ビング・データとGemini AIを使ってWikipediaデータを抽出し、要約
中級
これはOther, AI分野の自動化ワークフローで、12個のノードを含みます。主にSet, HttpRequest, ManualTrigger, ChainLlm, ChainSummarization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とGemini AIを使ってWikipediaのデータを抽出し、要約する
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •Google Gemini API Key
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": "sczRNO4u1HYc5YV7",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Extract & Summarize Wikipedia Data with Bright Data and Gemini AI",
"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": "0f4b4939-6356-4672-ae61-8d1daf66a168",
"name": "「Test workflow」クリック時",
"type": "n8n-nodes-base.manualTrigger",
"position": [
340,
-440
],
"parameters": {},
"typeVersion": 1
},
{
"id": "167e060a-c36c-462a-826c-81ef379c824b",
"name": "Google Gemini Chat Model For Summarization",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1520,
-60
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "a51f2634-8b59-4feb-be39-674e8f198714",
"name": "Google Gemini Chat Model2",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1000,
-240
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-pro-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "a1ec001f-6e97-4efb-91d9-9a037fbf472c",
"name": "Summary Webhook Notifier",
"type": "n8n-nodes-base.httpRequest",
"position": [
1860,
-280
],
"parameters": {
"url": "https://webhook.site/ce41e056-c097-48c8-a096-9b876d3abbf7",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "summary",
"value": "={{ $json.response.text }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "f4dd93b5-2a33-4ac7-a0c9-9e0956bea363",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
340,
-820
],
"parameters": {
"width": 400,
"height": 300,
"content": "## Note\n\nThis template deals with the Wikipedia data extraction and summarization of content with the Bright Data. \n\nThe LLM Data Extractor is responsible for producing a human readable content.\n\nThe Concise Summary Generator node is responsible for generating the concise summary of the Wikipedia extracted info.\n\n**Please make sure to update the Wikipedia URL with Bright Data Zone. Also make sure to set the Webhook Notification URL.**"
},
"typeVersion": 1
},
{
"id": "9bd6f913-c526-4e54-81f8-8885a0fe974f",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
780,
-820
],
"parameters": {
"width": 500,
"height": 300,
"content": "## LLM Usages\n\nGoogle Gemini Flash Exp model is being used to demonstrate the data extraction and summarization aspects.\n\nBasic LLM Chain is being used for extracting the html to text\n\nSummarization Chain is being used for summarization of the Wikipedia data.\n\n**Note - Replace Google Gemini with the Open AI or suitable LLM providers of your choice.**"
},
"typeVersion": 1
},
{
"id": "30008ce4-4de2-43c5-bb03-94db58262f86",
"name": "Wikipedia Web Request",
"type": "n8n-nodes-base.httpRequest",
"position": [
780,
-440
],
"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 }}"
},
{
"name": "format",
"value": "raw"
}
]
},
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "kdbqXuxIR8qIxF7y",
"name": "Header Auth account"
}
},
"typeVersion": 4.2
},
{
"id": "28656a7d-4bd8-41c8-8471-50d19d88e7f2",
"name": "LLM Data Extractor",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1000,
-440
],
"parameters": {
"text": "={{ $json.data }}",
"messages": {
"messageValues": [
{
"message": "You are an expert Data Formatter. Make sure to format the data in a human readable manner. Please output the human readable content without your own thoughts"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.6
},
{
"id": "7045af3b-9e74-42ef-92f0-f8d3266f2890",
"name": "Concise Summary Generator",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
1440,
-280
],
"parameters": {
"options": {
"summarizationMethodAndPrompts": {
"values": {
"prompt": "Write a concise summary of the following:\n\n\n\"{text}\"\n"
}
}
},
"chunkingMode": "advanced"
},
"typeVersion": 2
},
{
"id": "0cc843c1-252a-4c18-9856-5c7dfc732072",
"name": "Set Wikipedia URL with Bright Data Zone",
"type": "n8n-nodes-base.set",
"notes": "Set the URL which you are interested to scrap the data",
"position": [
560,
-440
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "1c132dd6-31e4-453b-a8cf-cad9845fe55b",
"name": "url",
"type": "string",
"value": "https://en.wikipedia.org/wiki/Cloud_computing?product=unlocker&method=api"
},
{
"id": "0fa387df-2511-4228-b6aa-237cceb3e9c7",
"name": "zone",
"type": "string",
"value": "web_unlocker1"
}
]
}
},
"notesInFlow": true,
"typeVersion": 3.4
},
{
"id": "6cb9930f-1924-4762-8150-f5cd0e063348",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
940,
-500
],
"parameters": {
"color": 4,
"width": 380,
"height": 420,
"content": "## Basic LLM Chain Data Extractor\n"
},
"typeVersion": 1
},
{
"id": "47811535-bce5-4946-aaa6-baef87db1100",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1400,
-340
],
"parameters": {
"color": 5,
"width": 340,
"height": 420,
"content": "## Summarization Chain\n"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "5b5e78fb-6e5a-4b92-838c-6c4060618e9c",
"connections": {
"28656a7d-4bd8-41c8-8471-50d19d88e7f2": {
"main": [
[
{
"node": "7045af3b-9e74-42ef-92f0-f8d3266f2890",
"type": "main",
"index": 0
}
]
]
},
"30008ce4-4de2-43c5-bb03-94db58262f86": {
"main": [
[
{
"node": "28656a7d-4bd8-41c8-8471-50d19d88e7f2",
"type": "main",
"index": 0
}
]
]
},
"7045af3b-9e74-42ef-92f0-f8d3266f2890": {
"main": [
[
{
"node": "a1ec001f-6e97-4efb-91d9-9a037fbf472c",
"type": "main",
"index": 0
}
]
]
},
"a51f2634-8b59-4feb-be39-674e8f198714": {
"ai_languageModel": [
[
{
"node": "28656a7d-4bd8-41c8-8471-50d19d88e7f2",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"0f4b4939-6356-4672-ae61-8d1daf66a168": {
"main": [
[
{
"node": "0cc843c1-252a-4c18-9856-5c7dfc732072",
"type": "main",
"index": 0
}
]
]
},
"0cc843c1-252a-4c18-9856-5c7dfc732072": {
"main": [
[
{
"node": "30008ce4-4de2-43c5-bb03-94db58262f86",
"type": "main",
"index": 0
}
]
]
},
"167e060a-c36c-462a-826c-81ef379c824b": {
"ai_languageModel": [
[
{
"node": "7045af3b-9e74-42ef-92f0-f8d3266f2890",
"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？
中級 - その他, 人工知能
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
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
ビング・データとGemini AIを使ってBing Copilot検索結果を抽出・要約
Gemini AIとBright Dataを使ってBing Copilot検索性別結果を抽出し、要約する
If
Set
Wait
+
If
Set
Wait
19 ノードRanjan Dailata
人工知能
ビング・データとGoogle Geminiを使ってIndeedの企業情報を抽出し、集約
Bright DataとGoogle Geminiを使ってIndeedの企業情報を抽出し、集約する
Set
Markdown
Http Request
+
Set
Markdown
Http Request
15 ノードRanjan Dailata
人事
ビング・データとGoogle Geminiを使ってYelpの店舗口コミを抽出し、要約
Bright DataとGoogle Geminiを使ってYelpの商家レビューを抽出し、要約する
Set
Merge
Http Request
+
Set
Merge
Http Request
12 ノードRanjan Dailata
人工知能
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
Googleトレンドデータ抽出、Bright DataとGoogle Geminiを使用して要約生成
Bright DataとGoogle Geminiを利用したGoogleトレンドデータ抽出と要約生成
Set
Gmail
Function
+
Set
Gmail
Function
16 ノードRanjan Dailata
エンジニアリング
