This article provides a complete, practical walkthrough of the Limit Splitout Automation Webhook n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Intermediate setup in 15-45 minutes. One‑time purchase: €29.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:  
   Automating Trustpilot Review Scraping & Sentiment Analysis Using n8n, DeepSeek, and OpenAI
   
   Meta Description:  
   Learn how to use n8n, DeepSeek, and OpenAI to automatically scrape, extract, analyze, and store Trustpilot reviews with real-time sentiment insights. A powerful automation workflow for businesses tracking online reputation.
   
   Keywords:  
   n8n workflow, Trustpilot scraper, sentiment analysis, OpenAI, DeepSeek, Google Sheets automation, review monitoring, customer feedback analysis, trustpilot automation, AI sentiment analysis, scraping reviews n8n
   
   Third-Party APIs Used:
   
   - Trustpilot (unofficial, via HTML scraping)
   - DeepSeek (deepseek-reasoner, via LangChain integration)
   - OpenAI (for sentiment analysis with categories)
   - Google Sheets API (OAuth2 for saving and updating review data)
   
   Article:
   
   In today’s digital landscape, online reviews play a crucial role in shaping the public perception of brands and businesses. Trustpilot, being one of the top platforms for consumer reviews, is a goldmine of valuable user feedback. But manually tracking and analyzing those reviews can be labor-intensive—unless you automate the process.
   
   This article breaks down a powerful workflow built in n8n that does just that: scrape reviews from Trustpilot, extract meaningful data, analyze sentiment using DeepSeek and OpenAI, and store the insights neatly into Google Sheets.
   
   Let’s explore how this automation works and the key technologies driving it.
   
   1. Setting the Stage: Trigger and Parameters  
   The journey starts with a Manual Trigger node in n8n, allowing users to test and run the workflow as needed. Next, a Set node defines two critical variables: the Trustpilot company ID (e.g., domain name like example.com) and the number of pages to scrape (up to a defined limit, such as 2 pages).
   
   2. Scraping the Trustpilot Pages  
   Using the HTTP Request node, the automation sends requests to Trustpilot, fetching recent reviews sorted by recency. The HTML content is then passed through an HTML Extract node (using a CSS selector) to pull out the individual review links.
   
   To avoid overloading the system, the workflow only processes a limited number of reviews at once using the Limit node. Each review link is split out for individual processing via the Split Out node.
   
   3. Preventing Duplicates: The Lookup  
   Before extracting data from each review, the workflow performs a lookup into a connected Google Sheet. If the review has already been stored—based on its unique review ID extracted from the URL—it is skipped. This ensures that duplicate reviews are not processed.
   
   4. Extracting and Structuring Review Content  
   If a new review is found, the workflow uses the HTTP Request node again to fetch its full HTML.
   
   An HTML Extract node then isolates the raw HTML of the review content using a CSS selector targeting the article tag. This HTML block is passed into a LangChain-powered Information Extractor node using the DeepSeek Reasoner model as the engine.
   
   DeepSeek is configured with extraction rules to capture:
   
   - Author name  
   - Star rating (1–5)  
   - Review date  
   - Title and full text of the review  
   - Number of reviews the user has written  
   - Country of the reviewer (2-letter code)
   
   All this data is extracted in clean JSON format, ready for analysis and storage.
   
   5. Sentiment Analysis with OpenAI  
   With the review text extracted, the workflow now performs sentiment classification using OpenAI’s Chat Model. The review content is fed into an OpenAI-powered sentiment analyzer, which categorizes it as one of: “Positive”, “Neutral”, or “Negative”. This provides immediate insight into how customers feel about the brand.
   
   The prompt configuration instructs OpenAI to only return valid JSON responses, ensuring compatibility with downstream processing.
   
   6. Writing to Google Sheets  
   After sentiment is added to the extracted data, the results are either appended or updated in a Google Sheet. This sheet acts as a lightweight review database, storing fields such as:
   
   - Review ID  
   - Date  
   - Author  
   - Title and Text  
   - Country  
   - Number of previous reviews by user  
   - Star rating  
   - Sentiment classification  
   - URL to the Trustpilot review
   
   The appendOrUpdate mechanism in the Google Sheets node ensures real-time syncing without duplication.
   
   Why This Workflow Matters  
   This n8n automation is a prime example of how no-code/low-code platforms can revolutionize data collection and customer experience management.
   
   Whether you're in marketing, product support, or C-level decision-making, having up-to-date review sentiment data lets you:
   
   - Quickly address negative feedback  
   - Highlight glowing testimonials  
   - Track customer perception trends over time  
   - Benchmark performance against competitors  
   
   Flexible and Powerful  
   The modular structure of this workflow means it’s highly adaptable. You can change the number of reviews fetched, integrate with CRM systems, or trigger alerts when negative reviews are detected.
   
   Conclusion  
   By combining web scraping via HTML extraction with AI-driven LLMs and cloud-based spreadsheets, this n8n workflow removes friction in gathering and analyzing customer feedback.
   
   Whether you're just starting to monitor your reputation or want to boost the efficiency of your current tools, adopting automation could move the needle significantly.
   
   This workflow proves one thing clearly: with the right tools—n8n, OpenAI, DeepSeek, and Google Sheets—you can stay informed, responsive, and in control of your brand's online narrative.
   
   Ready to reclaim your time and automate review insights? Dive into workflow automation with n8n today.

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.