Skip to main content

Crawl websites & answer questions with GPT-5 nano and Google Sheets

Workflow preview

Workflow preview
100%
Crawl websites & answer questions with GPT-5 nano and Google Sheets preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Web Consultation & Crawling Chatbot with Google Sheets Memory Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to ...

Best for

  • Market Research automation workflows
  • Multimodal AI automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

@n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmchatopenai, @n8n/n8n-nodes-langchain.memorybufferwindow, n8n-nodes-base.googlesheetstool, n8n-nodes-base.if, n8n-nodes-base.httprequest, n8n-nodes-base.xml, n8n-nodes-base.code

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Oriol Seguí.

Original n8n.io source

1.1 Workflow description

Title
Crawl websites & answer questions with GPT-5 nano and Google Sheets
Workflow name
Crawl websites & answer questions with GPT-5 nano and Google Sheets

Web Consultation & Crawling Chatbot with Google Sheets Memory

Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to index a website and then interact with its content as if it were a chatbot. ⚠ Note: if the site contains many pages, AI token consumption can generate high costs, especially during the initial crawling and analysis phase.


1. Initial Mode (first use with a URL)

When the user enters a URL for the first time:

  1. URL validation using AI (gpt-5-nano).

  2. Automatic sitemap discovery via robots.txt.

  3. Relevant sitemap selection (pages, posts, categories, or tags) using GPT-4o according to configured options. (Includes “OPTIONS” node to precisely choose which types of URLs to process)

  4. Crawling of all selected pages:

    • Downloads HTML of each page.

    • Converts HTML to Markdown.

    • AI analysis to extract:

      • Detected language.
      • Heading hierarchy (H1, H2, etc.).
      • Internal and external links.
      • Content summary.
  5. Structured storage in Google Sheets:

    • Lang
    • H1 and hierarchy
    • External URLs
    • Internal URLs
    • Summary Content
    • Data schema (flag to enable agent mode)

When finished, the sheet is marked with Data schema = true, signaling that the site is indexed.


2. Agent Mode (subsequent queries)

If the URL has already been indexed (Data schema = true):

  1. The chat becomes a LangChain Agent that:

    • Reads the database in Google Sheets.
    • Can perform real-time HTTP requests if it needs updated information.
    • Responds as if it were the website, using stored and live data.

This allows the user to ask questions such as:

  • "What’s on the contact page?"
  • "How many external links are there on the homepage?"
  • "Give me all the H1 headings from the services pages"
  • "What CTA would you suggest for my page?"
  • "How would you expand X content?"

Use cases

  • Build a chatbot that answers questions about a website’s content.
  • Index and analyze full websites for future queries.
  • SEO tool to list headings, links, and content summaries.
  • Assistant for quick exploration of a site’s structure.
  • Generate improvement recommendations and content strategies from site data.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - AI Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2.2

Block 2 - OpenAI Chat Model

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 3 - Simple Memory

Type / Role
@n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices
Version 1.3

Block 4 - Get row(s) in sheet in Google Sheets

Type / Role
n8n-nodes-base.googleSheetsTool - googleSheetsTool
Config choices
Version 4.6

Block 5 - If

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.2

Block 6 - Maping Sitemap

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Block 7 - XML1

Type / Role
n8n-nodes-base.xml - xml
Config choices
Version 1

Block 8 - UA Rotativo1

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 9 - Req Error

Type / Role
n8n-nodes-base.stopAndError - stopAndError
Config choices
Version 1

Block 10 - Sitemap Error

Type / Role
n8n-nodes-base.stopAndError - stopAndError
Config choices
Version 1

Block 11 - Req robots

Type / Role
n8n-nodes-base.httpRequest - httpRequest
Config choices
Version 4.2

Block 12 - extract sitemap url

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 13 - OPTIONS

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 14 - AI Agent1

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 2.2

Block 15 - OpenAI Chat Model1

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 16 - Chat web

Type / Role
@n8n/n8n-nodes-langchain.chatTrigger - chatTrigger
Config choices
Version 1.3

Block 17 - Structured Output Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 18 - If1

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.2

Block 19 - Respond to Chat

Type / Role
@n8n/n8n-nodes-langchain.chat - chat
Config choices
Version 1

Block 20 - Respond to Chat1

Type / Role
@n8n/n8n-nodes-langchain.chat - chat
Config choices
Version 1

Block 21 - Message a model

Type / Role
@n8n/n8n-nodes-langchain.openAi - openAi
Config choices
Version 1.8

Block 22 - XML

Type / Role
n8n-nodes-base.xml - xml
Config choices
Version 1

Block 23 - Loop Over Items

Type / Role
n8n-nodes-base.splitInBatches - splitInBatches
Config choices
Version 3

Block 24 - Message a model1

Type / Role
@n8n/n8n-nodes-langchain.openAi - openAi
Config choices
Version 1.8

Showing the first 24 of 44 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Crawl websites & answer questions with GPT-5 nano and Google Sheets
Complexity advanced
Nodes 44
Categories Market Research, Multimodal AI
Author Oriol Seguí
Published 14 Aug 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/7368/7368.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Crawl websites & answer questions with GPT-5 nano and Google Sheets do?

Web Consultation & Crawling Chatbot with Google Sheets Memory Who is this workflow for? This workflow is designed for SEO analysts, content creators, marketing agencies, and developers who need to ...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Market Research, Multimodal AI use case.