Automated website change monitoring with Bright Data, GPT-4.1 & Google Workspace
Needs changesWhat this workflow does
This AI workflow has 26 nodes and runs on a schedule (every week at 12:00). Along the way it connects Google Sheets, Google Drive, Google Docs and Gmail and 2 more.
How it runs
Trigger: On a schedule (every week at 12:00).
- Set workflow variables (Edit Fields (Set)): sets 5 fields: DriveFolderID, ComparisonSpreadsheetID, ComparisonSpreadsheetSheetName…
- Read from comparison spreadsheets (Google Sheets): uses Google Sheets
- Merge workflow variables with Google Sheet data (Edit Fields (Set)): sets 5 fields: ComparisonSpreadsheetFileName, ComparisonSpreadsheetSheetName, Email…
- Loop over each comparison URL (Loop Over Items (Split in Batches)): loops over the items in batches
- Web scraping and data extraction agent (AI Agent): runs an AI agent, with model: GPT-4.; 1 tool (scrape_as_markdown); output parser: Auto-fixing Output Parser
- Convert current week JSON response to file (Convert to File): converts data to a file (to json)
- Upload current week JSON file (Google Drive): uses Google Drive
- Update comparison sheet with current week file data (Google Sheets): update
- Check presence of previous week's file (If): checks a condition and branches into true / false
- Download previous week's file (Google Drive): download
…plus 11 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Web scraping and data extraction agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Web scraping and data extraction agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (17)
- Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Edit Fields (Set)
n8n-nodes-base.set - Google Sheets
n8n-nodes-base.googleSheets - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Drive
n8n-nodes-base.googleDrive - If
n8n-nodes-base.if - Extract from File
n8n-nodes-base.extractFromFile - Code
n8n-nodes-base.code - Markdown
n8n-nodes-base.markdown - Google Docs
n8n-nodes-base.googleDocs - Gmail
n8n-nodes-base.gmail - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Mcp Client Tool
n8n-nodes-mcp.mcpClientTool - Auto-fixing Output Parser
@n8n/n8n-nodes-langchain.outputParserAutofixing - Convert to File
n8n-nodes-base.convertToFile
From the author
Note: This template is for self-hosted n8n instances only You can use this workflow to fully automate website content monitoring and change detection on a weekly basis—even when there’s no native node for scraping or structured comparison. It uses an…