Automated Web Data Extraction and Sentiment Analysis Workflow

This n8n workflow automates the process of extracting structured data from web pages using Bright Data’s Web Unlocker, analyzing the content with Google Gemini’s language models, and performing sentiment analysis. The workflow begins with a manual trigger, allowing users to specify a target URL and zone for web scraping. It then sends a request to Bright Data to retrieve the webpage data in markdown format.

The markdown data is converted into plain text, which is subsequently analyzed by Google Gemini models for topic extraction and sentiment analysis. Additionally, the workflow performs data clustering to identify emerging trends across different locations and categories. All extracted and analyzed data are formatted into JSON, saved as binary files on disk, and sent via webhooks for further processing or notification.

This workflow is particularly useful for monitoring news, social media, or any web content for trending topics, sentiment shifts, or emerging patterns, making it ideal for market analysis, competitive intelligence, or research purposes.