Extract real estate listings with Snapshot Site, OpenAI, and Google Sheets
UnknownWhat this workflow does
This AI workflow has 13 nodes and runs on a schedule (every day at 14:00). Along the way it connects Google Sheets, OpenAI Chat Model and Snapshot Site (community).
How it runs
Trigger: On a schedule (every day at 14:00).
- Read Property Sources (Google Sheets): read (sheet)
- Loop Over Property Sources (Loop Over Items (Split in Batches)): loops over the items in batches
- Get Page HTML (Snapshot Site): screenshot
- Check for API Error (If): checks a condition and branches into true / false
- Build Error Record (Edit Fields (Set)): sets 3 fields: url, message, occurredAt
- Clean HTML (Code): runs custom JavaScript code
- Log Extraction Error (Google Sheets): append (sheet)
- Extract Listing Fields (Information Extractor): extracts structured fields from text with AI, with model: Extraction Model
- Split Listings (Split Out): splits a list into separate items
- Save Listings (Google Sheets): append or update (sheet)
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-snapshot-site is verified or supports 3.0 (used in Get Page HTML).
Nodes used (11)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Google Sheets
n8n-nodes-base.googleSheets - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - No Operation, do nothing
n8n-nodes-base.noOp - Snapshot Site
n8n-nodes-snapshot-site.snapshotSite - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Split Out
n8n-nodes-base.splitOut
From the author
Quick overview This workflow runs daily, reads real estate listing URLs from Google Sheets, captures rendered HTML with Snapshot Site, extracts structured listing details using OpenAI via n8n’s Information Extractor, and writes deduplicated results back to…