Dynamic Profile List Builder using AI Extraction and Google Sheets - n8n Workflow

Recruiters and Sourcers needing targeted prospect lists.
Marketing professionals building influencer lists or competitive analyses.
Data analysts requiring structured data extracted from multiple web pages.
Users looking for powerful n8n templates that utilize AI web extraction tools.

• Automation specialists mastering custom logic within an n8n workflow.

Manually building lists of industry experts or influencers from specialized platforms can be tedious and time-consuming. This robust n8n workflow solves this problem by automating the entire process, from initial search to final data cleanup and storage. By leveraging the advanced web extraction capabilities of the Airtop n8n node, the workflow first identifies pages listing relevant profiles and then extracts structured data (Name, Handle, URL) from each source. The results are then automatically deduped using custom JavaScript logic within an n8n node before being stored in Google Sheets. This highly efficient n8n workflow is one of the best n8n templates for rapid market research and list generation.

This n8n workflow executes a multi-step extraction process:

1. Trigger and Setup: The n8n trigger is a manual activation ('When clicking ‘Test workflow’'). The process immediately initializes a Set n8n node (Parameters) to define the search target (e.g., who: "Top \"Build in Public\" influencers" and where: "X").


2. Identify List Sources: The first Airtop n8n node ('Get urls') uses the defined parameters to run a targeted Google search and extracts up to 10 URLs that contain lists of the desired profiles.


3. Prepare Data: The 'Format results' Code n8n node parses the JSON response from Airtop, isolating the URLs so that each link is processed as a separate item for the next step.


4. Extract Profiles: The second Airtop n8n node ('Get people') iteratively visits every URL identified in the previous step. For each page, it uses AI to extract up to 20 profiles, capturing their name, identifier (handle/ID), and URL.


5. Clean and Dedupe: The 'Dedupe results' Code n8n node aggregates all extracted profiles across all source URLs. It applies cleaning logic (stripping tracking parameters from URLs) and ensures that only unique profiles remain, preventing duplicates in the final list. This demonstrates the power of custom scripting within an n8n workflow.


6. Final Storage: The final Google Sheets n8n node ('Add to spreadsheet') takes the deduped, structured profile data and appends it to a designated spreadsheet. It logs key information, including the source parameters defined by the initial n8n trigger setup, ensuring traceability.

To deploy this n8n workflow template, follow these steps:

1. Import: Copy the provided JSON code and paste it into your n8n instance using the 'New' > 'Import from JSON' function.


2. Credentials: You will need to set up two main credentials:

1. Google Sheets Setup: Modify the 'Add to spreadsheet' n8n node. Update the Document ID and Sheet Name parameters to point to your specific target spreadsheet where the profile lists will be stored.


2. Configuration: Update the 'Parameters' n8n node (Set type) to define the who and where variables for the specific list you wish to build (e.g., changing 'X' to 'LinkedIn' or 'GitHub').


3. Execute: Click 'Test workflow' to run a single execution, or activate the n8n workflow to run on a schedule (if you change the n8n trigger type).

This n8n workflow relies on a specific sequence of custom and standard n8n node operations:

When clicking ‘Test workflow’ (Manual Trigger n8n trigger):
Function: Starts the n8n workflow manually.
Key Configuration: Standard manual activation—perfect for development and testing of this n8n template.
Parameters (Set n8n node):
Function: Defines the target variables (who and where) for dynamic input into the scraping process.
Key Configuration: Assignments are set to who (e.g., 'influencers') and where (e.g., 'X').
Get urls (Airtop n8n node):
Function: Uses AI to perform a targeted Google search and extract URLs pointing to potential profile lists. This is the initial data discovery step.
Key Configuration: Resource: extraction, Operation: query, utilizes a JSON schema to ensure structured output containing title and url.
Format results (Code n8n node):
Function: Transforms the batch output of the previous n8n node into individual items, one per URL, preparing for parallel processing.
Key Configuration: Custom JavaScript to parse modelResponse and map results to output items.
Get people (Airtop n8n node):
Function: Iteratively visits each target URL and uses AI extraction to pull structured profile data (Name, ID, URL).
Key Configuration: Uses an expression for the url and a prompt optimized to extract lists of people based on the original parameters.
Dedupe results (Code n8n node):
Function: Cleans the extracted data, removes profiles missing names, cleans up tracking parameters from URLs, and enforces deduplication based on the profile URL. Essential for a clean final dataset.
Key Configuration: Aggregates input items and uses findIndex for deduplication logic.
Add to spreadsheet (Google Sheets n8n node):
Function: The final action, appending the cleaned, structured data to a Google Sheet.
* Key Configuration: Operation: append, mapping data fields like URL, Name, ID or Handle, and source parameters.