Scrape Trustpilot reviews 📊 with ScrapegraphAI and OpenAI Reputation analysis

This workflow automates the collection, analysis, and reporting of Trustpilot reviews for a specific company using ScrapeGraphAI, transforming unstructured customer feedback into structured insights and actionable intelligence. --- Key Advantages 1. ✅ End-to-End Automation The entire process—from scraping reviews to delivering a polished management report—is fully automated, eliminating manual data collection and analysis . 2. ✅ Structured Insights from Unstructured Data The workflow transforms raw, unstructured review text into structured fields and standardized sentiment categories, making analysis reliable and repeatable. 3. ✅ Company-Level Reputation Intelligence Instead of focusing on individual products, the analysis evaluates the overall brand, service quality, customer experience, and operational performance, which is critical for leadership and strategic teams. 4. ✅ Action-Oriented Outputs The AI-generated report goes beyond summaries by: Identifying reputational risks Highlighting improvement opportunities Proposing concrete actions with priorities, effort estimates, and KPIs 5. ✅ Visual & Executive-Friendly Reporting Automatic sentiment charts and structured executive summaries make insights immediately understandable for non-technical stakeholders. 6. ✅ Scalable and Configurable Easily adaptable to different companies or review volumes Page limits and batching protect against rate limits and excessive API usage 7. ✅ Cross-Team Value The output is tailored for multiple internal teams: Management Marketing Customer Support Operations Product & UX --- Ideal Use Cases Brand reputation monitoring Voice-of-the-customer programs Executive reporting Customer experience optimization Competitive benchmarking (by reusing the workflow across brands) --- How It Works This workflow automates the complete process of scraping Trustpilot reviews, extracting structured data, analyzing sentiment, and generating comprehensive reports. The workflow follows this sequence: 1. Trigger & Configuration: The workflow starts with a manual trigger, allowing users to set the target company URL and the number of review pages to scrape. 2. Review Scraping: An HTTP request node fetches review pages from Trustpilot with pagination support, extracting review links from the HTML content. 3. Review Processing: The workflow processes individual review pages in batches (limited to 5 reviews per execution for efficiency). Each review page is converted to clean markdown using ScrapegraphAI. 4. Data Extraction: An information extractor using OpenAI's GPT-4.1-mini model parses the markdown to extract structured review data including author, rating, date, title, text, review count, and country. 5. Sentiment Analysis: Another OpenAI model performs sentiment classification on each review text, categorizing it as Positive, Neutral, or Negative. 6. Data Aggregation: Processed reviews are collected and compiled into a structured dataset. 7. Analytics & Visualization: - A pie chart is generated showing sentiment distribution - A comprehensive reputation analysis report is created using an AI agent that evaluates company-level insights, recurring themes, and provides actionable recommendations 8. Reporting & Delivery: The analysis is converted to HTML format and sent via email, providing stakeholders with immediate insights into customer feedback and company reputation. Set Up Steps To configure and run this workflow: 1. Credential Setup: - Configure OpenAI API credentials for the chat models and information extraction - Set up ScrapeGraphAI credentials for webpage-to-markdown conversion - Configure Gmail OAuth2 credentials for email notifications 2. Company Configuration: - In the "Set Parameters" node, update companyid to the target Trustpilot company URL - Adjust maxpage to control how many review pages to scrape 3. Review Processing Limits: - The "Limit" node restricts processing to 5 reviews per execution to manage API costs and processing time - Adjust this v