata #leadgeneration #n8nworkflow #nocode #businessdirectories #openai

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - 🔘 Trigger: Manual Execution

Type / Role: n8n-nodes-base.manualTrigger - manualTrigger
Config choices: Version 1

Block 2 - 🔗 Set Yelp Business URL for Dr

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 3 - 🤖 Agent: Scrape Yelp Business Info

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 2

Block 4 - 💬 AI Model: Process Data

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.2

Block 5 - 🌐 Bright Data MCP Client

Type / Role: n8n-nodes-mcp.mcpClientTool - mcpClientTool
Config choices: Version 1

Block 6 - 📧 Send Partnership Proposal to Business Email

Type / Role: n8n-nodes-base.gmail - gmail
Config choices: Version 2.1

Block 7 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 8 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 9 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 10 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 11 - Sticky Note5

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 12 - Sticky Note9

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 13 - Auto-fixing Output Parser

Type / Role: @n8n/n8n-nodes-langchain.outputParserAutofixing - outputParserAutofixing
Config choices: Version 1

Block 14 - OpenAI Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.2

Block 15 - 📝 Parse Scraped Data into JSON1

Type / Role: @n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices: Version 1.3

3. Summary Table

Workflow	Scrape local business directories with Bright Data & OpenAI for lead generation
Complexity	advanced
Nodes	15
Categories	Lead Generation, AI Summarization
Author	Yaron Been
Published	13 Jul 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/5971/5971.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Lead Generation workflows AI Summarization workflows

Frequently asked questions

What does Scrape local business directories with Bright Data & OpenAI for lead generation do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Lead Generation, AI Summarization use case.

Yaron Been

180 workflows

Nodes

n8n-nodes-base.manualtrigger n8n-nodes-base.set @n8n/n8n-nodes-langchain.agent @n8n/n8n-nodes-langchain.lmchatopenai n8n-nodes-mcp.mcpclienttool n8n-nodes-base.gmail n8n-nodes-base.stickynote @n8n/n8n-nodes-langchain.outputparserautofixing

Complexity

advanced

Published 13 Jul 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/5971/5971.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Find LinkedIn engagement opportunities with Apify, Gemini, Google Sheets and Slack

## Quick overview Youtube Video: https://youtu.be/ehsagyRmri4 This workflow runs on a schedule to scrape recent LinkedIn posts with Apify, stores and evaluates them in Google Sheets using Google Gemini, then enriches shortlisted authors with Apify profile data, saves profile results to a second Sheet, and sends Slack alerts for comment and connection opportunities. ## How it works 1. Runs on a schedule and sets the Ideal Customer Profile (ICP) text used for evaluation. 2. Scrapes LinkedIn posts from Apify using the configured search query and merges the results with existing rows from a Google Sheets “Linkedin_Outreach_oppurtunities” sheet. 3. Limits processing to two posts, upserts the post details into Google Sheets, and sends each post’s content to Google Gemini to score whether it is a comment opportunity. 4. If the post is marked as an opportunity with a confidence score above 80, the workflow updates the corresponding Google Sheets row with the AI reasoning and suggested comment angle. 5. Aggregates the qualified opportunities, compares their author profile URLs against an existing “Profile_scraper” Google Sheet, and keeps only authors that are not already present. 6. Scrapes each new author profile with an Apify profile scraper, uses Google Gemini to score ICP match, saves the profile details and qualification summary to the “Profile_scraper” Google Sheet, and posts a Slack message with the shortlisted profile link. 7. Separately, a Google Sheets trigger watches the opportunities sheet for row updates and sends a Slack alert containing the post link, reasoning, and comment angle. ## Setup 1. Add Apify credentials and verify the actor IDs and input parameters for the LinkedIn post scraper and the profile scraper. 2. Configure Google Sheets access (service account for read/write nodes and a Google Sheets Trigger OAuth connection) and update the document IDs/sheet tabs for both the opportunities sheet and the profile sheet. 3. Add Google Gemini (Google PaLM) credentials and confirm the selected Gemini model names in both AI evaluation steps. 4. Add Slack credentials, choose the target channel, and adjust the Slack message text if needed. 5. Customize the ICP text and the LinkedIn search query/posted time window to match the audience and volume you want to monitor.

View

Enrich existing HubSpot company records with Veridion

## Quick Overview This workflow manually enriches existing HubSpot companies using Veridion, skipping records already marked as enriched and updating HubSpot with matched company details like industry, location, and key firmographics. ## How it works 1. Runs when you manually execute the workflow. 2. Fetches up to 100 companies from HubSpot and includes key properties such as name, domain, phone, and the custom veridion_enriched flag. 3. Stops with a clear error if the veridion_enriched property is missing, otherwise filters to only companies not yet marked as enriched. 4. Retrieves full details for each selected HubSpot company and sends its name, domain/website, and phone to Veridion for enrichment. 5. Checks whether Veridion returns a match and skips companies without a match. 6. Maps key Veridion fields and updates the HubSpot company record with enriched details and sets veridion_enriched to true. ## Setup 1. Create the HubSpot company custom properties veridion_enriched (boolean/checkbox) and veridion_industry (single-line text). 2. Add HubSpot App Token credentials and ensure the HubSpot company list request includes veridion_enriched, veridion_industry, name, domain/website, phone, and hs_object_id. 3. Add Veridion API credentials and confirm your HubSpot companies have at least a name plus a domain/website or phone for best matching.

View

Identify company decision makers with Coresignal and Google Sheets

## Quick Overview This workflow manually pulls company website data from Google Sheets, finds matching companies in Coresignal, and searches for decision-maker employees. It then writes the resulting contact and company details back to a dedicated “Decision makers” sheet in Google Sheets. ## How it works 1. Manually starts the workflow and reads company rows from a Google Sheets spreadsheet. 2. Normalizes each company website URL into a clean domain and searches Coresignal for the matching company by website domain. 3. Processes companies in batches and writes placeholder “no employee found” company details to the “Decision makers” sheet in Google Sheets. 4. For each matched company, searches Coresignal for current employees whose titles match common executive and leadership roles. 5. If the title-based search does not return a single employee ID, runs a broader Coresignal decision-maker search that excludes HR-related roles and departments. 6. Retrieves detailed employee (and, when needed, company) fields from Coresignal and appends or updates the “Decision makers” sheet with names, titles, emails, LinkedIn URLs, and company information. ## Setup 1. Create a Google Sheets OAuth2 connection and set the source sheet (companies with a Website field) and the target “Decision makers” sheet in the Google Sheets nodes. 2. Create a Coresignal API credential in n8n and ensure your plan supports company and employee Elasticsearch DSL search and profile retrieval. 3. Confirm your input sheet includes a website column named either Website or website, and adjust the Coresignal title/department filters to match the decision-maker roles you want to capture.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Scrape local business directories with Bright Data & OpenAI for lead generation

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Overview

Tools Used

How to Install

Use Cases

Connect with Me

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - 🔘 Trigger: Manual Execution

Block 2 - 🔗 Set Yelp Business URL for Dr

Block 3 - 🤖 Agent: Scrape Yelp Business Info

Block 4 - 💬 AI Model: Process Data

Block 5 - 🌐 Bright Data MCP Client

Block 6 - 📧 Send Partnership Proposal to Business Email

Block 7 - Sticky Note

Block 8 - Sticky Note1

Block 9 - Sticky Note2

Block 10 - Sticky Note3

Block 11 - Sticky Note5

Block 12 - Sticky Note9

Block 13 - Auto-fixing Output Parser

Block 14 - OpenAI Chat Model

Block 15 - 📝 Parse Scraped Data into JSON1

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions