LinkedIn Profile to JSON Resume Builder using Gemini & Bright Data - n8n Workflow

Recruiters and HR Professionals: Quickly standardize candidate profiles into machine-readable JSON formats. Data Engineers: Users needing a reliable n8n workflow template for web data extraction and complex AI-driven data structuring. Automation Specialists: Anyone looking to combine advanced web scraping techniques (Bright Data) with large language models (Google Gemini) within an n8n environment. Developers: Those requiring structured resume data for application processing or database integration.

Extracting data from dynamic websites like LinkedIn often requires specialized tools. This specific n8n workflow addresses this by integrating Bright Data's Web Unlocker for reliable profile scraping. The crucial challenge then becomes transforming the resulting messy, unstructured markdown data into a clean, standardized format like the JSON Resume schema. This is where the power of the Google Gemini LLM is utilized. The complete n8n workflow acts as a powerful data pipeline, ensuring high-quality, structured output ready for immediate use, drastically reducing manual data entry and parsing time. This efficient n8n automation process makes handling large volumes of profile data straightforward.

This complex n8n workflow follows a multi-stage process from trigger to structured output:

1. Trigger and Setup: The automation starts with a manual n8n trigger, initiating the process. A subsequent Set n8n node defines critical parameters: the target LinkedIn profile URL, the Bright Data zone (e.g., webunlocker1), and a target webhook URL for notification.


2. Web Scraping: The Perform Bright Data Web Request n8n node sends a request to the Bright Data API, using the specified zone and URL to scrape the profile content, requesting the data output in markdown format.


3. Data Preprocessing (LLM): The raw markdown data is fed into the Markdown to Textual Data Extractor n8n node. This Langchain n8n node utilizes the Google Gemini chat model to clean the input, removing residual HTML, scripts, and links, leaving behind only clean textual data.


4. Parallel Structured Extraction: The clean text branches into two parallel extraction pathways:

1. Final Actions: Both resulting JSON structures (the full resume and the skill list) are prepared. Custom Function n8n nodes convert the JSON data into binary format. Finally, the structured files are written to local disk (e.g., d:\JsonResume.json) and a notification containing the final structured resume data is sent via an httpRequest n8n node to the configured webhook URL.

To deploy this powerful n8n workflow template, follow these steps:

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


2. Credentials Setup:

1. Configuration Node: Open the Set URL and Bright Data Zone n8n node. Update the default values:

1. Local Output (Self-Hosted n8n): If you are using a self-hosted n8n instance, ensure the paths specified in the Write the structured content to disk and Write the structured skills content to disk n8n nodes (e.g., d:\Json_Resume.json) are accessible by the n8n container or host machine.

When clicking ‘Test workflow’ (Manual Trigger n8n trigger):
Function: Starts the n8n workflow manually for testing and initial setup.
Key Configuration: Standard manual initiation.
Set URL and Bright Data Zone (Set n8n node):
Function: Centralizes all necessary input variables (URL, Bright Data zone, webhook). This simplifies management of the n8n template.
Key Configuration: Defines url, zone, and webhooknotificationurl variables.
Perform Bright Data Web Request (HTTP Request n8n node):
Function: Communicates with the Bright Data API to execute the web scraping task, requesting raw markdown data.
Key Configuration: Uses POST method to https://api.brightdata.com/request. Authentication type is httpHeaderAuth. Body parameters include dynamically set zone and url, and static format: raw, dataformat: markdown.
Markdown to Textual Data Extractor (Langchain ChainLlm n8n node):
Function: Cleans the raw markdown output from Bright Data using the Gemini model, preparing it for structured extraction.
Key Configuration: Uses Google Gemini Chat Model for Markdown to Textual connection. Input text instructs the model to convert markdown to textual data only.
JSON Resume Extractor (Langchain Information Extractor n8n node):
Function: The core LLM processing step. It extracts the full resume details and maps them strictly to the comprehensive JSON Resume schema using the Gemini model.
Key Configuration: References a complex, pre-defined JSON schema for structured output. Connected to the Google Gemini Chat Model n8n node.
Skill Extractor (Langchain Information Extractor n8n node):
Function: Extracts a specific subset of data (skills) into a structured JSON array.
Key Configuration: Uses a simpler input schema (skill, desc). Connected to the dedicated Google Gemini Chat Model for Skill Extractor n8n node.
Create a binary data... (Function n8n node):
Function: Converts the final structured JSON objects into a Base64-encoded buffer, enabling them to be saved as binary files by the subsequent n8n node.
Write the structured content to disk (Read/Write File n8n node):
Function: Saves the final structured JSON resume file locally. This is a crucial output step for this n8n workflow.
* Key Configuration: Operation set to write, with a fixed file path (e.g., d:\JsonResume.json).