Impressum Company Details Extractor with Verified OpenAI JSON

Extract and verify Impressum company details automatically—returns clean, confirmed JSON

This n8n workflow takes a website URL, finds the site’s Impressum/imprint page, and uses OpenAI to extract company details as strict JSON. Even better: every extracted value is verified against the Impressum text before it’s returned—so your data stays reliable.

What this workflow does

• Receives a POST webhook with website (and optionally organization and reference_id).
• Validates and normalizes the URL, blocking private/local addresses and returning a 400 response for invalid inputs.
• Finds the Impressum URL by locating links or embedded content on the homepage, with a fallback to /impressum.
• Fetches and cleans the Impressum page by converting HTML into cleaned plain text and stopping when no usable content exists.
• Extracts fields with OpenAI Chat Completions as strict JSON.
• Verifies each value by checking that it literally appears in the Impressum text; unverified fields are dropped.
• Responds with JSON containing verified data, dropped_fields, and the detected impressum_url.

Use cases

• Build/maintain a dataset of German company contact/legal details for outreach and compliance workflows.
• Enrich leads by automatically pulling verified imprint data from prospect websites.
• Reduce manual research effort in SaaS operations and automation engineering tasks where accuracy matters.

Technical details

• n8n nodes used: if, code, webhook, http request, respond to webhook, and sticky note.
• OpenAI integration: sends cleaned Impressum text to https://api.openai.com/v1/chat/completions using an OpenAI API credential.
• Output: verified JSON values only, plus dropped_fields and impressum_url in the webhook response.