Automatisation Bright Data avec n8n : analyse de contenu et sentiment
Ce workflow n8n a pour objectif d'automatiser l'extraction, le résumé et l'analyse de sentiment de contenus à l'aide de Bright Data. Il est particulièrement utile pour les équipes marketing et communication qui cherchent à analyser rapidement des données textuelles et à en tirer des insights précieux. Grâce à cette automatisation n8n, les utilisateurs peuvent gagner du temps et améliorer leur efficacité en matière de traitement de contenu. Le workflow commence par un déclencheur manuel qui permet de tester le flux. Ensuite, plusieurs nœuds de type 'Sticky Note' sont utilisés pour afficher des informations pertinentes. Les données textuelles sont extraites à l'aide du nœud 'Markdown to Textual Data Extractor'. Par la suite, le workflow envoie des requêtes HTTP pour initier des notifications Webhook pour l'extraction de données et l'analyse de sentiment. Les modèles Google Gemini sont intégrés pour le résumé et l'analyse de sentiment, offrant des résultats précis et rapides. Enfin, les fichiers générés sont écrits sur le disque, permettant une consultation ultérieure. Cette automatisation apporte une valeur ajoutée significative en réduisant le temps d'analyse et en améliorant la prise de décision basée sur des données concrètes.
Workflow n8n analyse de données, Bright Data, marketing : vue d'ensemble
Schéma des nœuds et connexions de ce workflow n8n, généré à partir du JSON n8n.
Workflow n8n analyse de données, Bright Data, marketing : détail des nœuds
Inscris-toi pour voir l'intégralité du workflow
Inscription gratuite
S'inscrire gratuitementBesoin d'aide ?{
"id": "wTI77cpLkbxsRQat",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Brand Content Extract, Summarize & Sentiment Analysis with Bright Data",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
}
],
"nodes": [
{
"id": "646ef542-c601-4103-87e6-6fa9616d8c52",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
120,
-560
],
"parameters": {},
"typeVersion": 1
},
{
"id": "00b4ce90-c4f2-41c4-8943-7db3d0c3f81a",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
100,
-320
],
"parameters": {
"width": 400,
"height": 300,
"content": "## Note\n\nThis workflow deals with the brand content extraction by utilizing the Bright Data Web Unlocker Product.\n\nThe Basic LLM Chain, Information Extraction, Summarization Chain are being used to demonstrate the usage of the N8N AI capabilities.\n\n**Please make sure to set the web URL of your interest within the \"Set URL and Bright Data Zone\" node and update the Webhook Notification URL**"
},
"typeVersion": 1
},
{
"id": "5cc35b9b-7483-404e-96a3-1688f7b9078b",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
540,
-320
],
"parameters": {
"width": 480,
"height": 300,
"content": "## LLM Usages\n\nGoogle Gemini Flash Exp model is being used.\n\nBasic LLM Chain Data Extractor.\n\nInformation Extraction is being used for the handling the custom sentiment analysis with the structured response.\n\nSummarization Chain is being used for the creation of a concise summary of the extracted brand content."
},
"typeVersion": 1
},
{
"id": "e15f32de-58d9-4ea6-9d5c-f63975d1090d",
"name": "Markdown to Textual Data Extractor",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1240,
-440
],
"parameters": {
"text": "=You need to analyze the below markdown and convert to textual data. Please do not output with your own thoughts. Make sure to output with textual data only with no links, scripts, css etc.\n\n{{ $json.data }}",
"messages": {
"messageValues": [
{
"message": "You are a markdown expert"
}
]
},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "1462cd3b-b1d5-4ddf-9f1e-2b8f20faa19c",
"name": "Set URL and Bright Data Zone",
"type": "n8n-nodes-base.set",
"position": [
340,
-560
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "3aedba66-f447-4d7a-93c0-8158c5e795f9",
"name": "url",
"type": "string",
"value": "https://www.amazon.com/TP-Link-Dual-Band-Archer-BE230-HomeShield/dp/B0DC99N2T8"
},
{
"id": "4e7ee31d-da89-422f-8079-2ff2d357a0ba",
"name": "zone",
"type": "string",
"value": "web_unlocker1"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "9783e878-e864-4632-9b89-d78567204053",
"name": "AI Sentiment Analyzer with the structured response",
"type": "@n8n/n8n-nodes-langchain.informationExtractor",
"position": [
1740,
100
],
"parameters": {
"text": "=Perform the sentiment analysis on the below content and output with the structured information.\n\nHere's the content:\n\n{{ $('Perform Bright Data Web Request').item.json.data }}",
"options": {
"systemPromptTemplate": "You are an expert sentiment analyzer."
},
"schemaType": "manual",
"inputSchema": "{\n \"$schema\": \"http://json-schema.org/schema#\",\n \"title\": \"SentimentAnalysisResponseArray\",\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"sentiment\": {\n \"type\": \"string\",\n \"enum\": [\"Positive\", \"Neutral\", \"Negative\"],\n \"description\": \"The overall sentiment of the content.\"\n },\n \"confidence_score\": {\n \"type\": \"number\",\n \"minimum\": 0,\n \"maximum\": 1,\n \"description\": \"Confidence score of the sentiment classification.\"\n },\n \"sentence\": {\n \"type\": \"string\",\n \"description\": \"A natural language statement explaining the sentiment.\"\n }\n },\n \"required\": [\"sentiment\", \"confidence_score\", \"sentence\"],\n \"additionalProperties\": false\n }\n}\n"
},
"typeVersion": 1
},
{
"id": "41352a53-7821-4247-905e-7995e1e6e382",
"name": "Initiate a Webhook Notification for Markdown to Textual Data Extraction",
"type": "n8n-nodes-base.httpRequest",
"position": [
1720,
-460
],
"parameters": {
"url": "https://webhook.site/3c36d7d1-de1b-4171-9fd3-643ea2e4dd76",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "summary",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "9717b5df-f148-4c8c-95d4-cb7c54837228",
"name": "Initiate a Webhook Notification for AI Sentiment Analyzer",
"type": "n8n-nodes-base.httpRequest",
"position": [
2120,
100
],
"parameters": {
"url": "https://webhook.site/3c36d7d1-de1b-4171-9fd3-643ea2e4dd76",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "summary",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "88733b5f-cbb0-42a6-898c-7a1ccc94bef7",
"name": "Google Gemini Chat Model for Summary",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1260,
-780
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "560e3d33-61d8-4db6-b1df-89f4e915f3f1",
"name": "Google Gemini Chat Model for Data Extract",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1320,
-220
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "1b07608f-7174-46e8-af27-3abf100d9e3a",
"name": "Google Gemini Chat Model for Sentiment Analyzer",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1820,
320
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "b6b6df94-d3fc-45ee-a339-5a368ea000eb",
"name": "Initiate a Webhook Notification for Summarization",
"type": "n8n-nodes-base.httpRequest",
"position": [
1660,
-820
],
"parameters": {
"url": "https://webhook.site/3c36d7d1-de1b-4171-9fd3-643ea2e4dd76",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "summary",
"value": "={{ $json.response.text }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "f3e60ecd-5d07-4df0-a413-327b24db23ab",
"name": "Perform Bright Data Web Request",
"type": "n8n-nodes-base.httpRequest",
"position": [
560,
-560
],
"parameters": {
"url": "https://api.brightdata.com/request",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "zone",
"value": "={{ $json.zone }}"
},
{
"name": "url",
"value": "={{ $json.url }}?product=unlocker&method=api"
},
{
"name": "format",
"value": "raw"
},
{
"name": "data_format",
"value": "markdown"
}
]
},
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "kdbqXuxIR8qIxF7y",
"name": "Header Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "9030085f-5b05-41d9-94ee-668ee29df815",
"name": "Summarize Content",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
1240,
-980
],
"parameters": {
"options": {
"summarizationMethodAndPrompts": {
"values": {
"prompt": "Write a concise summary of the following:\n\n\n\"{text}\"\n\n"
}
}
},
"chunkingMode": "advanced"
},
"typeVersion": 2
},
{
"id": "fe93c4a6-de3b-481d-ba6c-5f315f5279c4",
"name": "Create a binary data for textual data",
"type": "n8n-nodes-base.function",
"position": [
1720,
-220
],
"parameters": {
"functionCode": "items[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "0811c300-1302-49b5-a334-ac8f960a5b8c",
"name": "Create a binary data for sentiment analysis",
"type": "n8n-nodes-base.function",
"position": [
2120,
320
],
"parameters": {
"functionCode": "items[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "01d798b7-7c62-4240-9d5e-f2e67ca047ae",
"name": "Write the AI Sentiment analysis file to disk",
"type": "n8n-nodes-base.readWriteFile",
"position": [
2520,
320
],
"parameters": {
"options": {},
"fileName": "d:\\Brand-Content-Sentiment-Analysis.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "f9faf283-ba8d-48e1-860e-2bb660cb9c1e",
"name": "Write the textual file to disk",
"type": "n8n-nodes-base.readWriteFile",
"position": [
2100,
-220
],
"parameters": {
"options": {},
"fileName": "d:\\Brand-Content-Textual.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "2c47c271-4456-4fc4-9a54-20784365a4af",
"name": "Create a binary data for summary",
"type": "n8n-nodes-base.function",
"position": [
1660,
-1060
],
"parameters": {
"functionCode": "items[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "c5f33f8d-93eb-47ac-a42f-717b39f4d7c2",
"name": "Write the summary file to disk",
"type": "n8n-nodes-base.readWriteFile",
"position": [
1880,
-1060
],
"parameters": {
"options": {},
"fileName": "d:\\Brand-Content-Summary.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "72938f7b-20c1-45d3-9348-878d6e0b8d60",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1200,
-1080
],
"parameters": {
"color": 4,
"width": 1100,
"height": 460,
"content": "## Summarization"
},
"typeVersion": 1
},
{
"id": "fcf1d1ad-d516-41bc-bf76-73ebb920ecba",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1720,
40
],
"parameters": {
"color": 6,
"width": 1000,
"height": 480,
"content": "## Sentiment Analysis"
},
"typeVersion": 1
},
{
"id": "9c44d01f-e30b-4597-ad74-09fa54b4ec84",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1200,
-520
],
"parameters": {
"color": 3,
"width": 1100,
"height": 480,
"content": "## Textual Data Extract"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "317a5d48-95c6-4425-a14a-6b2fec9e0802",
"connections": {
"Summarize Content": {
"main": [
[
{
"node": "Initiate a Webhook Notification for Summarization",
"type": "main",
"index": 0
},
{
"node": "Create a binary data for summary",
"type": "main",
"index": 0
}
]
]
},
"Set URL and Bright Data Zone": {
"main": [
[
{
"node": "Perform Bright Data Web Request",
"type": "main",
"index": 0
}
]
]
},
"Perform Bright Data Web Request": {
"main": [
[
{
"node": "Markdown to Textual Data Extractor",
"type": "main",
"index": 0
},
{
"node": "Summarize Content",
"type": "main",
"index": 0
}
]
]
},
"Create a binary data for summary": {
"main": [
[
{
"node": "Write the summary file to disk",
"type": "main",
"index": 0
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "Set URL and Bright Data Zone",
"type": "main",
"index": 0
}
]
]
},
"Markdown to Textual Data Extractor": {
"main": [
[
{
"node": "AI Sentiment Analyzer with the structured response",
"type": "main",
"index": 0
},
{
"node": "Initiate a Webhook Notification for Markdown to Textual Data Extraction",
"type": "main",
"index": 0
},
{
"node": "Create a binary data for textual data",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model for Summary": {
"ai_languageModel": [
[
{
"node": "Summarize Content",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Create a binary data for textual data": {
"main": [
[
{
"node": "Write the textual file to disk",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model for Data Extract": {
"ai_languageModel": [
[
{
"node": "Markdown to Textual Data Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Create a binary data for sentiment analysis": {
"main": [
[
{
"node": "Write the AI Sentiment analysis file to disk",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model for Sentiment Analyzer": {
"ai_languageModel": [
[
{
"node": "AI Sentiment Analyzer with the structured response",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Sentiment Analyzer with the structured response": {
"main": [
[
{
"node": "Initiate a Webhook Notification for AI Sentiment Analyzer",
"type": "main",
"index": 0
},
{
"node": "Create a binary data for sentiment analysis",
"type": "main",
"index": 0
}
]
]
},
"Initiate a Webhook Notification for AI Sentiment Analyzer": {
"main": [
[]
]
},
"Initiate a Webhook Notification for Markdown to Textual Data Extraction": {
"main": [
[]
]
}
}
}Workflow n8n analyse de données, Bright Data, marketing : pour qui est ce workflow ?
Ce workflow s'adresse aux équipes marketing, aux analystes de données et aux professionnels de la communication qui souhaitent automatiser l'analyse de contenu. Il est conçu pour des utilisateurs ayant un niveau technique intermédiaire, dans des entreprises de taille petite à moyenne.
Workflow n8n analyse de données, Bright Data, marketing : problème résolu
Ce workflow résout le problème de la lenteur et de l'inefficacité dans l'analyse de contenu. En automatisant le processus d'extraction, de résumé et d'analyse de sentiment, il élimine les frustrations liées à la gestion manuelle des données textuelles. Les utilisateurs peuvent ainsi obtenir des résultats concrets rapidement, ce qui leur permet de prendre des décisions éclairées basées sur des insights précis.
Workflow n8n analyse de données, Bright Data, marketing : étapes du workflow
Étape 1 : Le workflow est déclenché manuellement.
- Étape 1 : Des nœuds 'Sticky Note' affichent des informations pertinentes.
- Étape 2 : Le nœud 'Markdown to Textual Data Extractor' extrait les données textuelles.
- Étape 3 : Des requêtes HTTP sont envoyées pour initier des notifications Webhook pour l'extraction et l'analyse de sentiment.
- Étape 4 : Les modèles Google Gemini sont utilisés pour résumer le contenu et analyser le sentiment.
- Étape 5 : Les fichiers générés sont écrits sur le disque pour une consultation ultérieure.
Workflow n8n analyse de données, Bright Data, marketing : guide de personnalisation
Pour personnaliser ce workflow, vous pouvez modifier les paramètres des nœuds HTTP pour ajuster les URL de notification Webhook. Il est également possible de changer les modèles Google Gemini utilisés pour l'analyse et le résumé. Assurez-vous d'adapter les nœuds 'Sticky Note' pour afficher les informations pertinentes selon vos besoins. Pour sécuriser le flux, pensez à configurer les authentifications nécessaires pour les requêtes HTTP et à monitorer les résultats via des outils d'analyse.