7 scrape reviews from trustpilot

{
  "id": "7xkEgEP44GHwgc2N",
  "meta": {
    "instanceId": "c38e3b8a7e4240e6cdca062743f016c1029f385bf40345b6291939dfd83bfd77",
    "templateCredsSetupCompleted": true
  },
  "name": "7  scrape reviews from trustpilot",
  "tags": [],
  "nodes": [
    {
      "id": "a15211f7-505b-4f2a-ba53-c029f2e9b54a",
      "name": "Set Trustpilot company URL",
      "type": "n8n-nodes-base.set",
      "position": [
        -60,
        -140
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "2cf9cb42-883e-40da-9785-47755c9c6e9a",
              "name": "URL",
              "type": "string",
              "value": "https://www.trustpilot.com/review/hubspot.com"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "65afe387-1264-4e71-8308-00f9c7229806",
      "name": "Manual Start",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -220,
        -140
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "a8b8737b-592e-4b0f-abd5-844f8c0213ea",
      "name": "Agent : Fetch and analyze reviews",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        220,
        -140
      ],
      "parameters": {
        "text": "=`You are a web scraper connected to Bright Data's MCP tool using the scrape_as_markdown function.\n\nScrape the latest 5 reviews from the Trustpilot company page at this URL:\n{{ $json.URL }}\n\nUse the scrape_as_markdown tool with these parameters:\n{\n  \"url\": {{ $json.URL }},\n  \"max_items\": 5\n}\n\nAfter scraping, analyze each review and return a JSON array of 5 objects with these fields:\n\n- reviewer (string)\n- date (string)\n- rating (number)\n- sentiment (one of \"positive\", \"neutral\", or \"negative\")\n- mainIssue (string — summarize complaint or praise)\n- reviewText (string)\n\nReturn only valid JSON.\n`\n",
        "options": {},
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 2
    },
    {
      "id": "1d8b112c-7917-4f61-8b6e-3d6d98ce1947",
      "name": "Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        160,
        120
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "kmqnyfHdWfA8k1KC",
          "name": "OpenAi account 3"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "eb5f2d9a-aed9-48a1-ad61-7903b333314c",
      "name": "Bright Data MCP Scrapper",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        300,
        100
      ],
      "parameters": {
        "toolName": "scrape_as_markdown",
        "operation": "executeTool",
        "toolParameters": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Tool_Parameters', ``, 'json') }}"
      },
      "credentials": {
        "mcpClientApi": {
          "id": "dGu6Ys11ijXSTxcV",
          "name": "MCP Client (STDIO) account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "4c2639af-44c4-4579-beaa-cff5a9b50ae1",
      "name": "Splits Reviews into separate Objects",
      "type": "n8n-nodes-base.code",
      "position": [
        640,
        -140
      ],
      "parameters": {
        "jsCode": "// Access the first item in the input (AI Agent output)\nconst outputArray = $('Agent : Fetch and analyze reviews').first().json.output;\n\n// Map each review to a separate item (with `.json` wrapping)\nreturn outputArray.map(review => ({ json: review }));\n\n"
      },
      "typeVersion": 2,
      "alwaysOutputData": true
    },
    {
      "id": "1e4f0309-ac91-4ad7-836c-552b291db2e6",
      "name": "Save Reviews to Google Sheets",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        860,
        -140
      ],
      "parameters": {
        "columns": {
          "value": {
            "date ": "={{ $json.date }}",
            "rating": "={{ $json.rating }}",
            "reviewer": "={{ $json.reviewer }}",
            "mainIssue ": "={{ $json.mainIssue }}",
            "reviewText": "={{ $json.reviewText }}",
            "sentiment ": "={{ $json.sentiment }}"
          },
          "schema": [
            {
              "id": "reviewer",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "reviewer",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "date ",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "date ",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "rating",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "rating",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "sentiment ",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "sentiment ",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "mainIssue ",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "mainIssue ",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "reviewText",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "reviewText",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1dlaEmLIzSgTxH0whWJnx51lPHyb34bGxMSQig5KI7CQ/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1dlaEmLIzSgTxH0whWJnx51lPHyb34bGxMSQig5KI7CQ",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1dlaEmLIzSgTxH0whWJnx51lPHyb34bGxMSQig5KI7CQ/edit?usp=drivesdk",
          "cachedResultName": "scraped reviews from trustpilot"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "i899RBJ6SKiYYWwx",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.6
    },
    {
      "id": "8d3de4f3-b17e-4607-a4d2-75e2bb3dafb8",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -240,
        -440
      ],
      "parameters": {
        "color": 3,
        "width": 340,
        "height": 480,
        "content": "🔹 SECTION 1: 🚦 Start & Input Company URL\n🧩 Includes Nodes:\n\n🔘 Trigger: Manual Start\n\n🏢 Set Company Profile URL\n\n👣 What It Does:\nThis is your starting point. You manually click \"Execute workflow\" in n8n to begin the automation. The second node takes the company’s Trustpilot URL as input — this tells the AI agent which business page to scrape reviews from."
      },
      "typeVersion": 1
    },
    {
      "id": "157a1838-08dd-4866-a770-14d9c91c52c9",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        160,
        -820
      ],
      "parameters": {
        "color": 5,
        "width": 400,
        "height": 880,
        "content": "🤖 SECTION 2: 🧠 AI Agent – Scrape, Analyze & Summarize Trustpilot Reviews\n🧩 Includes Nodes:\n\n🤖 Agent: Fetch & Analyze Reviews\n\n🧠 Chat Model (AI Reasoning)\n\n🌐 Bright Data MCP Client\n\n🧾 JSON Review Formatter\n\nHere’s what happens step-by-step:\n\n🧠 The AI reads the Trustpilot company URL that you set earlier.\n\n🌐 The Bright Data MCP tool visits the company’s Trustpilot page using real mobile proxies to safely and accurately scrape the 5 most recent customer reviews.\n\n🧠 The AI then performs multiple tasks:\n\n📖 Reads each review and extracts the reviewer’s name, rating, and date.\n\n❤️ Performs sentiment analysis (Is the review positive, negative, or neutral?).\n\n🔁 Identifies recurring topics across reviews (e.g. “late delivery”, “amazing support”).\n\n🧵 Summarizes the main customer concern or praise in 1-2 lines.\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "30970761-128a-4f35-86ca-ace27105edfd",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        600,
        -680
      ],
      "parameters": {
        "color": 6,
        "width": 420,
        "height": 740,
        "content": "📊 SECTION 3: 📦 Split Reviews & 📥 Save to Google Sheets\n🧩 Includes Nodes:\n\n🔍 Function: Split Reviews into Objects\n\n📥 Google Sheets: Append Reviews\n\nHere’s how it works:\n🔍 The Function node (Split Reviews into Objects) receives the JSON array of all 5 reviews from the AI agent.\n👉 It loops through the array and separates each review into its own distinct object.\n\nThis ensures:\n\nEach review has its own data record\n\nClean and structured data per review\n\nCompatibility with downstream systems like spreadsheets, CRMs, or dashboards\n\n📥 The Google Sheets node receives these separate review objects and writes them to your Google Sheet, one row per review.\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "afd73d97-fb10-4c7a-bb8c-7cc9cdcfc379",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1900,
        -560
      ],
      "parameters": {
        "color": 4,
        "width": 1300,
        "height": 1820,
        "content": "    Analyze Review Site Sentiment\n\n✨ Built in n8n | AI-Powered | No-Code Automation\n\n🚀 Workflow Overview\nThis workflow automates the process of retrieving, analyzing, summarizing, and saving customer reviews from any Trustpilot company page. It enables you to extract key insights from real users without manual effort or coding.\n\n🛠️ Tools Used:\n\nn8n (No-code automation builder)\n\nBright Data MCP (Mobile proxy scraper)\n\nOpenAI (for AI-powered reasoning and sentiment analysis)\n\nGoogle Sheets (for storing the results)\n\n🧩 Workflow Sections\n🔹 SECTION 1: 🟢 Start & Input Company URL\n🧩 Nodes:\n\n🔘 Manual Start\n\n🏢 Set Trustpilot Company URL\n\n🎯 Description:\nThis section allows the user to trigger the workflow manually and provide a specific Trustpilot company profile URL as input.\n\n📌 Key Benefits:\n\nSimple to use — just paste the company URL\n\nReusable for any business\n\nNo backend modifications required to target a new company\n\n🤖 SECTION 2: 🧠 AI Agent — Scrape, Analyze & Summarize\n🧩 Nodes:\n\n🤖 Agent: Fetch and Analyze Reviews\n\n🧠 Chat Model (AI Reasoning)\n\n🌐 Bright Data MCP Scraper (executeTool)\n\n🧾 JSON Review Formatter (Output Parser)\n\n🎯 Description:\nThis is the intelligence core of the workflow. It uses the AI agent and Bright Data proxy tool to:\n\nAccess the Trustpilot page and scrape the 5 most recent customer reviews\n\nAnalyze each review for sentiment (positive, neutral, or negative)\n\nIdentify recurring topics or issues mentioned in reviews\n\nGenerate a brief summary representing the general customer sentiment\n\n📌 Key Benefits:\n\nNo scraping scripts required\n\nIntelligent insight extraction\n\nWorks reliably using real mobile IPs (bypasses protection)\n\n📊 SECTION 3: 🔍 Split Reviews & 📥 Save to Google Sheets\n🧩 Nodes:\n\n🔍 Splits Reviews into Separate Objects\n\n📄 Save Reviews to Google Sheets\n\n🎯 Description:\nThis section structures and stores the data. After the AI returns reviews in array format, the function node splits them into separate objects. Each review is then stored as an individual row in Google Sheets.\n\n📌 Key Benefits:\n\nClean, row-by-row storage for easy review\n\nCompatible with reporting and dashboard tools\n\nMaintains historical record of customer feedback\n\n✅ Workflow Summary\nSection\tWhat It Does\n1️⃣ Input\tAllows user to manually trigger and set company URL\n2️⃣ AI Agent\tScrapes, analyzes, identifies themes, and summarizes data\n3️⃣ Output\tSplits and saves review data to a structured spreadsheet"
      },
      "typeVersion": 1
    },
    {
      "id": "55a5aa8e-c5e5-443d-b71a-4dc2ae3438bb",
      "name": "Sticky Note9",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1900,
        -900
      ],
      "parameters": {
        "color": 4,
        "width": 1300,
        "height": 320,
        "content": "=======================================\n            WORKFLOW ASSISTANCE\n=======================================\nFor any questions or support, please contact:\n    [email protected]\n\nExplore more tips and tutorials here:\n   - YouTube: https://www.youtube.com/@YaronBeen/videos\n   - LinkedIn: https://www.linkedin.com/in/yaronbeen/\n=======================================\n"
      },
      "typeVersion": 1
    },
    {
      "id": "bff313ed-572b-47ec-bdb3-4299bc78bfb5",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1060,
        -680
      ],
      "parameters": {
        "color": 7,
        "width": 380,
        "height": 240,
        "content": "## I’ll receive a tiny commission if you join Bright Data through this link—thanks for fueling more free content!\n\n### https://get.brightdata.com/1tndi4600b25"
      },
      "typeVersion": 1
    },
    {
      "id": "4640997a-7f82-4d97-bf1d-60f063038c0d",
      "name": "Auto-fixing Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserAutofixing",
      "position": [
        420,
        120
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "784fad38-2ad5-4e31-b6ea-e594a3da6bba",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        420,
        320
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "kmqnyfHdWfA8k1KC",
          "name": "OpenAi account 3"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "17616722-c86c-4741-a1ea-2e30cc2ff420",
      "name": "Structured Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        580,
        320
      ],
      "parameters": {
        "schemaType": "manual",
        "inputSchema": "{\n  \"type\": \"array\",\n  \"items\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"reviewer\": { \"type\": \"string\" },\n      \"date\": { \"type\": \"string\" },\n      \"rating\": { \"type\": \"number\" },\n      \"sentiment\": {\n        \"type\": \"string\",\n        \"enum\": [\"positive\", \"neutral\", \"negative\"]\n      },\n      \"mainIssue\": { \"type\": \"string\" },\n      \"reviewText\": { \"type\": \"string\" }\n    },\n    \"required\": [\"reviewer\", \"date\", \"rating\", \"sentiment\", \"mainIssue\", \"reviewText\"]\n  }\n}"
      },
      "typeVersion": 1.3
    }
  ],
  "active": false,
  "pinData": {
    "Manual Start": [
      {
        "json": {}
      }
    ]
  },
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "cc92153a-30c0-4c8b-9c09-8196a98935ee",
  "connections": {
    "Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Agent : Fetch and analyze reviews",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Manual Start": {
      "main": [
        [
          {
            "node": "Set Trustpilot company URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Auto-fixing Output Parser",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Bright Data MCP Scrapper": {
      "ai_tool": [
        [
          {
            "node": "Agent : Fetch and analyze reviews",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Structured Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Auto-fixing Output Parser",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Auto-fixing Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Agent : Fetch and analyze reviews",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Set Trustpilot company URL": {
      "main": [
        [
          {
            "node": "Agent : Fetch and analyze reviews",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Agent : Fetch and analyze reviews": {
      "main": [
        [
          {
            "node": "Splits Reviews into separate Objects",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Splits Reviews into separate Objects": {
      "main": [
        [
          {
            "node": "Save Reviews to Google Sheets",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}