Reusable Web Page Scraper Tool using FireCrawl - n8n Workflow

AI developers needing reliable web scraping tools for their n8n agents.
Users looking for advanced, modular n8n templates for complex data extraction.
Automation specialists who frequently need to crawl sites within a larger n8n workflow structure.
Anyone building sophisticated automations using the Execute Workflow n8n node as a reusable function caller.

This specialized n8n workflow transforms web scraping into an easily accessible service tool. Instead of repeatedly implementing scraping logic, you deploy this one-time setup and call it whenever needed—it is especially useful for empowering AI Agents with up-to-date external knowledge retrieval. The underlying FireCrawl implementation, managed through a dedicated n8n node, handles complex rendering and extraction, delivering clean, reliable Markdown output. This modularity is a hallmark of efficient n8n automation design, making your main n8n workflow cleaner and dramatically easier to manage. This n8n workflow is a powerful component in any toolkit.

1. Execution Trigger: The n8n workflow begins with the Execute Workflow Trigger n8n node. This trigger is configured to be called by another active n8n workflow or an AI Agent request, anticipating input containing the target URL in the query.url field.


2. FireCrawl Request: The subsequent HTTP Request n8n node, configured for FireCrawl, handles the core scraping logic. It dynamically inserts the URL received from the initial n8n trigger into the request body and specifies that the resulting content must be formatted as structured Markdown.


3. Data Structuring: The n8n workflow uses an Edit Fields n8n node (Set node) to refine the FireCrawl response. It isolates the essential Markdown content ($json.data.markdown) and maps it to a simplified response field, ensuring the calling n8n workflow receives only the necessary, clean data.


4. Completion: The streamlined output is then returned instantly to the calling agent or parent n8n workflow, completing the extraction process provided by this n8n template.

1. Import this n8n workflow JSON file into your n8n instance.


2. Locate the FireCrawl n8n node (HTTP Request).


3. You must set up the required credential for FireCrawl. This is configured as 'HTTP Header Auth', where you provide a unique API key obtained from the FireCrawl service.


4. Save and Activate the n8n workflow. Once active, note the unique ID/endpoint of this n8n workflow; this is the target resource needed by the calling n8n node (such as an Execute Workflow or AI Agent Tool node) in your main automation.

Execute Workflow Trigger n8n trigger: Function: Acts as the designated entry point for external calls. Key Configuration: Used to receive the input object, expecting the URL under the query.url path.
FireCrawl (HTTP Request n8n node): Function: Executes the web scraping via the FireCrawl API. Key Configuration: Uses POST method; the JSON body dynamically pulls {{ $json.query.url }} from the trigger; requires a configured httpHeaderAuth credential; explicitly requests markdown format.

• Edit Fields (Set n8n node): Function: Transforms the complex API output into a simple, standardized structure before returning it. Key Configuration: Extracts $json.data.markdown and assigns the clean content to an output field named response for easy consumption by the primary n8n workflow.