Dumpling AIとGPT-4oを使ってAIニュースの自動レビューを生成
中級
これはAI, Marketing分野の自動化ワークフローで、14個のノードを含みます。主にCode, Wait, SplitOut, Aggregate, HttpRequest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。 Dumpling AI、GPT-4oを使って自動生成してAIニュースのレビューを投稿する
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •Google Sheets API認証情報
- •OpenAI API Key
使用ノード (14)
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": "M8PPLx0heLyG4kmQ",
"meta": {
"instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
"templateCredsSetupCompleted": true
},
"name": "Auto-Generate AI News Commentary with Dumpling AI and GPT-4o",
"tags": [],
"nodes": [
{
"id": "35ce9dd5-cc21-4cf9-a7ac-6cc9718fa86a",
"name": "操作なし, do nothing",
"type": "n8n-nodes-base.noOp",
"position": [
-420,
-160
],
"parameters": {},
"typeVersion": 1
},
{
"id": "c572b2c3-9e72-4d7d-89f9-364aa5c00f79",
"name": "Run on Schedule (Daily)",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-1080,
-60
],
"parameters": {
"rule": {
"interval": [
{}
]
}
},
"typeVersion": 1.2
},
{
"id": "412b5965-1278-4748-8d77-4c85d9eb9cff",
"name": "Fetch Topics with Empty Commentary",
"type": "n8n-nodes-base.googleSheets",
"position": [
-860,
-60
],
"parameters": {
"options": {
"returnFirstMatch": true
},
"filtersUI": {
"values": [
{
"lookupColumn": "generated commentary"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1rCXEWnIZd6cKIqsVRRynHEygQTztJM76rm4HM8Xlqbw/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1rCXEWnIZd6cKIqsVRRynHEygQTztJM76rm4HM8Xlqbw/edit?usp=drivesdk",
"cachedResultName": "News articles"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GaJqJHuS5mQxap7q",
"name": "Google Sheets account"
}
},
"typeVersion": 4.6
},
{
"id": "c04e7811-4e30-4e68-8342-55d79669072e",
"name": "Loop Through Each Topic",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-640,
-60
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "435798d5-59b3-4379-831a-9b8801a99f38",
"name": "待機 Before News Search",
"type": "n8n-nodes-base.wait",
"position": [
-420,
40
],
"webhookId": "2f67769b-0637-4b7e-9324-f8ba9520969c",
"parameters": {},
"typeVersion": 1.1
},
{
"id": "f0098d01-fa3b-40e8-aeeb-e9dd31606ddb",
"name": "Search News with Dumpling AI",
"type": "n8n-nodes-base.httpRequest",
"position": [
-200,
40
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/search-news",
"method": "POST",
"options": {},
"jsonBody": "={\n \"query\": \"{{ $json.Topic }}\",\n \"country\": \"US\",\n \"page\": 3,\n \"language\": \"en\"\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "43862942-4e19-4856-a3b0-2546d8a7a462",
"name": "Split Returned News Articles",
"type": "n8n-nodes-base.splitOut",
"position": [
20,
40
],
"parameters": {
"options": {},
"fieldToSplitOut": "news"
},
"typeVersion": 1
},
{
"id": "9b45eb16-66b1-45bc-b4a3-5ad46696b295",
"name": "Scrape Article Content with Dumpling AI",
"type": "n8n-nodes-base.httpRequest",
"position": [
240,
40
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/scrape",
"method": "POST",
"options": {},
"jsonBody": "={\n \"url\": \"{{ $json.link}}\"\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "ffa392af-04d1-4c6a-a05e-f63f765d7eca",
"name": "集計 Scraped Article Content",
"type": "n8n-nodes-base.aggregate",
"position": [
460,
40
],
"parameters": {
"options": {},
"fieldsToAggregate": {
"fieldToAggregate": [
{
"fieldToAggregate": "content"
}
]
}
},
"typeVersion": 1
},
{
"id": "5204f7c9-e5f8-4594-9428-4b46e92ba81d",
"name": "Clean Article Content",
"type": "n8n-nodes-base.code",
"position": [
680,
40
],
"parameters": {
"jsCode": "let rawContent = $input.first().json.content;\n\n// If content is not a string, try to stringify it\nif (typeof rawContent !== 'string') {\n rawContent = JSON.stringify(rawContent);\n}\n\nconst cleaned = rawContent\n .replace(/https?:\\/\\/[^\\s]+/g, '') // Remove full URLs\n .replace(/www\\.[^\\s]+/g, '') // Remove www links\n .replace(/\\[([^\\]]+)\\]\\(([^)]+)\\)/g, '$1') // Remove markdown links\n .replace(/<a[^>]*>(.*?)<\\/a>/gi, '$1') // Remove HTML anchor tags\n .replace(/\\s{2,}/g, ' ') // Remove extra spaces\n .trim();\n\nreturn [{\n json: {\n cleaned_content: cleaned\n }\n}];\n"
},
"typeVersion": 2
},
{
"id": "04fe4476-023b-49a5-8e72-0d251d78ae1a",
"name": "Generate LinkedIn Commentary (GPT-4o)",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
900,
40
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "chatgpt-4o-latest",
"cachedResultName": "CHATGPT-4O-LATEST"
},
"options": {},
"messages": {
"values": [
{
"content": "=You are a thought leader on LinkedIn. I will provide you with a news articles related to {{ $('Fetch Topics with Empty Commentary').item.json.Topic }}, and you will write a personal commentary in a confident, insightful, first-person voice.\n\nYour response should:\n- Start with a strong personal opinion or observation\n- Briefly connect the news to real-world trends or implications\n- Mention how this relates to your work, experience, or thinking\n- Use a human tone, no robotic phrasing or generic statements\n- End with a question or call to action to invite engagement\n\nKeep it under 600 characters. Avoid buzzwords or fluff. Be authentic.\n\nHere are the news articles:{{ $json.cleaned_content }}\n"
}
]
}
},
"credentials": {
"openAiApi": {
"id": "dd8NvMC6rvx8RITo",
"name": "OpenAi account 2"
}
},
"typeVersion": 1.8
},
{
"id": "ecc25fb7-52c0-4b89-94eb-06088b92e095",
"name": "Append Commentary Back to Sheet",
"type": "n8n-nodes-base.googleSheets",
"position": [
1260,
40
],
"parameters": {
"columns": {
"value": {
"Topic": "={{ $('Fetch Topics with Empty Commentary').item.json.Topic }}",
"generated commentary": "={{ $json.message.content }}"
},
"schema": [
{
"id": "Topic",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Topic",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "generated commentary",
"type": "string",
"display": true,
"required": false,
"displayName": "generated commentary",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Image",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "Image",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Topic"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1rCXEWnIZd6cKIqsVRRynHEygQTztJM76rm4HM8Xlqbw/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1rCXEWnIZd6cKIqsVRRynHEygQTztJM76rm4HM8Xlqbw/edit?usp=drivesdk",
"cachedResultName": "News articles"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GaJqJHuS5mQxap7q",
"name": "Google Sheets account"
}
},
"typeVersion": 4.6
},
{
"id": "62e5001b-0aa9-40eb-bf65-6ca6ff1e3b32",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1100,
-260
],
"parameters": {
"width": 1100,
"height": 340,
"content": "### 📥 Fetch Topics and Search News via Dumpling AI\n\nThis section starts with a scheduled trigger. It pulls entries from a Google Sheet where the “generated commentary” is empty, meaning the topic hasn’t been processed. Each topic is looped individually. A short wait is applied to manage rate limits. Dumpling AI’s `/search-news` endpoint is then triggered to retrieve relevant articles based on the topic keyword.\n"
},
"typeVersion": 1
},
{
"id": "3c3904a5-90d3-486a-8f69-bb6b33b5d234",
"name": "付箋1",
"type": "n8n-nodes-base.stickyNote",
"position": [
240,
-280
],
"parameters": {
"width": 1120,
"height": 360,
"content": "### ✍️ Scrape Articles, Clean Text, Generate Commentary, and Append\n\nEach article is split out and scraped using Dumpling AI’s `/scrape` endpoint to get full content. The aggregated content is cleaned via a Code node, removing links and excess formatting. GPT-4o generates a LinkedIn-style first-person commentary using this cleaned content. The final output is saved back to the Google Sheet under the “generated commentary” field.\n"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "2f3ec71f-7ba1-46bf-bbd3-633a9e526a47",
"connections": {
"5204f7c9-e5f8-4594-9428-4b46e92ba81d": {
"main": [
[
{
"node": "04fe4476-023b-49a5-8e72-0d251d78ae1a",
"type": "main",
"index": 0
}
]
]
},
"c04e7811-4e30-4e68-8342-55d79669072e": {
"main": [
[
{
"node": "No Operation, do nothing",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait Before News Search",
"type": "main",
"index": 0
}
]
]
},
"c572b2c3-9e72-4d7d-89f9-364aa5c00f79": {
"main": [
[
{
"node": "412b5965-1278-4748-8d77-4c85d9eb9cff",
"type": "main",
"index": 0
}
]
]
},
"Wait Before News Search": {
"main": [
[
{
"node": "f0098d01-fa3b-40e8-aeeb-e9dd31606ddb",
"type": "main",
"index": 0
}
]
]
},
"f0098d01-fa3b-40e8-aeeb-e9dd31606ddb": {
"main": [
[
{
"node": "43862942-4e19-4856-a3b0-2546d8a7a462",
"type": "main",
"index": 0
}
]
]
},
"43862942-4e19-4856-a3b0-2546d8a7a462": {
"main": [
[
{
"node": "9b45eb16-66b1-45bc-b4a3-5ad46696b295",
"type": "main",
"index": 0
}
]
]
},
"ecc25fb7-52c0-4b89-94eb-06088b92e095": {
"main": [
[
{
"node": "c04e7811-4e30-4e68-8342-55d79669072e",
"type": "main",
"index": 0
}
]
]
},
"Aggregate Scraped Article Content": {
"main": [
[
{
"node": "5204f7c9-e5f8-4594-9428-4b46e92ba81d",
"type": "main",
"index": 0
}
]
]
},
"412b5965-1278-4748-8d77-4c85d9eb9cff": {
"main": [
[
{
"node": "c04e7811-4e30-4e68-8342-55d79669072e",
"type": "main",
"index": 0
}
]
]
},
"04fe4476-023b-49a5-8e72-0d251d78ae1a": {
"main": [
[
{
"node": "ecc25fb7-52c0-4b89-94eb-06088b92e095",
"type": "main",
"index": 0
}
]
]
},
"9b45eb16-66b1-45bc-b4a3-5ad46696b295": {
"main": [
[
{
"node": "Aggregate Scraped Article Content",
"type": "main",
"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 - 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
[テンプレート] AIペットショップ v8
AIペットショップアシスタント - GPT-4o、Googleカレンダー、WhatsApp/Instagram/Facebookを統合
If
N8n
Set
+
If
N8n
Set
244 ノードAmanda Benks
営業
AI破冰コンテンツジェネレーター：Dumpling AIを使用してWebサイトをスクレイピングしAirtableに保存
AI破冰コンテンツジェネレーター：Dumpling AIを使用してWebサイトをスクレイピングしAirtableに保存
Wait
Airtable
Http Request
+
Wait
Airtable
Http Request
9 ノードYang
人工知能
ペットショップ 4
ペットショップ予約AIエージェント
If
Set
Code
+
If
Set
Code
187 ノードBruno Dias
人工知能
AI个性化多製品メールマーケティング
基于SMTP轮换のAI个性化多製品メールマーケティング（GPT-4o/o3-mini）
If
Code
Wait
+
If
Code
Wait
41 ノードBadr
営業
LinkedIn オートメーション - Archit Jain
GPT-4 と Google Sheets を使って Twitter AI 投稿から LinkedIn コンテンツを自動作成
Code
Wait
Limit
+
Code
Wait
Limit
35 ノードArchit Jain
人工知能
競合企業のコンテンツ分析を通じて市場調査と SEO のコンテンツカンパスを発見
競合サイトのコンテンツ空白をInfraNodusのGraphRAGで分析し、SEOを支援
If
Code
Wait
+
If
Code
Wait
37 ノードInfraNodus
人工知能
