LinkedIn 潜在客户生成：GPT-4o + Apify + Google Sheets + Phantombuster

受众描述 → GPT-4o 生成 Apollo 搜索 URL → Apify 抓取潜在客户 → GPT-4o 撰写破冰语 → 写入 Google Sheets → 可选触发 Phantombuster 发送连接请求

给谁

销售/SDR 团队、独立开发者或需要自动化 LinkedIn 潜在客户获取与初步触达的用户

你会得到

通过表单输入受众描述，自动生成 Apollo 搜索 URL、抓取潜在客户信息、撰写个性化破冰语，并记录到 Google Sheets，可选自动触发 Phantombuster 发送 LinkedIn 连接请求

你需要

n8n · openai · http-request · google-sheets

步骤

1. 通过表单收集受众描述

   在 n8n 中配置 Form Trigger 节点。表单标题为 'Audience'，包含一个必填字段 'descritpion of the company '（原文拼写），占位文本提示填写公司位置、规模、行业等信息。发布表单 URL 后，用户或 SDR 通过该 URL 提交目标受众描述。

2. 用 GPT-4o 生成 Apollo 搜索 URL

   配置 OpenAI 节点，模型选择 GPT-4o，启用 JSON 输出。系统提示设定为销售助手角色；用户提示包含 Apollo URL 模板示例，说明可修改的字段（地点、职位、关键词），并要求返回 {"SearchUrl":"..."} 格式。输入变量为表单提交的 'descritpion of the company '。

   运行提示词 · 来源原文。OpenAI node system message (node: Genrating appolo Url for apify to scrap)

   复制提示词

   you are a helpful intelligent sales assitant

   运行提示词 · 来源原文。OpenAI node user message template (node: Genrating appolo Url for apify to scrap)

   复制提示词

   your task is to take as input of a prospect audeince and turn that into a apollo serach URL here is an example of the URL 
   https://app.apollo.io/#/people?personLocations[]=United%20States&includedOrganizationKeywordFields[]=tags&includedOrganizationKeywordFields[]=name&sortAscending=false&sortByField=recommendations_score&qKeywords=marketing%20agency%20&page=1&personTitles[]=ceo%20and%20founder&personTitles[]=co-founder
   This url describes a search for peolpe that are 
   -located in the united state 
   - Holds the titles: CEO,founder,co founder 
   - have a keyword assosiated with "marketing "agency"
   you can only make changes to these fields only 
   return your response as using this format  
   {"SearchUrl":"SearchUrlgoeshere"}

   运行提示词 · 来源原文。OpenAI node dynamic input expression

   复制提示词

   ={{ $json['descritpion of the company '] }}

3. 通过 Apify Actor 抓取潜在客户

   配置 HTTP Request 节点，方法为 POST，URL 固定为 https://api.apify.com/v2/acts/jljBwyyQakqrL1wae/run-sync-get-dataset-items。JSON body 包含 cleanOutput: true 与 url 字段（引用上一步生成的 SearchUrl）。请求头需添加 Accept: application/json 和 Authorization: Bearer YOUR_TOKEN_HERE key（将 YOUR_TOKEN_HERE key 替换为实际 Apify API token）。

   运行提示词 · 来源原文。HTTP Request node JSON body (node: Run apify actor to scrap the proscpect)

   复制提示词

   ={
       "cleanOutput": true,
       "url": "{{ $json.message.content.SearchUrl }}"
   }

   运行提示词 · 来源原文。HTTP Request node Authorization header value (placeholder to be replaced)

   复制提示词

   Bearer YOUR_TOKEN_HERE key

4. 用 GPT-4o 生成个性化破冰语

   配置第二个 OpenAI 节点，模型同样选择 GPT-4o。系统提示为 'you are a helpful '；用户提示要求根据 LinkedIn 资料生成极短、有力的破冰语，指定模板格式 'Hey {{name}}, loved seeing {{thingaboutThem}}, Im also into {{plausibleTieIN}}, thought Id connect.'，强调必须改写（paraphrase）而非直接引用 LinkedIn 字段内容，避免陈词滥调，保持极简风格。输出格式为 {"Icebreaker":"..."}。输入为 Apify 返回的潜在客户数据。

   运行提示词 · 来源原文。OpenAI node system message (node: Genrate ice breaker by scraping linkedin data)

   复制提示词

   you are a helpful

   运行提示词 · 来源原文。OpenAI node user message template (node: Genrate ice breaker by scraping linkedin data)

   复制提示词

   your task is to input a bunch of linkedin profile information of a user, and then geenrate a very short,very punchy incebreaker that i can use as a variable in my connection request 
   return your output in this format 
   {"Icebreaker":"Icebreakergoeshere"}
   in order to ensure icebreakers are punchy and high quality, make them follow this template 
   Hey {{name}}, loved seeing {{thingaboutThem}}, Im also into {{plausibleTieIN}}, thought Id connect.
   For {{thingaboutThem}}and {{plausibleTiein}}, never use the exact information provided in a linked in field. instead,always parapharse. this makes it seems human written instead of just an automated message, Also, make it super short. Dont say stuff like ""passionate about truning vision into reality " or anything like that be extremely Laconic and spartan.

   运行提示词 · 来源原文。OpenAI node dynamic input expression

   复制提示词

   map the prospect's LinkedIn or details from the previous node.

5. 将破冰语写入 Google Sheets

   配置 Google Sheets 节点，操作选择 appendOrUpdate。需预先创建 Google Sheet 并添加列：name、linkedin url、company website、description 以及 Apify 节点生成的其他字段。在节点中映射对应字段，documentId 和 sheetName 需填入实际表格信息（来源中留空，由用户配置）。确保 Google Service Account 凭证已共享给该表格。

   搭建指导 · 来源原文。Sticky Note guidance for Google Sheets column setup

   复制提示词

   Create a google sheet add relevant colums name,linkedin url,company website,description and oter coloums that are genrated by the apify node and map them accordingly

6. 聚合数据批次

   配置 Aggregate 节点，选择 aggregateAllItemData。该节点将 Google Sheets 输出的多行数据聚合为批量格式，为下一步触发 Phantombuster 做准备。无需额外提示词。

7. 触发 Phantombuster 发送连接请求（可选）

   配置 HTTP Request 节点，方法为 POST，URL 为 https://api.phantombuster.com/api/v2/(your agent id goes here)/launch，需将 (your agent id goes here) 替换为实际 Agent ID。请求头添加 X-Phantombuster-Key: api key goes here（替换为实际 API key）。无需请求体。若不需要自动发送连接请求，可禁用此节点。

   搭建指导 · 来源原文。Sticky Note guidance for Phantombuster HTTP Request configuration

   复制提示词

   Triggers the phantom buster a platform that sends linkedin connection requests. to your leads, you have to go to the api credentials to get the relevant url but i hvae harcoded one for the connection request and add your api key to the header, and the agent ID of the agent you are running will be available in the url of the agent in phantombuster thats it no body  is needed.

你是一个 n8n 工作流搭建助手。用户想要复现一个 LinkedIn 潜在客户生成自动化流程。请协助用户：1) 确认已具备所有必要凭证（OpenAI、Apify、Google Sheets、Phantombuster）；2) 按步骤导入 workflow.json 并配置各节点参数；3) 替换所有占位符（YOUR_TOKEN_HERE key、your agent id goes here、documentId/sheetName）；4) 先用测试数据执行一次端到端验证。不要代替用户执行实际 API 调用或发送真实连接请求。