Automatisation Google Sheets avec n8n : gestion de captures d'écran
Ce workflow n8n a pour objectif d'automatiser la gestion des captures d'écran de pages web et leur intégration dans Google Sheets. Il s'adresse aux équipes marketing et aux entreprises qui souhaitent améliorer leur suivi visuel des contenus en ligne. Grâce à cette automatisation n8n, vous pouvez facilement récupérer des URLs, prendre des captures d'écran, et les stocker dans Google Drive tout en mettant à jour vos feuilles de calcul. Le processus commence par un déclencheur programmé qui récupère la liste des pages web à surveiller depuis Google Sheets. Ensuite, chaque URL est traitée pour prendre une capture d'écran via une requête HTTP. Les captures d'écran sont ensuite téléchargées et stockées dans Google Drive. Si des modifications sont détectées, le workflow met à jour les images de base dans Google Sheets. Ce système permet non seulement de gagner du temps, mais aussi de réduire les erreurs humaines liées à la gestion manuelle des images. En intégrant cette solution, les entreprises peuvent améliorer leur efficacité opérationnelle et garantir une documentation visuelle à jour de leurs contenus en ligne.
Workflow n8n Google Sheets, captures d'écran : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n Google Sheets, captures d'écran : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"meta": {
"instanceId": "408f9fb9940c3cb18ffdef0e0150fe342d6e655c3a9fac21f0f644e8bedabcd9"
},
"nodes": [
{
"id": "cb62c9a5-2f43-4328-af94-84c2cb731d9c",
"name": "Base Image",
"type": "n8n-nodes-base.googleDrive",
"position": [
260,
660
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.base }}"
},
"options": {
"binaryPropertyName": "data_1"
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "yOwz41gMQclOadgu",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "b1c304cc-9949-441a-ac2a-275c8d4c51fc",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1120,
900
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-pro-latest"
},
"credentials": {
"googlePalmApi": {
"id": "dSxo6ns5wn658r8N",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "964d94bf-be2a-424e-ab0e-c1c1fe260ebd",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1320,
900
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n\t\"properties\": {\n\t\t\"type\": {\n \t\t\"type\": \"string\",\n \"description\": \"type of regression. One of text, number, image, color or position.\"\n \t\t},\n\t\t\"description\": { \"type\": \"string\" },\n \"previous_state\": { \"type\": \"string\" },\n \"current_state\": { \"type\": \"string\" }\n\t}\n }\n}"
},
"typeVersion": 1.2
},
{
"id": "67195eb2-1729-42b0-8275-bdd6128b81aa",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2340,
20
],
"parameters": {
"color": 4,
"width": 405.95003875719203,
"height": 180.74812634463558,
"content": "### Part A. Generate Base Images\nBefore we can run our visual regression tests, we must generate a series of base screenshots to compare against. This part of the workflow uses an external website screenshotting service, [Apify.com](https://www.apify.com?fpr=414q6), to achieve this. This part of the workflow should only be run when we want to update our base screenshots."
},
"typeVersion": 1
},
{
"id": "85f9b371-1710-4c9c-a0ed-210d9c0e5d64",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
162.7495769165307,
500
],
"parameters": {
"color": 7,
"width": 702.1744987652204,
"height": 548.4621171664835,
"content": "## 5. Download Base and Generate new Webpage Screenshot\n[Learn more about Apify.com](https://www.apify.com?fpr=414q6)\n\nLooping for each webpage, we'll do 2 tasks (1) download the base screenshot for the url and (2) and use our [Apify.com](https://www.apify.com?fpr=414q6) webpage screenshot actor again to generate a fresh screenshot."
},
"typeVersion": 1
},
{
"id": "8bff4efc-d9f9-485c-b51d-a8edc29d1105",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
900,
500
],
"parameters": {
"color": 7,
"width": 759.5372282495247,
"height": 548.702446115556,
"content": "## 6. Compare Screenshots using Vision Model\n[Read more about the basic LLM chain](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n\nTo carry out our visual regression test, we need to send both screenshots simultaneously to our Vision model. This is easily achieved using n8n's built-in basic LLM chain where we can define two user messages of the binary type. For our vision model, we'll use Google's Gemini but any capable vision model will also do the job. A Structured Output Parser is used here to return the AI's response in JSON format, this is for easier formatting purposes which we'll get to in the next step."
},
"typeVersion": 1
},
{
"id": "a92d11e5-0985-4a8f-bc43-8bc0ca48e744",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
397.518987341772,
93.8157360237642
],
"parameters": {
"color": 7,
"width": 885.2402868841493,
"height": 388.92815062755926,
"content": "## 7. Create Report In Linear\n[Learn more about integrating with Linear.app](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.linear)\n\nFor the final step, we'll generate a simple report which will capture any changes detected in our webpages list. Let's do this by first combining our webpages with their test results and filter out any in the page where no changes were detected. Next, we'll aggregate all changes into the Linear.app node which will be formatted into a markdown snippet and used to create a new issue in Linear. If you don't use Linear, feel free to swap this out for JIRA or even Slack."
},
"typeVersion": 1
},
{
"id": "3f52c006-6c0a-456d-ab3c-ee5a16726299",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-1680,
580
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "478ee25d-3f0f-4f6c-bf34-add1dc14c3cb",
"name": "Wait",
"type": "n8n-nodes-base.wait",
"position": [
-1240,
820
],
"webhookId": "f06eab66-30a7-48ad-90ee-cb3394eb2edb",
"parameters": {
"amount": 2
},
"typeVersion": 1.1
},
{
"id": "64b5f755-a85e-4ae5-ad81-113c1ef9b64c",
"name": "Download Screenshot",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1260,
360
],
"parameters": {
"url": "={{ $json.screenshotUrl }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "8f99ef1f-1cdc-4d80-b858-e9960a805dd4",
"name": "Upload to Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
-1080,
360
],
"parameters": {
"name": "={{ $('Merge').item.json.url.urlEncode() }}",
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive"
},
"options": {
"simplifyOutput": true
},
"folderId": {
"__rl": true,
"mode": "list",
"value": "1lAFxJPWcA_sOcjr3UUKKfFfoTwd4Stkh",
"cachedResultUrl": "https://drive.google.com/drive/folders/1lAFxJPWcA_sOcjr3UUKKfFfoTwd4Stkh",
"cachedResultName": "base_images"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"id": "yOwz41gMQclOadgu",
"name": "Google Drive account"
}
},
"typeVersion": 3
},
{
"id": "5e253123-89ba-42d5-b743-60bfd1ebae5b",
"name": "Update Base Image",
"type": "n8n-nodes-base.googleSheets",
"position": [
-900,
360
],
"parameters": {
"columns": {
"value": {
"url": "={{ $('Merge').item.json.url }}",
"base": "={{ $json.id }}"
},
"schema": [
{
"id": "service",
"type": "string",
"display": true,
"required": false,
"displayName": "service",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "url",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "base",
"type": "string",
"display": true,
"required": false,
"displayName": "base",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"url"
]
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit?usp=drivesdk",
"cachedResultName": "Visual Regression List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "XHvC7jIRR8A2TlUl",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "fa7339b7-b7dd-4ecd-8dc2-f42f6549adb6",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
-1440,
360
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "47845df9-a50e-429e-b81e-5eefd996d5c7",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-560,
380
],
"parameters": {
"rule": {
"interval": [
{
"field": "weeks",
"triggerAtDay": [
1
],
"triggerAtHour": 6
}
]
}
},
"typeVersion": 1.2
},
{
"id": "63492aa4-3535-4832-a9d0-0a949e46ec81",
"name": "Get URLs with Missing Base Images",
"type": "n8n-nodes-base.googleSheets",
"position": [
-1980,
480
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit?usp=drivesdk",
"cachedResultName": "Visual Regression List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "XHvC7jIRR8A2TlUl",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "8907f3b9-0613-4057-8adb-fd5c4e25cf72",
"name": "Run Webpage Screenshot",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1420,
820
],
"parameters": {
"url": "https://api.apify.com/v2/acts/apify~screenshot-url/run-sync-get-dataset-items",
"method": "POST",
"options": {},
"jsonBody": "={{\n{\n \"delay\": 0,\n \"format\": \"png\",\n \"proxy\": {\n \"useApifyProxy\": true\n },\n \"scrollToBottom\": false,\n \"urls\": [\n {\n \"url\": $json.url\n }\n ],\n \"viewportWidth\": 1280,\n \"waitUntil\": \"domcontentloaded\",\n \"waitUntilNetworkIdleAfterScroll\": false\n}\n}}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth"
},
"credentials": {
"httpQueryAuth": {
"id": "cO2w8RDNOZg8DRa8",
"name": "Apify API"
}
},
"typeVersion": 4.2
},
{
"id": "3dc45b2d-4c4a-44d5-9b45-3e2144479603",
"name": "Run Webpage Screenshot1",
"type": "n8n-nodes-base.httpRequest",
"position": [
273,
833
],
"parameters": {
"url": "https://api.apify.com/v2/acts/apify~screenshot-url/run-sync-get-dataset-items",
"method": "POST",
"options": {},
"jsonBody": "={{\n{\n \"delay\": 0,\n \"format\": \"png\",\n \"proxy\": {\n \"useApifyProxy\": true\n },\n \"scrollToBottom\": false,\n \"urls\": [\n {\n \"url\": $json.url\n }\n ],\n \"viewportWidth\": 1280,\n \"waitUntil\": \"domcontentloaded\",\n \"waitUntilNetworkIdleAfterScroll\": false\n}\n}}",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth"
},
"credentials": {
"httpQueryAuth": {
"id": "cO2w8RDNOZg8DRa8",
"name": "Apify API"
}
},
"typeVersion": 4.2
},
{
"id": "672d64fb-7782-427e-8779-953e51118fbc",
"name": "Has Changes",
"type": "n8n-nodes-base.filter",
"position": [
680,
300
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "20b18a7e-bf98-4f39-baa9-4d965097526a",
"operator": {
"type": "array",
"operation": "lengthGt",
"rightType": "number"
},
"leftValue": "={{ $json.output }}",
"rightValue": 0
}
]
}
},
"typeVersion": 2.2
},
{
"id": "efa168ec-ff05-471b-869f-cee5a222594a",
"name": "Combine Row and Result",
"type": "n8n-nodes-base.set",
"position": [
500,
300
],
"parameters": {
"mode": "raw",
"options": {},
"jsonOutput": "={{\n{\n ...$('Get Webpages List').item.json,\n output: $json.output\n}\n}}\n"
},
"typeVersion": 3.4
},
{
"id": "1fe901dc-f460-41b8-8042-0fcb0474092f",
"name": "Wait1",
"type": "n8n-nodes-base.wait",
"position": [
1580,
900
],
"webhookId": "6bbf2e65-bed1-4efc-bb31-09d12c644dc5",
"parameters": {
"amount": 1
},
"typeVersion": 1.1
},
{
"id": "7891f052-4073-4746-a04b-27c7c4fa1e63",
"name": "Aggregate",
"type": "n8n-nodes-base.aggregate",
"position": [
860,
300
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "ef2b2ddb-51f9-4576-bd99-9efa39be5163",
"name": "Create Report",
"type": "n8n-nodes-base.linear",
"position": [
1040,
300
],
"parameters": {
"title": "=Visual Regression Report {{ $now.format('yyyy-MM-dd') }}",
"teamId": "1c721608-321d-4132-ac32-6e92d04bb487",
"additionalFields": {
"description": "=Visual Regression Workflow picked up the following changes:\n\n{{\n$json.data.map(row =>\n`### ${row.url}\n${row.output.map(issue =>\n`* **${issue.description}** - expected \"${issue.previous_state}\" but got \"${issue.current_state}\"`\n).join('\\n')}`\n).join('\\n');\n}}"
}
},
"credentials": {
"linearApi": {
"id": "Nn0F7T9FtvRUtEbe",
"name": "Linear account"
}
},
"typeVersion": 1
},
{
"id": "477b89f7-00ca-4001-a246-0887bcb553eb",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-2180,
480
],
"parameters": {},
"typeVersion": 1
},
{
"id": "eb7f6310-5465-4638-b702-5ecbd98a0199",
"name": "Get Webpages List",
"type": "n8n-nodes-base.googleSheets",
"position": [
-360,
380
],
"parameters": {
"options": {},
"filtersUI": {
"values": [
{
"lookupValue": "2",
"lookupColumn": "=row_number"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1RbobwHCJiYKnic6T-VA3kPr-Grd4Y_ZSQXqy2st_T84/edit?usp=drivesdk",
"cachedResultName": "Visual Regression List"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "XHvC7jIRR8A2TlUl",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "6c0f7341-14c9-48c2-9447-edab0ad18df7",
"name": "For Each Webpage...",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-40,
440
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "62e13166-458d-4c63-8911-740f9ceaeb54",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-660,
160
],
"parameters": {
"color": 7,
"width": 561.2038065501644,
"height": 408.0284015307624,
"content": "## 4. Trigger Visual Regression Test Run\n[Read more about the Schedule Trigger](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.scheduletrigger/)\n\nOnce we've generated our base images to compare with in Part A, we can now run our Visual Regression Tests. These tests are intended to check for unexpected changes to a webpage by using some form of image detection. To trigger Part B, we'll start with a schedule trigger and pull a list of webpages to test from Google Sheets."
},
"typeVersion": 1
},
{
"id": "8d958f44-fd2c-49b4-adbd-d8a99b2614c8",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2340,
218.0216140230686
],
"parameters": {
"color": 7,
"width": 626.9985071319608,
"height": 487.40071048786325,
"content": "## 1. Get List of Webpages to Generate Base Images\n[Learn more about using Google Sheets](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googlesheets/)\n\nThis workflow is split into 2 parts: Part A will generate the \"base\" screenshots to compare new screenshots against. To capture these base screenshots, we'll use Google Sheets to hold our list of webpages and their screenshot references (we'll come on to that later).\n\nExample Sheet: https://docs.google.com/spreadsheets/d/e/2PACX-1vTXRZRi55dUbLAsWZboJqH5U-EK0ZRSse8pkqANAV4Ss70otpQ97zgT8YBd3dL4d2u2UC1TTx_o1o1R/pubhtml"
},
"typeVersion": 1
},
{
"id": "ee776b4d-4532-4c08-ac38-35d40afbd8ad",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1480,
580
],
"parameters": {
"color": 7,
"width": 653.369086691465,
"height": 443.1120543367141,
"content": "## 2. Generate Webpage Screenshot via Apify\n[Learn more about Apify.com](https://www.apify.com?fpr=414q6)\n\nTo generate a screenshot of the webpage, we'll need a third party service since this functionality is outside the scope of n8n. Feel free to pick whichever internal or external service works for you but I've had great experience using [Apify.com](https://www.apify.com?fpr=414q6) - a popular webscraping SaaS who offer a generous free plan and require very little configuration to get started.\n\nThe Apify \"actor\" (ie. a type of scraper) we'll be using is specifically designed to take webpage screenshots."
},
"typeVersion": 1
},
{
"id": "3d90e103-2829-4075-b3d4-5ba848af4843",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1520,
160
],
"parameters": {
"color": 7,
"width": 808.188722669735,
"height": 397.73072497123115,
"content": "## 3. Upload Screenshot to Google Drive\n[Read more about using the Google Drive node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googledrive/)\n\nOnce we have our screenshots, we'll download them from Apify and upload them to our Google Drive for safe keeping. After uploading, we'll capture the new Google Drive IDs for the images into our Google Sheet, this will allow us to reference them again when we perform the visual regression testing."
},
"typeVersion": 1
},
{
"id": "e47d14ec-ad78-42c8-a294-301dcd581a67",
"name": "Download New Screenshot",
"type": "n8n-nodes-base.httpRequest",
"position": [
453,
833
],
"parameters": {
"url": "={{ $json.screenshotUrl }}",
"options": {
"response": {
"response": {
"responseFormat": "file",
"outputPropertyName": "data_2"
}
}
}
},
"typeVersion": 4.2
},
{
"id": "8ca118bc-3d19-48ac-9d9c-0892993da736",
"name": "Combine Screenshots",
"type": "n8n-nodes-base.merge",
"position": [
660,
660
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "03359cbb-d7af-4118-a32a-3fe24062dc9f",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-660,
20
],
"parameters": {
"color": 4,
"width": 394.03359370567625,
"height": 111.52173490405977,
"content": "### Part B. Run Visual Regression Test\nIn this part of the workflow, we'll retrieve our list of webpages to test with our AI vision model. This part can be run as many times as required."
},
"typeVersion": 1
},
{
"id": "a78c0f92-aa61-483b-95bf-dd60958f182d",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2920,
220
],
"parameters": {
"width": 553.2963720930223,
"height": 473.4987906976746,
"content": "## Try It Out!\n\n### This workflow implements an approach to Visual Regression Testing - a means to test websites for defects - using AI Vision Models.\n\nThis workflow uses a Google Sheet to track a list of webpages to test and is split into 2 parts; Part A generates the base screenshots of the list and Part B runs the visual regression testing.\n\nThe example spreadsheet can be found here: https://docs.google.com/spreadsheets/d/e/2PACX-1vTXRZRi55dUbLAsWZboJqH5U-EK0ZRSse8pkqANAV4Ss70otpQ97zgT8YBd3dL4d2u2UC1TTx_o1o1R/pubhtml\n\n**[Apify.com](https://www.apify.com?fpr=414q6)** is the screenshot generator of choice and a free account with $5 in credit is available via this [link](https://www.apify.com?fpr=414q6).\n\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!"
},
"typeVersion": 1
},
{
"id": "a0b257e5-99f8-409a-bc67-2468db377d6c",
"name": "Visual Regression Agent",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1120,
740
],
"parameters": {
"text": "Identify changes between the base image and test image.",
"messages": {
"messageValues": [
{
"message": "=You help with visual regression testing for websites. Identify changes to text content, images, colors, position and layouts of the elements in the screenshots. Ignore text styling or casing changes.\nThe first image will be the base image and the second image will be the test. Note all changes to the test image which differ from the base. If there are no changes, it is okay to return an empty array."
},
{
"type": "HumanMessagePromptTemplate",
"messageType": "imageBinary",
"binaryImageDataKey": "data_1"
},
{
"type": "HumanMessagePromptTemplate",
"messageType": "imageBinary",
"binaryImageDataKey": "data_2"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.4
}
],
"pinData": {},
"connections": {
"Wait": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Download Screenshot",
"type": "main",
"index": 0
}
]
]
},
"Wait1": {
"main": [
[
{
"node": "For Each Webpage...",
"type": "main",
"index": 0
}
]
]
},
"Aggregate": {
"main": [
[
{
"node": "Create Report",
"type": "main",
"index": 0
}
]
]
},
"Base Image": {
"main": [
[
{
"node": "Combine Screenshots",
"type": "main",
"index": 0
}
]
]
},
"Has Changes": {
"main": [
[
{
"node": "Aggregate",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
],
[
{
"node": "Run Webpage Screenshot",
"type": "main",
"index": 0
}
]
]
},
"Upload to Drive": {
"main": [
[
{
"node": "Update Base Image",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Get Webpages List",
"type": "main",
"index": 0
}
]
]
},
"Get Webpages List": {
"main": [
[
{
"node": "For Each Webpage...",
"type": "main",
"index": 0
}
]
]
},
"Combine Screenshots": {
"main": [
[
{
"node": "Visual Regression Agent",
"type": "main",
"index": 0
}
]
]
},
"Download Screenshot": {
"main": [
[
{
"node": "Upload to Drive",
"type": "main",
"index": 0
}
]
]
},
"For Each Webpage...": {
"main": [
[
{
"node": "Combine Row and Result",
"type": "main",
"index": 0
}
],
[
{
"node": "Base Image",
"type": "main",
"index": 0
},
{
"node": "Run Webpage Screenshot1",
"type": "main",
"index": 0
}
]
]
},
"Combine Row and Result": {
"main": [
[
{
"node": "Has Changes",
"type": "main",
"index": 0
}
]
]
},
"Run Webpage Screenshot": {
"main": [
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Download New Screenshot": {
"main": [
[
{
"node": "Combine Screenshots",
"type": "main",
"index": 1
}
]
]
},
"Run Webpage Screenshot1": {
"main": [
[
{
"node": "Download New Screenshot",
"type": "main",
"index": 0
}
]
]
},
"Visual Regression Agent": {
"main": [
[
{
"node": "Wait1",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Visual Regression Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Visual Regression Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Get URLs with Missing Base Images": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
},
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "Get URLs with Missing Base Images",
"type": "main",
"index": 0
}
]
]
}
}
}Workflow n8n Google Sheets, captures d'écran : pour qui est ce workflow ?
Ce workflow s'adresse principalement aux équipes marketing, aux responsables de contenu et aux entreprises qui gèrent des sites web. Un niveau technique intermédiaire est recommandé pour la personnalisation des paramètres et l'intégration des outils.
Workflow n8n Google Sheets, captures d'écran : problème résolu
Ce workflow résout le problème de la gestion manuelle des captures d'écran, qui peut être chronophage et sujette à des erreurs. En automatisant ce processus, les utilisateurs éliminent les frustrations liées à la mise à jour des images et garantissent que leurs documents restent à jour. Le résultat est une gestion plus fluide des contenus visuels, permettant aux équipes de se concentrer sur des tâches à plus forte valeur ajoutée.
Workflow n8n Google Sheets, captures d'écran : étapes du workflow
Étape 1 : Le workflow est déclenché selon un calendrier défini.
- Étape 1 : Il récupère la liste des URLs depuis Google Sheets.
- Étape 2 : Pour chaque URL, une capture d'écran est prise via une requête HTTP.
- Étape 3 : Les captures d'écran sont téléchargées et stockées dans Google Drive.
- Étape 4 : Si des changements sont détectés, les images de base dans Google Sheets sont mises à jour.
- Étape 5 : Le processus se répète pour chaque page web listée.
Workflow n8n Google Sheets, captures d'écran : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier l'URL de la feuille Google Sheets pour pointer vers votre propre document. Ajustez également les paramètres des noeuds de capture d'écran pour définir la taille et la qualité des images. Si vous souhaitez ajouter d'autres outils, vous pouvez intégrer des API supplémentaires dans le workflow. Assurez-vous de sécuriser vos accès à Google Drive et à Google Sheets en utilisant des authentifications appropriées.