Website Content Analyzer and Google Sheets Storage with GPT-4 - n8n Workflow

SEO Specialists: Quickly analyze competitor websites for structure, keywords, and CTAs.
Market Researchers: Automate the gathering and summarization of industry news or resource pages.
Content Strategists: Generate concise summaries of long-form articles without manual reading.
n8n Developers: Users seeking a robust example of integrating web scraping, LLM processing, and database storage within one n8n template.

Manually analyzing website content and extracting key data points is time-consuming and prone to errors. This efficient n8n workflow eliminates that manual labor by combining web scraping capabilities with the analytical power of large language models (LLMs).

This specific n8n workflow is designed to fetch raw HTML, clean it up, and feed it directly into an OpenAI n8n node configured to act as a professional website analyst. The analyst role ensures the output is not just a summary, but a structured breakdown, identifying the site’s purpose, target audience, and ten key pieces of extracted information. The final step of this n8n automation is securely storing the generated insights into a dedicated Google Sheet, making the data instantly accessible for further review or reporting. Utilizing this pre-built n8n template saves significant time and maximizes the value of your collected data.

This comprehensive n8n workflow operates through a four-stage process, initiated by a simple n8n trigger.

1. Initiation and Scraping: The n8n automation starts with the 'Click to Start' manual n8n trigger. This immediately executes the 'Input Your Website URL' HTTP Request n8n node, which fetches the raw content (HTML) from the specified target URL (defaulting to a Medium article in the provided n8n template).


2. Data Preprocessing: The raw HTML output is messy and difficult for an LLM to process efficiently. The workflow uses the specialized 'Convert to Markdown Format' n8n node to strip out unnecessary formatting and convert the HTML into clean, readable Markdown text. This crucial step improves the quality and focus of the AI analysis.


3. AI Analysis (GPT-4): The cleaned Markdown content is passed to the 'Process the Markdown to readable Contents' OpenAI n8n node. This node uses a powerful system prompt instructing GPT-4 to act as a professional website analyst. It performs two specific tasks: generating a concise summary and extracting ten specific, actionable data points (like CTAs, contact info, etc.).


4. Storage: The final output—the structured summary and key extracted data—is automatically routed to the 'Save the Website Scraping content to Google Sheet' n8n node. This ensures the valuable analysis performed by the n8n workflow is logged instantly in a spreadsheet for organized data management.

To deploy this powerful n8n workflow and begin automating your content analysis, follow these setup steps:

1. Import the n8n Workflow: Copy the provided JSON data and paste it directly into your n8n instance via the 'New' menu and selecting 'Import from JSON'. This installs the complete n8n template.


2. Configure URL: In the 'Input Your Website URL' n8n node, change the default URL parameter to the specific website you wish to analyze.


3. Set Up OpenAI Credentials: Open the 'Process the Markdown to readable Contents' n8n node. Add or select your OpenAI API Key credential. Ensure the model ID is appropriate for your usage (this n8n template is configured for GPT-4 level models).


4. Set Up Google Sheets Credentials: Open the 'Save the Website Scraping content to Google Sheet' n8n node. Add or select your Google Sheets OAuth2 API credential.


5. Configure Google Sheet Destination: Within the same Google Sheets n8n node, specify the 'Document ID' of your target spreadsheet and the 'Sheet Name' where the analyzed data should be saved. Map the output fields from the OpenAI n8n node (e.g., the summary and extracted data) to the corresponding columns in your spreadsheet.

Click to Start (Manual Trigger): The initiating n8n trigger for running the analysis on demand.
Input Your Website URL (HTTP Request n8n node): Responsible for fetching the raw HTML content from the target URL. Crucially configured to return the response as a string, which is necessary for the next processing step.
Convert to Markdown Format (Markdown n8n node): A dedicated n8n node that cleanses the noisy HTML data into a focused Markdown format, making the data structure clearer and reducing token consumption in the subsequent AI analysis.
Process the Markdown to readable Contents (OpenAI Langchain n8n node): The core intelligence of the n8n workflow. It uses a custom system prompt to guide GPT-4 to perform deep analytical extraction, summarizing the website's purpose and isolating ten key data points from the content provided by the preceding n8n node.

• Save the Website Scraping content to Google Sheet (Google Sheets n8n node): The final action n8n node, configured to 'update' the sheet, saving the high-value AI analysis output in a structured, permanent record.