This n8n workflow automates the real-time extraction of detailed job, company, and salary information from online sources, leveraging Bright Data MCP clients and OpenAI’s language models. Designed for HR and recruitment professionals, it streamlines data collection and analysis, making it easier to gather comprehensive job market insights.

The process begins when a manual trigger initiates the workflow. It uses the Bright Data MCP Client to scrape job posting data from a specified URL, and additionally fetches company details and salary information based on the job role. The retrieved web content is then processed through OpenAI’s mini GPT-4 models to extract structured data, including job descriptions, salary ranges, company information, and relevant insights.

The extracted data is merged into a unified JSON object. This data is then saved as a JSON file locally and sent via a webhook to notify an external system. Simultaneously, the information is appended or updated in a Google Sheet for record-keeping and further analysis.

Additional nodes include sticky notes for documentation and disclaimers, emphasizing that the workflow uses community nodes and is suitable for self-hosted n8n instances. Practical uses include market research, salary benchmarking, or creating a data-driven HR dashboard to support talent acquisition strategies.

Node Count	>20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.informationExtractor, @n8n/n8n-nodes-langchain.lmChatOpenAi, aggregate, function, googleSheets, httpRequest, manualTrigger, merge, n8n-nodes-mcp.mcpClient, readWriteFile, set, stickyNote