Extraction d'informations de produits à partir de captures d'écran de pages web avec Dumpling AI et GPT-4o
Intermédiaire
Ceci est unAI, Marketingworkflow d'automatisation du domainecontenant 11 nœuds.Utilise principalement des nœuds comme SplitOut, GoogleDrive, HttpRequest, GoogleSheets, OpenAi, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Extraire des informations de produits à partir de captures d'écran de pages web avec Dumpling AI et GPT-4o
Prérequis
- •Informations d'identification Google Drive API
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Informations d'identification Google Sheets API
- •Clé API OpenAI
Catégorie
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
"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": "Déclenchement sur nouvelle URL dans la feuille",
"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": "Capture d'écran pleine page avec Dumpling AI",
"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": "Extraire toutes les données visibles de la capture d'écran (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": "Télécharger le fichier de capture d'écran",
"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": "Sauvegarder la capture d'écran dans le dossier Drive",
"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": "Journaliser l'URL de la capture d'écran dans la feuille de calcul",
"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": "Extraire les informations produits du texte de capture d'écran avec GPT-4o",
"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": "Séparer chaque produit en enregistrement individuel",
"type": "n8n-nodes-base.splitOut",
"position": [
716,
-180
],
"parameters": {
"options": {},
"fieldToSplitOut": "message.content.products"
},
"typeVersion": 1
},
{
"id": "94b7e7bf-5b8f-431a-9020-ca39c409ce0d",
"name": "Sauvegarder les informations produits dans la feuille Google",
"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": "Note autocollante",
"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": "Note autocollante 1",
"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
}
]
]
}
}
}Foire aux questions
Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Intelligence Artificielle, Marketing
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Constructeur de bulletin d'actualités IA : Grâce à Dumpling AI pour scraper les sites, GPT-4o pour résumer
Constructeur de briefings d'actualités IA : Dumpling AI pour le scraping de sites, résumé par GPT-4o
Set
Code
Gmail
+
Set
Code
Gmail
10 NœudsYang
Intelligence Artificielle
Génération automatique de commentaires de presse IA avec Dumpling AI et GPT-4o
Utiliser Dumpling AI et GPT-4o pour générer automatiquement des commentaires d'actualités IA
Code
Wait
Split Out
+
Code
Wait
Split Out
14 NœudsYang
Intelligence Artificielle
Génération de titres en fonction des suggestions de saisie semi-automatique avec Dumpling AI + GPT-4o
Utiliser Dumpling AI + GPT-4o pour générer des titres à partir de suggestions de complétion automatique
Set
Split Out
Http Request
+
Set
Split Out
Http Request
8 NœudsYang
Design
Génération automatique de blogs et d'images IA à partir de vidéos YouTube avec Dumpling AI et GPT-4o
Utiliser Dumpling AI et GPT-4o pour générer automatiquement des articles de blog et des images IA à partir de vidéos YouTube
Airtable
Google Drive
Http Request
+
Airtable
Google Drive
Http Request
10 NœudsYang
Design
Extraction de prospects commerciaux de Google Maps et sauvegarde dans Google Sheets via Dumpling AI
Extraire les commerciaux de Google Maps vers Google Sheets avec Dumpling AI
Split Out
Http Request
Google Sheets
+
Split Out
Http Request
Google Sheets
5 NœudsYang
Ventes
Génération automatique de publications Facebook à partir d'analyses vidéo avec Dumpling AI + GPT-4o
Utiliser Dumpling AI + GPT-4o pour générer automatiquement des publications Facebook à partir des insights vidéo
Google Drive
Http Request
Google Sheets
+
Google Drive
Http Request
Google Sheets
8 NœudsYang
Intelligence Artificielle
Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds11
Catégorie2
Types de nœuds7
Description de la difficulté
Auteur
Yang
@yangLiens externes
Voir sur n8n.io →
Partager ce workflow