Indeed Company Data Scraper & Summarization with Airtable, Bright Data and Google Gemini
工作流概述
这是一个包含19个节点的复杂工作流，主要用于自动化处理各种任务。
工作流源代码
{
"id": "TTj6BiN7bQKTa6FM",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Indeed Company Data Scraper & Summarization with Airtable, Bright Data and Google Gemini",
"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"
},
{
"id": "rKOa98eAi3IETrLu",
"name": "HR",
"createdAt": "2025-04-13T04:59:30.580Z",
"updatedAt": "2025-04-13T04:59:30.580Z"
}
],
"nodes": [
{
"id": "390ebd32-6ce4-4894-9b4f-7b376db5b724",
"name": "When clicking ‘Test workflow’",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-220,
-545
],
"parameters": {},
"typeVersion": 1
},
{
"id": "8ba6b208-b4ad-443c-8b24-c51b3b5ad880",
"name": "Google Gemini Chat Model For Summarization",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1784,
-300
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "394a7291-618a-42f0-8e1b-18ed7c8496c3",
"name": "Webhook HTTP Request",
"type": "@n8n/n8n-nodes-langchain.toolHttpRequest",
"position": [
2280,
-160
],
"parameters": {
"url": "https://webhook.site/daf9d591-a130-4010-b1d3-0c66f8fcf467",
"method": "POST",
"sendBody": true,
"parametersBody": {
"values": [
{
"name": "search_summary",
"value": "={{ $json.response.text }}",
"valueProvider": "fieldValue"
},
{
"name": "search_result"
}
]
},
"toolDescription": "Extract the response and format a structured JSON response"
},
"typeVersion": 1.1
},
{
"id": "4e1352a5-0fa6-4fee-a93d-cc0a0a4fdd6f",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-240,
-1080
],
"parameters": {
"width": 400,
"height": 320,
"content": "## Note
Deals with the Company web scraping by utilizing Bright Data Web Unlocker Product.
The Basic LLM Chain, Summarization and AI Agent are being used to demonstrate the usage of the n8n AI capabilities.
**Please make sure to connect to Airtable with the Base Table as \"Indeed\" and the default Table1 filled with the indeed links to scrape.
Also make sure to update the Webhook Notification URL**"
},
"typeVersion": 1
},
{
"id": "bf184d27-ed62-44fa-bed2-65a1f703179e",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
720,
-1080
],
"parameters": {
"width": 480,
"height": 320,
"content": "## LLM Usages
Google Gemini Flash Exp model is being used.
Basic LLM Chain Data Extractor.
Summarization Chain is being used for the summarization of search results.
The AI Agent formats the search result and pushes it to the Webhook via HTTP Request"
},
"typeVersion": 1
},
{
"id": "78f32ce2-1e79-4f3e-8561-4a5e07d88696",
"name": "Perform Indeed Web Request",
"type": "n8n-nodes-base.httpRequest",
"position": [
1100,
-670
],
"parameters": {
"url": "https://api.brightdata.com/request",
"method": "POST",
"options": {},
"sendBody": true,
"sendHeaders": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "zone",
"value": "={{ $('Set Bright Data Zone').item.json.zone }}"
},
{
"name": "url",
"value": "=https://www.indeed.com/cmp/{{ encodeURI($('Airtable').item.json.Link) }}?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": "3738e714-59aa-4b0b-876c-c2f15a1d7479",
"name": "Indeed Expert AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
2072,
-395
],
"parameters": {
"text": "=You are an Indeed Expert. You need to format the search result and push it to the Webhook via HTTP Request. Here is the search result - {{ $('Markdown to Textual Data Extractor').item.json.text }}",
"options": {},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "47e96e87-8ac7-43d7-af6f-b52404be4eec",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1408,
-300
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "b2b8f3f6-ef13-47ff-8e6e-4c262b352b2e",
"name": "Markdown to Textual Data Extractor",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1320,
-520
],
"parameters": {
"text": "=You need to analyze the below markdown and convert to textual data.
{{ $json.data }}",
"messages": {
"messageValues": [
{
"message": "You are a markdown expert"
}
]
},
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "791d5991-0baa-4aff-8dbe-465c1335889f",
"name": "Convert Markdown to HTML",
"type": "n8n-nodes-base.markdown",
"position": [
1398,
-820
],
"parameters": {
"mode": "markdownToHtml",
"options": {},
"markdown": "={{ $json.data }}"
},
"typeVersion": 1
},
{
"id": "844c49a6-edd0-4a63-944e-44310e39ab09",
"name": "Initiate a Webhook Notification for Markdown to HTML Response",
"type": "n8n-nodes-base.httpRequest",
"position": [
1774,
-820
],
"parameters": {
"url": "https://webhook.site/daf9d591-a130-4010-b1d3-0c66f8fcf467",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "html_response",
"value": "={{ $json.data }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "cb7b971d-17a9-4b49-8807-7a9d4f7550d2",
"name": "Set Bright Data Zone",
"type": "n8n-nodes-base.set",
"position": [
0,
-545
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "4e7ee31d-da89-422f-8079-2ff2d357a0ba",
"name": "zone",
"type": "string",
"value": "web_unlocker1"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "47702b8b-5722-4fe0-93fc-950470b043c8",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
440,
-545
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "cb42b109-0950-45cb-ae74-3a87b724f6fc",
"name": "Airtable",
"type": "n8n-nodes-base.airtable",
"position": [
220,
-545
],
"parameters": {
"base": {
"__rl": true,
"mode": "list",
"value": "appHnxLQRVHbCzDyj",
"cachedResultUrl": "https://airtable.com/appHnxLQRVHbCzDyj",
"cachedResultName": "Indeed"
},
"table": {
"__rl": true,
"mode": "list",
"value": "tblS1f5XWVMfdyjOz",
"cachedResultUrl": "https://airtable.com/appHnxLQRVHbCzDyj/tblS1f5XWVMfdyjOz",
"cachedResultName": "Table 1"
},
"options": {},
"operation": "search"
},
"credentials": {
"airtableTokenApi": {
"id": "yXTVs1Lgka4VUTCB",
"name": "Airtable Personal Access Token account"
}
},
"typeVersion": 2.1
},
{
"id": "faf3d158-e625-4829-8e90-2549d747e674",
"name": "If Link field is not empty",
"type": "n8n-nodes-base.if",
"position": [
880,
-670
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "42eae1de-1d71-4418-862d-9cb9f8fb44e6",
"operator": {
"type": "string",
"operation": "notEmpty",
"singleValue": true
},
"leftValue": "={{ $json.Link }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "d81941a5-b267-4cac-9134-42caac9948ef",
"name": "Wait",
"type": "n8n-nodes-base.wait",
"position": [
660,
-670
],
"webhookId": "f348d66e-ee91-40d4-8e52-83d8d3ca32f2",
"parameters": {
"amount": 10
},
"typeVersion": 1.1
},
{
"id": "6903a767-ab81-4a01-8b98-914afab45c63",
"name": "Indeed Summarizer",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
1696,
-520
],
"parameters": {
"options": {}
},
"typeVersion": 2
},
{
"id": "1cd297e9-30b9-4cb3-b2b4-96bc1e3e9d95",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
200,
-1080
],
"parameters": {
"width": 480,
"height": 320,
"content": "## Airtable Table Data Sample
[
{
\"id\": \"recCDNhVfdlc97cgf\",
\"createdTime\": \"2025-04-14T02:55:31.000Z\",
\"Tab\": \"Starbucks\",
\"Link\": \"https://www.indeed.com/cmp/Starbucks\"
},
{
\"id\": \"recR7VEJrwXX7XjVl\",
\"createdTime\": \"2025-04-14T02:55:31.000Z\",
\"Tab\": \"BrightData\",
\"Link\": \"https://www.indeed.com/cmp/bright-data\"
}
]"
},
"typeVersion": 1
},
{
"id": "d125e31f-845b-498e-9b3c-e5e8c14ed166",
"name": "Google Gemini Chat Model for AI Agent",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2080,
-160
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "98d3cc1a-123e-468e-814f-7a96d38b8e36",
"connections": {
"Wait": {
"main": [
[
{
"node": "If Link field is not empty",
"type": "main",
"index": 0
}
]
]
},
"Airtable": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Indeed Summarizer": {
"main": [
[
{
"node": "Indeed Expert AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Set Bright Data Zone": {
"main": [
[
{
"node": "Airtable",
"type": "main",
"index": 0
}
]
]
},
"Webhook HTTP Request": {
"ai_tool": [
[
{
"node": "Indeed Expert AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Indeed Expert AI Agent": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Convert Markdown to HTML": {
"main": [
[
{
"node": "Initiate a Webhook Notification for Markdown to HTML Response",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Markdown to Textual Data Extractor",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"If Link field is not empty": {
"main": [
[
{
"node": "Perform Indeed Web Request",
"type": "main",
"index": 0
}
]
]
},
"Perform Indeed Web Request": {
"main": [
[
{
"node": "Markdown to Textual Data Extractor",
"type": "main",
"index": 0
},
{
"node": "Convert Markdown to HTML",
"type": "main",
"index": 0
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "Set Bright Data Zone",
"type": "main",
"index": 0
}
]
]
},
"Markdown to Textual Data Extractor": {
"main": [
[
{
"node": "Indeed Summarizer",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model for AI Agent": {
"ai_languageModel": [
[
{
"node": "Indeed Expert AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Google Gemini Chat Model For Summarization": {
"ai_languageModel": [
[
{
"node": "Indeed Summarizer",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}功能特点
- 自动检测新邮件
- AI智能内容分析
- 自定义分类规则
- 批量处理能力
- 详细的处理日志
技术分析
节点类型及作用
- Manualtrigger
- @N8N/N8N Nodes Langchain.Lmchatgooglegemini
- @N8N/N8N Nodes Langchain.Toolhttprequest
- Stickynote
- Httprequest
复杂度评估
配置难度：
维护难度：
扩展性：
实施指南
前置条件
- 有效的Gmail账户
- n8n平台访问权限
- Google API凭证
- AI分类服务订阅
配置步骤
- 在n8n中导入工作流JSON文件
- 配置Gmail节点的认证信息
- 设置AI分类器的API密钥
- 自定义分类规则和标签映射
- 测试工作流执行
- 配置定时触发器（可选）
关键参数
| 参数名称 | 默认值 | 说明 |
|---|---|---|
| maxEmails | 50 | 单次处理的最大邮件数量 |
| confidenceThreshold | 0.8 | 分类置信度阈值 |
| autoLabel | true | 是否自动添加标签 |
最佳实践
优化建议
- 定期更新AI分类模型以提高准确性
- 根据邮件量调整处理批次大小
- 设置合理的分类置信度阈值
- 定期清理过期的分类规则
安全注意事项
- 妥善保管API密钥和认证信息
- 限制工作流的访问权限
- 定期审查处理日志
- 启用双因素认证保护Gmail账户
性能优化
- 使用增量处理减少重复工作
- 缓存频繁访问的数据
- 并行处理多个邮件分类任务
- 监控系统资源使用情况
故障排除
常见问题
邮件未被正确分类
检查AI分类器的置信度阈值设置，适当降低阈值或更新训练数据。
Gmail认证失败
确认Google API凭证有效且具有正确的权限范围，重新进行OAuth授权。
调试技巧
- 启用详细日志记录查看每个步骤的执行情况
- 使用测试邮件验证分类逻辑
- 检查网络连接和API服务状态
- 逐步执行工作流定位问题节点
错误处理
工作流包含以下错误处理机制：
- 网络超时自动重试（最多3次）
- API错误记录和告警
- 处理失败邮件的隔离机制
- 异常情况下的回滚操作