{ "name": "LinkedIn Lead Scraper", "nodes": [ { "parameters": { "model": { "__rl": true, "value": "gpt-4.1-mini", "mode": "list", "cachedResultName": "gpt-4.1-mini" }, "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "typeVersion": 1.2, "position": [ 200, 240 ], "id": "8096cfc8-6071-4604-898d-65443c9bf3a0", "name": "OpenAI Chat Model" }, { "parameters": { "schemaType": "manual", "inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"platform\": {\n \"type\": \"string\",\n \"enum\": [\"LinkedIn\"]\n },\n \"roles\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"lead_count\": {\n \"type\": \"integer\",\n \"minimum\": 1,\n \"maximum\": 1000\n },\n \"filters\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"location\": {\n \"type\": \"string\"\n },\n \"keywords\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\"platform\", \"roles\", \"lead_count\", \"filters\", \"location\", \"keywords\"]\n}" }, "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "typeVersion": 1.2, "position": [ 380, 240 ], "id": "dd51b4b8-044d-49b3-953a-fa9c61107348", "name": "Structured Output" }, { "parameters": { "promptType": "define", "text": "=You are an instruction parser for an AI lead scraping system. Parse the user request and extract structured information.\nRules:\n1. Platform Detection\nLook for platform mention in user query. If no platform is mentioned, default to \"LinkedIn\".\n2. Role Extraction\nExtract job titles, skills, or professional categories. Include variations and synonyms:\n\n\"AI engineer\" OR \"ML engineer\" OR \"Machine Learning engineer\"\n\"founder\" OR \"CEO\" OR \"co-founder\"\n\"developer\" OR \"software engineer\" OR \"programmer\"\n\"data scientist\" OR \"data analyst\" OR \"ML researcher\"\n\n3. Lead Count\nExtract numbers mentioned in phrases like:\n\n\"20 leads\", \"find 50\", \"at least 30\", \"I want 25\"\nIf not specified, default to 10\n\n4. Filters\nExtract constraints and qualifiers including:\nCompany Type:\n\n\"startup\", \"enterprise\", \"funded company\", \"series A\", \"series B\", \"YC company\", \"unicorn\"\n\"small company\", \"large corporation\", \"Fortune 500\"\n\nExperience Level:\n\n\"senior\", \"junior\", \"mid-level\", \"entry-level\"\n\"5+ years\", \"10+ years experience\", \"recent graduate\"\n\"lead\", \"principal\", \"staff\", \"director level\"\n\nContact Information:\n\n\"email available\", \"LinkedIn profile\", \"phone number\", \"contact details\"\n\nIndustry Specific:\n\n\"fintech\", \"healthcare\", \"SaaS\", \"e-commerce\", \"edtech\", \"blockchain\"\n\"AI/ML\", \"cybersecurity\", \"biotech\", \"cleantech\"\n\nCompany Size:\n\n\"team of 10-50\", \"500+ employees\", \"small team\", \"large organization\"\n\nFunding Status:\n\n\"recently funded\", \"profitable\", \"bootstrap\", \"venture backed\"\n\"raised funding\", \"IPO\", \"acquired\"\n\n5. Location\nExtract geographic information:\n\nCities: \"San Francisco\", \"New York\", \"Mumbai\", \"London\"\nStates/Regions: \"California\", \"Texas\", \"Maharashtra\"\nCountries: \"United States\", \"India\", \"United Kingdom\"\nRemote preferences: \"remote\", \"remote-first\", \"distributed team\"\nMultiple locations: \"SF or NYC\", \"US or Canada\"\n\n6. Keywords\nExtract relevant search terms and synonyms that would be useful for search optimization:\n\nTechnical skills, tools, programming languages\nIndustry buzzwords and terminology\nCompany descriptors and qualifiers\n\nOutput Format:\nRespond ONLY with valid JSON following the specified schema. No explanations, comments, or additional text.\nExample Input Processing:\nInput: \"search for profile which have AI automation and are located in Mumbai\"\nExpected Output:\njson{\n \"platform\": \"LinkedIn\",\n \"roles\": [\"AI automation specialist\", \"AI automation engineer\"],\n \"lead_count\": 10,\n \"filters\": [\"AI automation experience\", \"automation tools\"],\n \"location\": \"Mumbai\",\n \"keywords\": [\"AI\", \"automation\", \"machine learning\", \"artificial intelligence\"]\n}\nInput: \"Find 25 senior software engineers at YC startups in San Francisco with email addresses\"\nExpected Output:\njson{\n \"platform\": \"LinkedIn\",\n \"roles\": [\"senior software engineer\", \"software engineer\"],\n \"lead_count\": 25,\n \"filters\": [\"YC company\", \"startup\", \"senior level\", \"email available\"],\n \"location\": \"San Francisco\",\n \"keywords\": [\"software engineer\", \"Y Combinator\", \"startup\", \"senior\"]\n}\n\n\"example_outputs\": {\n \"example_1\": {\n \"input\": \"search for profile which have AI automation and are located in Mumbai\",\n \"output\": {\n \"platform\": \"LinkedIn\",\n \"roles\": [\"AI automation specialist\", \"AI automation engineer\"],\n \"lead_count\": 10,\n \"filters\": [\"AI automation experience\", \"automation tools\"],\n \"location\": \"Mumbai\",\n \"keywords\": [\"AI\", \"automation\", \"machine learning\", \"artificial intelligence\"]\n }\n },\n \"example_2\": {\n \"input\": \"Find 25 senior software engineers at YC startups in San Francisco with email addresses\",\n \"output\": {\n \"platform\": \"LinkedIn\",\n \"roles\": [\"senior software engineer\", \"software engineer\"],\n \"lead_count\": 25,\n \"filters\": [\"YC company\", \"startup\", \"senior level\", \"email available\"],\n \"location\": \"San Francisco\",\n \"keywords\": [\"software engineer\", \"Y Combinator\", \"startup\", \"senior\"]\n }\n },\n \"example_3\": {\n \"input\": \"Scrape LinkedIn for AI/ML interns or internship opportunities at startups that have recently received funding. I want at least 20 valid leads\",\n \"output\": {\n \"platform\": \"LinkedIn\",\n \"roles\": [\"AI intern\", \"ML intern\", \"machine learning intern\", \"artificial intelligence intern\"],\n \"lead_count\": 20,\n \"filters\": [\"startup\", \"recently funded\", \"internship\", \"series A\", \"series B\", \"venture capital\"],\n \"location\": \"\",\n \"keywords\": [\"AI\", \"ML\", \"machine learning\", \"artificial intelligence\", \"intern\", \"startup\", \"funding\"]\n }\n },\n \"example_4\": {\n \"input\": \"Get me 50 CTOs from fintech companies in New York or remote\",\n \"output\": {\n \"platform\": \"LinkedIn\",\n \"roles\": [\"CTO\", \"Chief Technology Officer\", \"VP Engineering\"],\n \"lead_count\": 50,\n \"filters\": [\"fintech\", \"financial technology\", \"C-level\", \"executive\"],\n \"location\": \"New York OR remote\",\n \"keywords\": [\"CTO\", \"fintech\", \"financial technology\", \"chief technology officer\"]\n }\n },\n \"example_5\": {\n \"input\": \"Find founders on Linkedin who raised Series A in the last 6 months\",\n \"output\": {\n \"platform\": \"Linkedin\",\n \"roles\": [\"founder\", \"CEO\", \"co-founder\"],\n \"lead_count\": 10,\n \"filters\": [\"series A\", \"recently funded\", \"last 6 months\", \"raised funding\"],\n \"location\": \"\",\n \"keywords\": [\"founder\", \"CEO\", \"series A\", \"funding\", \"startup\"]\n }\n },\n \"example_6\": {\n \"input\": \"Search Linkedin for React developers with 5+ years experience who work at unicorn companies\",\n \"output\": {\n \"platform\": \"Linkedin\",\n \"roles\": [\"React developer\", \"Frontend developer\", \"Full-stack developer\"],\n \"lead_count\": 10,\n \"filters\": [\"5+ years experience\", \"unicorn company\", \"senior level\", \"billion dollar valuation\"],\n \"location\": \"\",\n \"keywords\": [\"React\", \"JavaScript\", \"frontend\", \"unicorn\", \"developer\"]\n }\n }\nUser request: \n{{ $json.chatInput }}", "hasOutputParser": true }, "type": "@n8n/n8n-nodes-langchain.chainLlm", "typeVersion": 1.6, "position": [ 200, 0 ], "id": "21d08e8b-33e2-4a0a-b646-52e855cef53c", "name": "AI Search Planner" }, { "parameters": { "jsCode": "// LinkedIn Profile Search Query Builder - Profile Only\nconst input = items[0].json.output;\n\n// Extract and normalize data\nconst roles = input.roles || [];\nconst leadCount = input.lead_count || input.leadCount || 10;\nconst filters = input.filters || [];\nconst location = input.location || '';\nconst keywords = input.keywords || [];\n\n// Helper function to create quoted phrases with OR logic\nfunction createQuotedTerms(terms) {\n return terms.filter(term => term && term.trim())\n .map(term => `\"${term.trim()}\"`)\n .join(' OR ');\n}\n\n// Helper function to build location query\nfunction buildLocationQuery(location) {\n if (!location) return '';\n \n // Handle multiple locations separated by OR, comma, or \"or\"\n const locationTerms = location.split(/\\s+(?:OR|or)\\s+|,\\s*/)\n .map(loc => loc.trim())\n .filter(loc => loc);\n \n if (locationTerms.length === 1) {\n return `\"${locationTerms[0]}\"`;\n } else if (locationTerms.length > 1) {\n return `(${locationTerms.map(loc => `\"${loc}\"`).join(' OR ')})`;\n }\n return '';\n}\n\n// Build single LinkedIn profile search query\nconst roleQuery = createQuotedTerms(roles);\nconst locationQuery = buildLocationQuery(location);\nconst filterQuery = filters.length > 0 ? createQuotedTerms(filters) : '';\nconst keywordQuery = keywords.length > 0 ? createQuotedTerms(keywords) : '';\n\n// Build LinkedIn profile query\nlet profileQuery = 'site:linkedin.com/in';\nconst queryParts = [];\n\nif (roleQuery) queryParts.push(roleQuery);\nif (locationQuery) queryParts.push(locationQuery);\nif (filterQuery) queryParts.push(filterQuery);\nif (keywordQuery && !roleQuery) queryParts.push(keywordQuery); // Only add keywords if no roles\n\nif (queryParts.length > 0) {\n profileQuery += ` ${queryParts.join(' ')}`;\n}\n\n// Return single result for LinkedIn profiles only\nreturn [{\n json: {\n searchQuery: profileQuery.trim(),\n leadCount: leadCount,\n platform: 'linkedin'\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 560, 0 ], "id": "c349d5e0-388a-4dec-a84f-719dbde64665", "name": "Build LinkedIn Query" }, { "parameters": { "url": "=https://serpapi.com/search.json", "sendQuery": true, "queryParameters": { "parameters": [ { "name": "engine", "value": "=google" }, { "name": "q", "value": "={{ $json.searchQuery }}" }, { "name": "api_key", "value": "YOUR_API_KEY" }, { "name": "num", "value": "={{ $json.leadCount }}" } ] }, "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 760, 0 ], "id": "1e507949-aa15-452c-84b6-c1bacd950f11", "name": "Google Search (SerpAPI)" }, { "parameters": { "operation": "append", "documentId": { "__rl": true, "value": "YOUR_SHEET_ID", "mode": "list", "cachedResultName": "LinkedIn Scrapper", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/YOUR_SHEET_ID/edit?usp=drivesdk" }, "sheetName": { "__rl": true, "value": "gid=0", "mode": "list", "cachedResultName": "Sheet1", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/YOUR_SHEET_ID/edit#gid=0" }, "columns": { "mappingMode": "defineBelow", "value": { "Name": "={{ $json.name }}", "Role": "={{ $json.role }}", "Connections": "={{ $json.connections }}", "Company": "={{ $json.company }}", "LinkedinUrl": "={{ $json.linkedinUrl }}", "Email": "={{ $json.email }}", "Snippet": "={{ $json.snippet }}", "ScrappedAt": "={{ $json.scrapedAt }}" }, "matchingColumns": [], "schema": [ { "id": "Name", "displayName": "Name", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "Role", "displayName": "Role", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "Connections", "displayName": "Connections", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "Company", "displayName": "Company", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "LinkedinUrl", "displayName": "LinkedinUrl", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "Email", "displayName": "Email", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "Snippet", "displayName": "Snippet", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false }, { "id": "ScrappedAt", "displayName": "ScrappedAt", "required": false, "defaultMatch": false, "display": true, "type": "string", "canBeUsedToMatch": true, "removed": false } ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {} }, "type": "n8n-nodes-base.googleSheets", "typeVersion": 4.5, "position": [ 1160, 0 ], "id": "e4aae9b3-3297-41a1-a402-dc4837dd723c", "name": "Save Leads to Sheet" }, { "parameters": { "jsCode": "// This array will hold all parsed leads\nconst leads = [];\n\n// Simple regex to find emails in text\nconst emailRegex = /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-z]{2,}/gi;\n\n// Loop over the 'organic_results' array from SerpAPI\nfor (const result of items[0].json.organic_results || []) {\n\n // Extract title, link, and snippet from each search result\n const nameAndRole = result.title || \"\"; // e.g. \"Jane Doe - SaaS Founder\"\n const link = result.link || \"\"; // LinkedIn profile URL\n const connections = result.displayed_link || \"\"; // 590+ followers\n const snippet = result.snippet || \"\"; // Description snippet from Google\n const extensions = result.rich_snippet?.top?.extensions || []; // Additional info, often includes company\n\n // Split title into name and role (based on \" - \")\n const [namePart, rolePart] = nameAndRole.split(\" - \");\n\n // Try to get company name from extensions (usually in 3rd position)\n let company = \"\";\n if (extensions.length >= 3 && typeof extensions[2] === \"string\") {\n company = extensions[2].trim(); // Safe trim only if it's a string\n }\n\n // Try to extract email from snippet using regex\n let emails = snippet.match(emailRegex);\n // Use the first email if available, else empty string\n let email = (emails && emails.length > 0) ? emails[0].trim() : \"\";\n\n // Push the cleaned lead data into the leads array\n leads.push({\n json: {\n name: namePart?.trim() || \"\", // Safely trim name\n role: rolePart?.trim() || \"\", // Safely trim role\n company: company, // Already trimmed\n connections: connections,\n linkedinUrl: link,\n email: email, // Extracted email if found\n snippet: snippet,\n scrapedAt: new Date().toISOString() // Timestamp when scraped\n }\n });\n}\n\n// Return all extracted leads to the next node\nreturn leads;\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 960, 0 ], "id": "66e6d166-5464-4a85-b023-4eb028ee9e89", "name": "Extract Lead Data" }, { "parameters": { "options": {} }, "type": "@n8n/n8n-nodes-langchain.chatTrigger", "typeVersion": 1.1, "position": [ 0, 0 ], "id": "7e79c859-d061-4f02-9b00-bd57f6669d38", "name": "Lead Request" } ], "connections": { "OpenAI Chat Model": { "ai_languageModel": [ [ { "node": "AI Search Planner", "type": "ai_languageModel", "index": 0 } ] ] }, "Structured Output": { "ai_outputParser": [ [ { "node": "AI Search Planner", "type": "ai_outputParser", "index": 0 } ] ] }, "AI Search Planner": { "main": [ [ { "node": "Build LinkedIn Query", "type": "main", "index": 0 } ] ] }, "Build LinkedIn Query": { "main": [ [ { "node": "Google Search (SerpAPI)", "type": "main", "index": 0 } ] ] }, "Google Search (SerpAPI)": { "main": [ [ { "node": "Extract Lead Data", "type": "main", "index": 0 } ] ] }, "Extract Lead Data": { "main": [ [ { "node": "Save Leads to Sheet", "type": "main", "index": 0 } ] ] }, "Lead Request": { "main": [ [ { "node": "AI Search Planner", "type": "main", "index": 0 } ] ] } }, "settings": { "executionOrder": "v1" }, "pinData": {} }