Extract Named Entities from Web Pages with Google NL API

This workflow creates an automated pipeline that receives a web page URL via webhook, fetches and cleans the HTML content, then analyzes it with Google's Natural Language API to extract named entities like people, organizations, locations, and more, complete with salience scores. It responds directly with structured JSON data ready for further processing or storage.

Key benefits include eliminating manual entity identification, which is time-consuming and error-prone, leveraging Google's accurate NLP for reliable results, and enabling scalable analysis of multiple web pages. Ideal for high-volume content processing without custom coding.

Perfect for content strategists, SEO professionals, data analysts, marketers, and researchers. Use cases: competitor analysis, semantic SEO audits, content categorization, lead generation from web data, and automated research pipelines.

Setup requires an n8n instance and Google Cloud project with Natural Language API enabled and API key configured. Simple to deploy and customize for specific entity types or post-processing.