Produktinformationen aus Webseiten-Screenshots mit Dumpling AI und GPT-4o extrahieren

• •Google Drive API-Anmeldedaten
• •Möglicherweise sind Ziel-API-Anmeldedaten erforderlich
• •Google Sheets API-Anmeldedaten
• •OpenAI API Key

{
  "id": "D3YKQWTlFoSxj7lp",
  "meta": {
    "instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
    "templateCredsSetupCompleted": true
  },
  "name": "Extract Product Info from Webpage Screenshots using Dumpling AI and GPT-4o",
  "tags": [],
  "nodes": [
    {
      "id": "fd1389e6-1495-4226-a158-db98a2a5b1ab",
      "name": "Auslöser bei neuer URL in Tabelle",
      "type": "n8n-nodes-base.googleSheetsTrigger",
      "position": [
        -980,
        -180
      ],
      "parameters": {
        "event": "rowAdded",
        "options": {},
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit?usp=drivesdk",
          "cachedResultName": "Competitors"
        }
      },
      "credentials": {
        "googleSheetsTriggerOAuth2Api": {
          "id": "qDzHSzTkclwDHpSR",
          "name": "Google Sheets Trigger account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "0c6cf56f-8244-4131-96c0-2dee533c68d4",
      "name": "Vollständigen Seiten-Screenshot mit Dumpling AI erstellen",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -760,
        -180
      ],
      "parameters": {
        "url": "https://app.dumplingai.com/api/v1/screenshot",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"url\":\"{{ $json.URL }}\",\n  \"fullPage\": true\n}\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "RLFzAcGRepr5eXZB",
          "name": "n8n"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "aa6ba2a5-6d25-4ca7-afef-05b688bf630b",
      "name": "Alle sichtbaren Daten aus Screenshot extrahieren (Dumpling AI)",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -540,
        -180
      ],
      "parameters": {
        "url": "https://app.dumplingai.com/api/v1/extract-image",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"inputMethod\": \"url\",\n  \"images\": [\"{{ $json.screenshotUrl }}\"],\n  \"prompt\": \"You are a detail-oriented assistant. Analyze the screenshot provided and extract all visible information in a clear and organized way. Include all text content exactly as it appears, labels, buttons, icons, or form field names, any numbers, figures, or timestamps, section headers or groupings, notes or messages if any, and table data or list items if present. Present the result in a neatly structured format using plain text. Do not summarize, interpret, or skip anything. Maintain the original order and layout as much as possible for clarity.\"\n}\n\n",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "RLFzAcGRepr5eXZB",
          "name": "n8n"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "574a04b5-3b5a-4f7e-830a-de3cb580e355",
      "name": "Screenshot-Datei herunterladen",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -320,
        -180
      ],
      "parameters": {
        "url": "={{ $('Take Full-Page Screenshot using Dumpling AI').item.json.screenshotUrl }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "41a174e8-15e5-4c95-840d-8b6a99ac3539",
      "name": "Screenshot in Drive-Ordner speichern",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -100,
        -180
      ],
      "parameters": {
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive"
        },
        "options": {},
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1TT91LtI3ods32838DMggLM8v397DTWIH",
          "cachedResultName": "Webpage-Screenshoot"
        }
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "B0Hulh0j065xznhI",
          "name": "Google Drive account 2"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "fcd1c828-0704-4d74-87f0-601320ec1740",
      "name": "Screenshot-URL in Tabellenkalkulation protokollieren",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        120,
        -180
      ],
      "parameters": {
        "columns": {
          "value": {
            "URL": "={{ $('Trigger on New URL in Sheet').item.json.URL }}",
            "screenshoot URL": "={{ $('Take Full-Page Screenshot using Dumpling AI').item.json.screenshotUrl }}"
          },
          "schema": [
            {
              "id": "URL",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "URL",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "screenshoot URL",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "screenshoot URL",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Summary of the webpage",
              "type": "string",
              "display": true,
              "removed": true,
              "required": false,
              "displayName": "Summary of the webpage",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "URL"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "appendOrUpdate",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit#gid=0",
          "cachedResultName": "Sheet1"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit?usp=drivesdk",
          "cachedResultName": "Competitors"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "GaJqJHuS5mQxap7q",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "b8d6b452-be2d-41e2-aa67-911131ad66c5",
      "name": "Produktinformationen aus Screenshot-Text mit GPT-4o extrahieren",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        340,
        -180
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o",
          "cachedResultName": "GPT-4O"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "=Extract only the product-related information from the text. For each product, return a JSON object with the following fields: \"name\", \"ratings\", \"purchased\", \"price\", \"deal\", \"delivery\", \"buyingOptions\", \"colorOptions\", and \"badges\". Include only the available fields for each product. If a field is not mentioned for a product, skip it. Ignore unrelated content like navigation, help, or footer sections. Return the final output as a JSON object with a top-level \"products\" array containing the structured results.\n\nExample JSON output:\n{\n  \"products\": [\n    {\n      \"name\": \"JBL Tune 510BT - Bluetooth headphones with up to 40 hours battery, microphone for call, foldable and comfortable\",\n      \"ratings\": \"76,254\",\n      \"purchased\": \"100K+ bought in past month\",\n      \"price\": \"$49.95\",\n      \"delivery\": \"FREE delivery Tue, May 27\",\n      \"deal\": \"Free 30 day Amazon music with purchase\",\n      \"buyingOptions\": \"$25.87 (2+ used & new offers)\",\n      \"colorOptions\": [\"Black\", \"Blue\", \"White\", \"Purple\"]\n    },\n    {\n      \"name\": \"Beats Studio Pro - Wireless Bluetooth Noise Cancelling Headphones\",\n      \"ratings\": \"20,437\",\n      \"purchased\": \"10K+ bought in past month\",\n      \"price\": \"$199.95\",\n      \"deal\": \"List: $349.95\",\n      \"delivery\": \"FREE delivery Tue, May 27\",\n      \"buyingOptions\": \"$146.65 (5+ used & new offers)\"\n    }\n  \n  ]\n}"
            },
            {
              "content": "=Here is the text: {{ $('Extract All Visible Data from Screenshot (Dumpling AI)').item.json.results }}"
            }
          ]
        },
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "id": "fdhWALG84tBLgSZT",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "2c390314-9d9c-464d-a80b-b8c1e12bb671",
      "name": "Jedes Produkt in einzelnen Datensatz aufteilen",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        716,
        -180
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "message.content.products"
      },
      "typeVersion": 1
    },
    {
      "id": "94b7e7bf-5b8f-431a-9020-ca39c409ce0d",
      "name": "Produktinformationen in Google-Tabelle speichern",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        936,
        -180
      ],
      "parameters": {
        "columns": {
          "value": {
            "deal": "={{ $json.deal }}",
            "price": "={{ $json.price }}",
            "ratings": "={{ $json.ratings }}",
            "purchased": "={{ $json.purchased }}",
            "Product Name": "={{ $json.name }}",
            "buyingOptions": "={{ $json.buyingOptions }}"
          },
          "schema": [
            {
              "id": "Product Name",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Product Name",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "price",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "price",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "purchased",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "purchased",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "ratings",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "ratings",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "deal",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "deal",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "buyingOptions",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "buyingOptions",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit#gid=641974727",
          "cachedResultName": "Sheet2"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1TDp408j9W1D8DF21XI5WrpeIA56qWjLBRlmWXqgo0p4/edit?usp=drivesdk",
          "cachedResultName": "Competitors"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "GaJqJHuS5mQxap7q",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "df27aa1a-1cbe-4913-90d1-09ac5a484677",
      "name": "Haftnotiz",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -960,
        -360
      ],
      "parameters": {
        "width": 1000,
        "height": 220,
        "content": "### 📸 Automate Screenshot Capture & Text Extraction\n\nThis first part of the workflow begins by monitoring a Google Sheet for new URLs. When a new row is added, Dumpling AI captures a full-page screenshot of the given URL. Then, Dumpling AI’s extract-image endpoint pulls all visible text and UI elements from the screenshot. The file is downloaded and saved in Google Drive for future reference. A separate log of the screenshot URL is written back to the original spreadsheet.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "657a7360-b9d1-40c5-93a5-be032c22de88",
      "name": "Haftnotiz1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        80,
        -360
      ],
      "parameters": {
        "width": 960,
        "height": 220,
        "content": "### 🛍️ Extract and Store Product Listings with GPT-4o\n\nAfter saving the screenshot, GPT-4o receives the extracted text and processes it to identify structured product details like name, price, rating, purchase volume, deals, and buying options. Each product is split into an individual record using a Split Out node. Finally, each product is appended to a different sheet for structured logging and analysis.\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "991d7669-24c9-40b5-b921-07c63f9778c0",
  "connections": {
    "574a04b5-3b5a-4f7e-830a-de3cb580e355": {
      "main": [
        [
          {
            "node": "41a174e8-15e5-4c95-840d-8b6a99ac3539",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "fd1389e6-1495-4226-a158-db98a2a5b1ab": {
      "main": [
        [
          {
            "node": "0c6cf56f-8244-4131-96c0-2dee533c68d4",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "41a174e8-15e5-4c95-840d-8b6a99ac3539": {
      "main": [
        [
          {
            "node": "fcd1c828-0704-4d74-87f0-601320ec1740",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "fcd1c828-0704-4d74-87f0-601320ec1740": {
      "main": [
        [
          {
            "node": "b8d6b452-be2d-41e2-aa67-911131ad66c5",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "2c390314-9d9c-464d-a80b-b8c1e12bb671": {
      "main": [
        [
          {
            "node": "94b7e7bf-5b8f-431a-9020-ca39c409ce0d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "0c6cf56f-8244-4131-96c0-2dee533c68d4": {
      "main": [
        [
          {
            "node": "aa6ba2a5-6d25-4ca7-afef-05b688bf630b",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "b8d6b452-be2d-41e2-aa67-911131ad66c5": {
      "main": [
        [
          {
            "node": "2c390314-9d9c-464d-a80b-b8c1e12bb671",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "aa6ba2a5-6d25-4ca7-afef-05b688bf630b": {
      "main": [
        [
          {
            "node": "574a04b5-3b5a-4f7e-830a-de3cb580e355",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}