AIアゲント駆動のProduct Huntデータ抽出と検索（Bright DataとGoogle Geminiを使用）
上級
これはAI, Marketing分野の自動化ワークフローで、21個のノードを含みます。主にSet, Function, McpClient, HttpRequest, GoogleSheetsなどのノードを使用、AI技術を活用したスマート自動化を実現。 Bright Data MCPとGoogle Gemini AIを使ってProduct Huntデータをクロールして検索
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •Google Sheets API認証情報
- •Google Gemini API Key
使用ノード (21)
ワークフロープレビュー
ノード接続関係を可視化、ズームとパンをサポート
ワークフローをエクスポート
以下のJSON設定をn8nにインポートして、このワークフローを使用できます
{
"id": "ko4fOc1jV3wKbt7T",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "AI Agent Driven ProductHunt Data Extract & Search with Bright Data & Google Gemini",
"tags": [
{
"id": "Kujft2FOjmOVQAmJ",
"name": "Engineering",
"createdAt": "2025-04-09T01:31:00.558Z",
"updatedAt": "2025-04-09T01:31:00.558Z"
},
{
"id": "ZOwtAMLepQaGW76t",
"name": "Building Blocks",
"createdAt": "2025-04-13T15:23:40.462Z",
"updatedAt": "2025-04-13T15:23:40.462Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
}
],
"nodes": [
{
"id": "5af692c1-c035-49c0-84ac-d9dcff94269b",
"name": "ワークフロー実行時",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-640,
-20
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c6f927ef-1664-4a4a-b9b0-faf9f9e052b6",
"name": "Bright Data全ツール一覧",
"type": "n8n-nodes-mcp.mcpClient",
"position": [
-420,
-20
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "08175de9-ddc7-4664-87e9-cf3b6e9008b6",
"name": "入力フィールド設定",
"type": "n8n-nodes-base.set",
"position": [
-200,
-20
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "ac9abb54-45af-488d-b3f8-f923c85dbda9",
"name": "base_url",
"type": "string",
"value": "https://www.producthunt.com"
},
{
"id": "a15e928c-7c39-46a0-9bd2-5a3a7564d4ed",
"name": "category",
"type": "string",
"value": "resumes"
},
{
"id": "2d440cf4-4e48-400d-9752-1ea6d5cfcc62",
"name": "search",
"type": "string",
"value": "The best resume tools in 2025"
},
{
"id": "5d0e3985-b268-4ca6-8702-07f6f2f439b7",
"name": "engine",
"type": "string",
"value": "google"
},
{
"id": "c4781bc2-b870-4030-9ce8-3b7111a8ea59",
"name": "webhook_url",
"type": "string",
"value": "https://webhook.site/c9118da2-1c54-460f-a83a-e5131b7098db"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "cba889d2-71b7-46fa-a723-00d41e1e891d",
"name": "AIエージェント",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
280,
-20
],
"parameters": {
"text": "={{ $json.agent_operation }}\n\nOuput the data in a clean and human readable format. Output only the tool response.",
"options": {},
"promptType": "define"
},
"retryOnFail": true,
"typeVersion": 2
},
{
"id": "e2f19c38-899d-475f-87f8-2305c27560ab",
"name": "Google Gemini チャットモデル",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
100,
220
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "bae60554-4022-4af3-a2c7-067235b2f03a",
"name": "Google検索用MCPクライアント",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
280,
220
],
"parameters": {
"toolName": "search_engine",
"operation": "executeTool",
"toolParameters": "={\n \"query\": \"{{ $('Set the Input Fields').item.json.search }}\",\n \"engine\": \"{{ $('Set the Input Fields').item.json.engine }}\"\n} ",
"descriptionType": "manual",
"toolDescription": "=Perform a search as per the specified search engine : {{ $('Set the Input Fields').item.json.engine }}"
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "b1ca5ed5-e0e5-4434-897b-25efad53577f",
"name": "Markdownデータ抽出用MCPクライアント",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
480,
220
],
"parameters": {
"toolName": "scrape_as_markdown",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $('Set the Input Fields').item.json.base_url }}/categories/{{ encodeURI($('Set the Input Fields').item.json.category) }}\"\n} ",
"descriptionType": "manual",
"toolDescription": "Perform Product Hunt data scrapping in markdown format"
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "57305e8e-2731-45e7-b1d8-d9f73786f1da",
"name": "エージェント操作設定",
"type": "n8n-nodes-base.set",
"position": [
20,
-20
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "f243ff07-a39e-4fdc-a32b-2c50e809b3fa",
"name": "agent_operation",
"type": "string",
"value": "=Perform a Product Hunt data extract"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "be721837-c5e8-4ade-98fc-01b6aae10dd9",
"name": "構造化データ抽出用バイナリデータ作成",
"type": "n8n-nodes-base.function",
"position": [
760,
-20
],
"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": "83cf444d-4b85-4688-ac1c-67fb6027b2ec",
"name": "構造化コンテンツをディスクに書き込み",
"type": "n8n-nodes-base.readWriteFile",
"position": [
980,
-20
],
"parameters": {
"options": {},
"fileName": "=d:\\ProductData.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "2f179451-1a1d-437a-bddd-370d5deed3a2",
"name": "構造化データ用Webhook通知開始",
"type": "n8n-nodes-base.httpRequest",
"position": [
760,
180
],
"parameters": {
"url": "={{ $('Set the Input Fields').item.json.webhook_url }}",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "product_info",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "7431be44-2bc5-466a-aa24-cff3aa97ecef",
"name": "付箋2",
"type": "n8n-nodes-base.stickyNote",
"position": [
340,
-420
],
"parameters": {
"color": 3,
"width": 440,
"height": 120,
"content": "## Disclaimer\nThis template is only available on n8n self-hosted as it's making use of the community node for MCP Client."
},
"typeVersion": 1
},
{
"id": "2c01a180-4202-4287-a656-c9afb052c950",
"name": "付箋4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
-300
],
"parameters": {
"color": 5,
"width": 440,
"height": 220,
"content": "## LLM Usages\n\nGoogle Gemini LLM is being utilized for the AI Agent handling"
},
"typeVersion": 1
},
{
"id": "02ba0f5d-f210-46fa-888a-53740f2f57d7",
"name": "付箋5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-700,
-840
],
"parameters": {
"color": 7,
"width": 400,
"height": 400,
"content": "## Logo\n\n\n\n"
},
"typeVersion": 1
},
{
"id": "2561fbea-ac79-4a48-a141-9906bec656ed",
"name": "付箋3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-700,
-400
],
"parameters": {
"width": 400,
"height": 320,
"content": "## Note\n\nDeals with the ProductHunt data extraction by utilizing the Bright Data MCP and Google Gemini LLM.\n\n**Please make sure to set the input fields node and the agent operation node to fulfill your needs**"
},
"typeVersion": 1
},
{
"id": "7c7e69f2-393e-4725-9bc6-0fd6e3271ea0",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
-460
],
"parameters": {
"color": 4,
"width": 440,
"height": 120,
"content": "## Agent Operation\n\n1. Perform a Product Hunt data extract\n2. Google search and extract data"
},
"typeVersion": 1
},
{
"id": "823039f1-e41f-4286-adde-4da05924f8cf",
"name": "構造化データ抽出器",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
760,
440
],
"parameters": {
"text": "=Extract the links, keywords, description from {{ $('AI Agent').item.json.output }}\n\nConstruct the links with the base url as {{ $('Set the Input Fields').item.json.base_url }}",
"batching": {},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.7
},
{
"id": "467a58f7-b480-4975-9045-17ffef12553b",
"name": "構造化出力パーサー",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
980,
640
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n\t\"type\": \"array\",\n\t\"properties\": {\n\t\t\"link\": {\n\t\t\t\"type\": \"string\"\n\t\t},\n \"desc\": {\n\t\t\t\"type\": \"string\"\n\t\t}\n\t}\n}"
},
"typeVersion": 1.2
},
{
"id": "c6a9ef1d-f1d8-469c-a149-20b70613a7a4",
"name": "Google Gemini チャットモデル構造化データ抽出",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
740,
640
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "d9ca7a55-ccb8-4c34-aec1-792f67e7cab4",
"name": "構造化データ用Googleスプレッドシート更新",
"type": "n8n-nodes-base.googleSheets",
"position": [
1200,
440
],
"parameters": {
"columns": {
"value": {
"structured_data": "={{ $json.output.toJsonString() }}"
},
"schema": [
{
"id": "structured_data",
"type": "string",
"display": true,
"required": false,
"displayName": "structured_data",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"structured_data"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1785677350,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1cmJkB_DuSUbHoZ-LthySa7utEZFIvzeLinGcHjMyvzI/edit#gid=1785677350",
"cachedResultName": "Sheet2"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1cmJkB_DuSUbHoZ-LthySa7utEZFIvzeLinGcHjMyvzI",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1cmJkB_DuSUbHoZ-LthySa7utEZFIvzeLinGcHjMyvzI/edit?usp=drivesdk",
"cachedResultName": "ProductHunt"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "Zjoxh2BUZ6VXGQhA",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "380351d4-2b49-4824-bbb6-3bba45f9fb37",
"name": "AIエージェント用Googleスプレッドシート更新",
"type": "n8n-nodes-base.googleSheets",
"position": [
760,
-220
],
"parameters": {
"columns": {
"value": {
"output": "={{ $json.output.toJsonString() }}"
},
"schema": [
{
"id": "output",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "output",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"output"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/10gAihQMT8-h8Mpehe9j-xxN4oTTpg8qwToI-I-Eauew/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1cmJkB_DuSUbHoZ-LthySa7utEZFIvzeLinGcHjMyvzI",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1cmJkB_DuSUbHoZ-LthySa7utEZFIvzeLinGcHjMyvzI/edit?usp=drivesdk",
"cachedResultName": "ProductHunt"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "Zjoxh2BUZ6VXGQhA",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "07e2bb99-d6bf-4023-b61a-582436d22d04",
"connections": {
"cba889d2-71b7-46fa-a723-00d41e1e891d": {
"main": [
[
{
"node": "be721837-c5e8-4ade-98fc-01b6aae10dd9",
"type": "main",
"index": 0
},
{
"node": "2f179451-1a1d-437a-bddd-370d5deed3a2",
"type": "main",
"index": 0
},
{
"node": "380351d4-2b49-4824-bbb6-3bba45f9fb37",
"type": "main",
"index": 0
},
{
"node": "823039f1-e41f-4286-adde-4da05924f8cf",
"type": "main",
"index": 0
}
]
]
},
"08175de9-ddc7-4664-87e9-cf3b6e9008b6": {
"main": [
[
{
"node": "57305e8e-2731-45e7-b1d8-d9f73786f1da",
"type": "main",
"index": 0
}
]
]
},
"57305e8e-2731-45e7-b1d8-d9f73786f1da": {
"main": [
[
{
"node": "cba889d2-71b7-46fa-a723-00d41e1e891d",
"type": "main",
"index": 0
}
]
]
},
"e2f19c38-899d-475f-87f8-2305c27560ab": {
"ai_languageModel": [
[
{
"node": "cba889d2-71b7-46fa-a723-00d41e1e891d",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"467a58f7-b480-4975-9045-17ffef12553b": {
"ai_outputParser": [
[
{
"node": "823039f1-e41f-4286-adde-4da05924f8cf",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"823039f1-e41f-4286-adde-4da05924f8cf": {
"main": [
[
{
"node": "d9ca7a55-ccb8-4c34-aec1-792f67e7cab4",
"type": "main",
"index": 0
}
]
]
},
"bae60554-4022-4af3-a2c7-067235b2f03a": {
"ai_tool": [
[
{
"node": "cba889d2-71b7-46fa-a723-00d41e1e891d",
"type": "ai_tool",
"index": 0
}
]
]
},
"c6f927ef-1664-4a4a-b9b0-faf9f9e052b6": {
"main": [
[
{
"node": "08175de9-ddc7-4664-87e9-cf3b6e9008b6",
"type": "main",
"index": 0
}
]
]
},
"b1ca5ed5-e0e5-4434-897b-25efad53577f": {
"ai_tool": [
[
{
"node": "cba889d2-71b7-46fa-a723-00d41e1e891d",
"type": "ai_tool",
"index": 0
}
]
]
},
"5af692c1-c035-49c0-84ac-d9dcff94269b": {
"main": [
[
{
"node": "c6f927ef-1664-4a4a-b9b0-faf9f9e052b6",
"type": "main",
"index": 0
}
]
]
},
"be721837-c5e8-4ade-98fc-01b6aae10dd9": {
"main": [
[
{
"node": "83cf444d-4b85-4688-ac1c-67fb6027b2ec",
"type": "main",
"index": 0
}
]
]
},
"c6a9ef1d-f1d8-469c-a149-20b70613a7a4": {
"ai_languageModel": [
[
{
"node": "823039f1-e41f-4286-adde-4da05924f8cf",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}よくある質問
このワークフローの使い方は？
上記のJSON設定コードをコピーし、n8nインスタンスで新しいワークフローを作成して「JSONからインポート」を選択、設定を貼り付けて認証情報を必要に応じて変更してください。
このワークフローはどんな場面に適していますか？
上級 - 人工知能, マーケティング
有料ですか？
このワークフローは完全無料です。ただし、ワークフローで使用するサードパーティサービス（OpenAI APIなど）は別途料金が発生する場合があります。
関連ワークフロー
Brave検索による構造化データ抽出（Bright Data MCP + Google Gemini）
Bright Data MCPとGoogle Geminiを使用してBrave検索から構造化されたデータを抽出
Set
Switch
Function
+
Set
Switch
Function
24 ノードRanjan Dailata
人工知能
DNB企業検索と抽出：Bright DataとOpenAI 4o miniを使用
Bright Data そして OpenAI 4o mini に基づく DNB 社検索と抽出
Set
Function
Mcp Client
+
Set
Function
Mcp Client
18 ノードRanjan Dailata
プロダクト
Amazon製品の価格下落をBright Dataで抽出・要約・分析
Bright DataとGoogle GeminiでAmazonの価格下落情報を抽出・要約・分析
Set
Wait
Merge
+
Set
Wait
Merge
26 ノードRanjan Dailata
人工知能
Bright Data MCPとGoogle Geminiを使用した法の事例研究抽出ツール、データマイニングツール
Bright Data MCPとGoogle Geminiを使用した法のケーススタディ抽出データマイニングツール
Set
Code
Wait
+
Set
Code
Wait
22 ノードRanjan Dailata
人工知能
Bright Dataを使用したブランドコンテンツの抽出・要約・感情分析
Bright DataとGoogle Geminiを使用してブランドコンテンツを抽出および分析
Set
Function
Http Request
+
Set
Function
Http Request
23 ノードRanjan Dailata
人工知能
Bright Data MCPサーバーとGoogle Geminiを使ったLinkedInウェブスクレイピング
Bright Data MCPサーバーとGoogle Geminiを使用したLinkedInデータの抽出・変換
Set
Code
Merge
+
Set
Code
Merge
20 ノードRanjan Dailata
人工知能
ワークフロー情報
難易度
上級
ノード数21
カテゴリー2
ノードタイプ13
作成者
Ranjan Dailata
@ranjancseA Professional based out of India specialized in handling AI-powered automations. Contact me at ranjancse@gmail.com
外部リンク
n8n.ioで表示 →
このワークフローを共有