Brief

Overview

This is an automated product review data extraction workflow designed to collect and structure customer feedback from e-commerce platforms. The workflow navigates to product review pages, extracts key review data, and exports it in a structured format for analysis.

Use Cases

Market Research & Analysis

Competitor product sentiment analysis
Customer satisfaction tracking across products
Feature preference identification from user feedback

E-commerce Intelligence

Monitor product reputation and review trends
Identify common customer pain points
Track rating distribution patterns

Content & SEO Strategy

Gather authentic customer testimonials
Extract product benefits from real user experiences
Analyze review keywords for marketing insights

Quality Assurance

Identify recurring product issues from reviews
Track customer complaints and concerns
Monitor review sentiment over time

Workflow Steps

1. Start - Configuration

Input Parameters:

Product_Link: https://www.amazon.com/Hanes-Pullover-EcoSmart-Fleece-Hoodie/dp/B00JUM36R8/ref=zg_bs_c_fashion_d_sccl_4/146-1087718-7489941?pd_rd_w=6TZ5F&content-id=amzn1.sym.fef9af56-6177-46e9-8710-a5293a68dd39&pf_rd_p=fef9af56-6177-46e9-8710-a5293a68dd39&pf_rd_r=JNXJAATGG1DBHR9RZ46B&pd_rd_wg=pgqac&pd_rd_r=d64f6e43-d248-4ab8-80b2-024daa096705&pd_rd_i=B00JUM36R8&psc=1

Browser Settings:

Chrome browser (US region)

2. Visit Product Reviews Page

Navigates to the product review page using Product_Link
Error handling: Stop task on abnormal situations

3. Condition

Judgment conditions：Is there a continue shopping bottom？

4. Click Element（Child nodes of the judgment condition）

Click to continue shopping

5. Extract Data

Data Scope: Full page extraction

Extraction Logic:

Collect all review text → Summarize into "Summary" field
Extract ratings → Store in "Rating" field
Extract reviewer names → Store in "Name" field
Error handling: Stop task on failure

6. Finish: Output Data_1

Output Format: JSON

Optional: Save as file
Error handling: Stop task on abnormal situations

Part 2: Continue With n8n Automation

Browser Act workflows can be seamlessly integrated with n8n to create fully automated review analysis systems, making your work more efficient and actionable.

Automated Workflow Integration

Step 1: API Polling & Data Retrieval

Call Run API to initiate the BrowserAct workflow
Check execution status
Call Get API to retrieve results
Loop Logic: If data is incomplete or status is "unfinished", restart the loop after a delay
Ensures reliable data collection even for large scraping tasks

Step 2: AI-Powered Analysis

AI Agent processes the extracted review data
Connected components:
- Chat Model: OpenAI GPT for natural language analysis
- Memory: Maintains context across analysis sessions
- Tools: Telegram & Email integration

AI Analysis Prompt:

From the {{ $json.output.string }} you can see the reviews. 
It contains a list of maps like this:
[{
  "Name": "...",
  "Rating": "...",
  "Summary": "..."
}]

Read every single "Summary" item, analyze them, and generate 
improvement recommendations. Send these recommendations in text format.

Step 3: Multi-Channel Notification

Send Telegram Message: Instant notifications with analysis results
Send Email: Detailed recommendations and insights
Automatic distribution to stakeholders

Benefits of n8n Integration

✅ Fully Automated: Schedule reviews to run automatically (daily/weekly)
✅ AI-Enhanced Insights: Transform raw reviews into actionable recommendations
✅ Multi-Channel Alerts: Receive insights via Telegram and Email
✅ Error Handling: Automatic retry logic ensures data completeness
✅ Scalable: Handle large-scale review monitoring effortlessly

Core Function: Automated navigation → Bulk data extraction (reviews + ratings + names) → AI analysis → Structured recommendations → Multi-channel delivery

Need help? Contact us at

Discord: [Discord Community]
E-mail: service@browseract.com

20-50credits per task (estimated)