使用Decodo、Gemini AI和Google Sheets抓取、结构化并存储新闻数据
高级
这是一个Market Research, AI Summarization领域的自动化工作流，包含 18 个节点。主要使用 Set, Wait, Crypto, SplitOut, GoogleSheets 等节点。 使用Decodo、Gemini AI和Google Sheets抓取、结构化并存储新闻数据
前置要求
- •Google Sheets API 凭证
- •Google Gemini API Key
使用的节点 (18)
工作流预览
可视化展示节点连接关系，支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"meta": {
"instanceId": "689fa22e68cd4198e4ae37f3cc44f498087edd235a867e22515be823bab694c7",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "dad6ee4f-190c-40d6-b164-49dd6f4b820e",
"name": "计划触发器",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
960,
-368
],
"parameters": {
"rule": {
"interval": [
{}
]
}
},
"typeVersion": 1.2
},
{
"id": "10ba30a4-f1e5-4567-9e64-fbe7b58a6219",
"name": "分割论坛",
"type": "n8n-nodes-base.splitOut",
"position": [
1408,
-368
],
"parameters": {
"include": "selectedOtherFields",
"options": {
"destinationFieldName": "url"
},
"fieldToSplitOut": "forums",
"fieldsToInclude": "geo"
},
"typeVersion": 1
},
{
"id": "59a50a1d-ae14-4947-b27e-cfb29d44d7f3",
"name": "迭代论坛",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1632,
-368
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "f2cac076-1743-47be-a0d9-a0b70f477404",
"name": "Google Gemini 模型",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2096,
-272
],
"parameters": {
"options": {}
},
"credentials": {
"googlePalmApi": {
"id": "C4mfRdRQfQ524QK8",
"name": "Johan Gemini"
}
},
"typeVersion": 1
},
{
"id": "6ec03e78-3b6d-40f3-8351-2210dee705fb",
"name": "提取结构化新闻数据",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
2080,
-496
],
"parameters": {
"text": "=",
"batching": {},
"messages": {
"messageValues": [
{
"message": "=You are an intelligent data extraction model specialized in reading unstructured forum or news data and converting it into structured JSON format."
},
{
"type": "HumanMessagePromptTemplate",
"message": "=Your task is to extract a list of news posts from the provided scraped text. Each post should include:\n- title\n- url\n- source (domain name)\n- points (integer, can be null)\n- comments (integer, can be null)\n- author (string, can be null)\n- posted_at (string, e.g. or \"2025-10-18\")\n\nReturn the result strictly as a JSON array following this schema:\n[\n {\n \"title\": \"\",\n \"url\": \"\",\n \"source\": \"\",\n \"points\": 0,\n \"comments\": 0,\n \"author\": \"\",\n \"posted_at\": \"\"\n }\n]\n\nRules:\n- Output JSON only — no explanations, comments, or markdown formatting.\n- Never include text outside the JSON array.\n- Ensure all keys exist even if null.\n- Determine the posted dates using {{ $now.format('yyyy-MM-dd HH:mm:ss') }} as reference."
},
{
"type": "HumanMessagePromptTemplate",
"message": "=Example scraped text:\n\"1. Claude Haiku 4.5 (anthropic.com/news/claude-haiku-4-5) - 617 points by adocomplete 2 hours ago | 228 comments\n2. Claude Haiku 4.5 System Card (anthropic.com/system-card.pdf) - 51 points by vinhnx 1 day ago | 1 comment\""
},
{
"type": "AIMessagePromptTemplate",
"message": "=[\n {\n \"title\": \"Claude Haiku 4.5\",\n \"url\": \"https://www.anthropic.com/news/claude-haiku-4-5\",\n \"source\": \"anthropic.com\",\n \"points\": 617,\n \"comments\": 228,\n \"author\": \"adocomplete\",\n \"posted_at\": \"2025-10-18\"\n },\n {\n \"title\": \"Claude Haiku 4.5 System Card\",\n \"url\": \"https://www.anthropic.com/system-card.pdf\",\n \"source\": \"anthropic.com\",\n \"points\": 51,\n \"comments\": 1,\n \"author\": \"vinhnx\",\n \"posted_at\": \"2025-10-17\"\n }\n]"
},
{
"type": "HumanMessagePromptTemplate",
"message": "=={{ $json.data.results.first().content }}"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "3325da16-bc04-4c47-b2d7-dd35ab706a34",
"name": "解析 JSON 输出",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
2224,
-272
],
"parameters": {
"jsonSchemaExample": "[\n {\n \"title\": \"Claude Haiku 4.5\",\n \"url\": \"https://www.anthropic.com/news/claude-haiku-4-5\",\n \"source\": \"anthropic.com\",\n \"points\": 617,\n \"comments\": 228,\n \"author\": \"adocomplete\",\n \"posted_at\": \"2025-10-18\"\n },\n {\n \"title\": \"Claude Haiku 4.5 System Card\",\n \"url\": \"https://www.anthropic.com/system-card.pdf\",\n \"source\": \"anthropic.com\",\n \"points\": 51,\n \"comments\": 1,\n \"author\": \"vinhnx\",\n \"posted_at\": \"2025-10-17\"\n }\n]"
},
"typeVersion": 1.3
},
{
"id": "e54df6e4-4498-496a-9038-baf64da0bf8a",
"name": "分割新闻项",
"type": "n8n-nodes-base.splitOut",
"position": [
2432,
-640
],
"parameters": {
"options": {},
"fieldToSplitOut": "output"
},
"typeVersion": 1
},
{
"id": "ef9511a9-b1c6-4613-9131-35add8ba953c",
"name": "生成唯一键",
"type": "n8n-nodes-base.crypto",
"position": [
2656,
-640
],
"parameters": {
"value": "={{ `${$json.url}+${$json.author}` }}",
"dataPropertyName": "key"
},
"executeOnce": false,
"typeVersion": 1
},
{
"id": "a170da82-089c-461d-84db-4dcf445c5927",
"name": "在抓取之间等待",
"type": "n8n-nodes-base.wait",
"position": [
2656,
-272
],
"webhookId": "4c658f26-ded6-4162-bb08-0fa0db99a667",
"parameters": {
"unit": "minutes",
"amount": 1
},
"executeOnce": false,
"typeVersion": 1.1
},
{
"id": "40ae6657-16a4-4c7e-b471-fdbab870e69e",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
-752
],
"parameters": {
"width": 864,
"height": 848,
"content": ""
},
"typeVersion": 1
},
{
"id": "9e816c1f-15dc-4bbd-baed-f19f2c8e2470",
"name": "更新 Google Sheet（新闻）",
"type": "n8n-nodes-base.googleSheets",
"position": [
2880,
-640
],
"parameters": {
"columns": {
"value": {
"key": "={{ $json.key }}",
"url": "={{ $json.url }}",
"title": "={{ $json.title }}",
"author": "={{ $json.author }}",
"points": "={{ $json.points }}",
"source": "={{ $json.source }}",
"comments": "={{ $json.comments }}",
"posted_at": "={{ $json.posted_at }}",
"last_updated": "={{ $now }}"
},
"schema": [
{
"id": "key",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "key",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "title",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "title",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "url",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "source",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "source",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "points",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "points",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "comments",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "comments",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "author",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "author",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "posted_at",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "posted_at",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "last_updated",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "last_updated",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"key"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 800242193,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1ZT7TGHRidqMlQpx-mCcqzUMdg_dzidPCZxNrabKJrhM/edit#gid=800242193",
"cachedResultName": "News"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Workflow Config').item.json.sheet_id }}"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GBiqmzOXHpo7XcLf",
"name": "Johan Sheets"
}
},
"typeVersion": 4.7
},
{
"id": "534a4190-017a-44c1-a909-e1e246f2696b",
"name": "工作流配置",
"type": "n8n-nodes-base.set",
"position": [
1184,
-368
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "3896038b-41c9-496f-af43-dee58ca1ee4f",
"name": "forums",
"type": "array",
"value": "={{[\n \"https://news.ycombinator.com/from?site=openai.com\",\n \"https://news.ycombinator.com/from?site=anthropic.com\",\n]}}"
},
{
"id": "371bf5a1-4377-4f15-9521-f240efd7db47",
"name": "geo",
"type": "string",
"value": "United States"
},
{
"id": "232246ee-aebd-4b4c-abc3-15818c2830d7",
"name": "sheet_id",
"type": "string",
"value": "={{ YOUR_SHEET_ID }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "0b9f0b9b-c682-4c78-80a4-2e2873cf21de",
"name": "便签2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1136,
-464
],
"parameters": {
"color": 5,
"width": 192,
"height": 240,
"content": "### 指定论坛 URL、地理位置和 Sheet ID"
},
"typeVersion": 1
},
{
"id": "a0abdc20-c173-4561-9ad4-9c83e6b50e5b",
"name": "便签7",
"type": "n8n-nodes-base.stickyNote",
"position": [
2832,
-736
],
"parameters": {
"color": 5,
"width": 192,
"height": 272,
"content": "### 确保您的表格选项卡匹配列架构"
},
"typeVersion": 1
},
{
"id": "630ddec3-b370-4c23-b306-21e8c63cf989",
"name": "便签3",
"type": "n8n-nodes-base.stickyNote",
"position": [
912,
-464
],
"parameters": {
"color": 5,
"width": 192,
"height": 240,
"content": "### 调整计划（例如，每天午夜）"
},
"typeVersion": 1
},
{
"id": "490d8405-a01d-48a4-ae8e-f213dcba5128",
"name": "抓取论坛数据",
"type": "@decodo/n8n-nodes-decodo.decodo",
"position": [
1856,
-496
],
"parameters": {
"geo": "={{ $json.geo }}",
"url": "={{ $json.url }}"
},
"credentials": {
"decodoApi": {
"id": "kfy3Vs5AgxfDGzpC",
"name": "Johan Decodo"
}
},
"typeVersion": 1
},
{
"id": "dc69f29f-5553-4edd-a730-4786fb8a9302",
"name": "便签8",
"type": "n8n-nodes-base.stickyNote",
"position": [
2384,
-496
],
"parameters": {
"color": 5,
"width": 192,
"height": 272,
"content": "### 确保您的表格选项卡匹配列架构"
},
"typeVersion": 1
},
{
"id": "4a9901a4-1487-4eb2-8ce5-351f62749f12",
"name": "记录抓取结果",
"type": "n8n-nodes-base.googleSheets",
"position": [
2432,
-400
],
"parameters": {
"columns": {
"value": {
"geo": "={{ $('Iterate Forums').item.json.geo }}",
"forum": "={{ $('Iterate Forums').item.json.url }}",
"news_count": "={{ $json.output.length }}",
"scraped_at": "={{ $now }}"
},
"schema": [
{
"id": "forum",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "forum",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "geo",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "geo",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "news_count",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "news_count",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "scraped_at",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "scraped_at",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1ZT7TGHRidqMlQpx-mCcqzUMdg_dzidPCZxNrabKJrhM/edit#gid=0",
"cachedResultName": "Logs"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Workflow Config').item.json.sheet_id }}"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GBiqmzOXHpo7XcLf",
"name": "Johan Sheets"
}
},
"executeOnce": false,
"typeVersion": 4.7
}
],
"pinData": {},
"connections": {
"Split Forums": {
"main": [
[
{
"node": "Iterate Forums",
"type": "main",
"index": 0
}
]
]
},
"Iterate Forums": {
"main": [
[],
[
{
"node": "Scrape Forum Data",
"type": "main",
"index": 0
}
]
]
},
"Workflow Config": {
"main": [
[
{
"node": "Split Forums",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Workflow Config",
"type": "main",
"index": 0
}
]
]
},
"Split News Items": {
"main": [
[
{
"node": "Generate Unique Key",
"type": "main",
"index": 0
}
]
]
},
"Parse JSON Output": {
"ai_outputParser": [
[
{
"node": "Extract Structured News Data",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Scrape Forum Data": {
"main": [
[
{
"node": "Extract Structured News Data",
"type": "main",
"index": 0
}
]
]
},
"Log Scrape Results": {
"main": [
[
{
"node": "Wait Between Scrapes",
"type": "main",
"index": 0
}
]
]
},
"Generate Unique Key": {
"main": [
[
{
"node": "Update Google Sheet (News)",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Model": {
"ai_languageModel": [
[
{
"node": "Extract Structured News Data",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Wait Between Scrapes": {
"main": [
[
{
"node": "Iterate Forums",
"type": "main",
"index": 0
}
]
]
},
"Extract Structured News Data": {
"main": [
[
{
"node": "Split News Items",
"type": "main",
"index": 0
},
{
"node": "Log Scrape Results",
"type": "main",
"index": 0
}
],
[]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
高级 - 市场调研, AI 摘要总结
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
每周SEO监控清单审计至Google Sheets（使用Gemini和Decodo）
每周SEO监控清单审计至Google Sheets（使用Gemini和Decodo）
Set
Code
Merge
+9
19 节点Fahmi Fahreza
市场调研
自动化 Meta 广告分析
使用 Gemini AI、ScrapingFlash 和 Google Sheets 自动分析 Meta 广告
Limit
Split Out
Http Request
+8
17 节点Paul-François GORIAUX
市场调研
使用 Bright Data API 和 AI 抓取分析 Google 广告并发送邮件报告
使用 Bright Data API 和 AI 抓取分析 Google 广告并发送邮件报告
Set
Code
Gmail
+15
45 节点Zacharia Kimotho
市场调研
新抓取器_TechCrunch新闻-AI1
TechCrunch AI文章抓取与分类器，使用GPT-4.1-nano到Sheets和Telegram
Set
Code
Html
+12
18 节点Mujahid Kabae
市场调研
使用Decodo和Gemini分析Trustpilot和Sitejabber情感并保存到Sheets
使用Decodo和Gemini分析Trustpilot和Sitejabber情感并保存到Sheets
Set
Merge
Form Trigger
+7
18 节点Fahmi Fahreza
市场调研
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
每日 WhatsApp 群组智能分析：GPT-4.1 分析与语音消息转录
If
Set
Code
+20
52 节点Daniel Lianes
杂项
