{ "updatedAt": "2025-12-25T01:31:56.743Z", "createdAt": "2025-12-24T12:13:53.194Z", "id": "iitZ5h0qrXbgxu2R", "name": "03_ANALYST_Website_Scoring", "active": false, "isArchived": false, "nodes": [ { "parameters": { "rule": { "interval": [ { "field": "minutes", "minutesInterval": 1 } ] } }, "type": "n8n-nodes-base.scheduleTrigger", "typeVersion": 1.1, "position": [ -2336, 64 ], "id": "2686e786-4c0b-48be-b5ee-ff3ca4076bf3", "name": "Every 1 Minute", "disabled": true }, { "parameters": { "operation": "getAll", "tableId": "leads", "limit": 5, "matchType": "allFilters", "filters": { "conditions": [ { "keyName": "status", "condition": "eq", "keyValue": "raw" } ] } }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ -2128, 64 ], "id": "20c755ec-bf8f-4edd-a89e-19ff206c211f", "name": "Query Raw Leads", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": { "conditions": { "options": { "caseSensitive": false, "leftValue": "", "typeValidation": "strict" }, "conditions": [ { "id": "check-leads-exist", "leftValue": "={{ $json.length }}", "rightValue": "", "operator": { "type": "number", "operation": "notEmpty" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2, "position": [ -1936, 64 ], "id": "0cf44872-c9da-4ecf-adfd-e7917fe0ab47", "name": "Leads Exist?" }, { "parameters": { "operation": "update", "tableId": "leads" }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ -1728, -48 ], "id": "7453ddfc-6e5d-4c46-b3b0-1dd59b2cd516", "name": "Mark as Enriching", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": { "url": "={{ 'https://' + $json.domain }}", "options": { "allowUnauthorizedCerts": true, "redirect": { "redirect": { "maxRedirects": 3 } }, "timeout": 10000 } }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.1, "position": [ -1536, -48 ], "id": "1156d29a-47cb-41e3-8dd5-d6abd23dfea7", "name": "Fetch Website" }, { "parameters": { "jsCode": "// Get the HTML response and lead data\nconst html = $input.first().json || '';\nconst lead = $('Query Raw Leads').item.json;\n\n// Function to clean HTML\nfunction cleanHTML(html) {\n if (typeof html !== 'string') {\n return '';\n }\n \n // Remove script tags and content\n let cleaned = html.replace(/)<[^<]*)*<\\/script>/gi, '');\n \n // Remove style tags and content\n cleaned = cleaned.replace(/)<[^<]*)*<\\/style>/gi, '');\n \n // Remove HTML tags\n cleaned = cleaned.replace(/<[^>]+>/g, ' ');\n \n // Decode common HTML entities\n cleaned = cleaned\n .replace(/ /g, ' ')\n .replace(/&/g, '&')\n .replace(/</g, '<')\n .replace(/>/g, '>')\n .replace(/"/g, '\"')\n .replace(/'/g, \"'\");\n \n // Remove extra whitespace\n cleaned = cleaned.replace(/\\s+/g, ' ').trim();\n \n return cleaned;\n}\n\n// Function to extract metadata\nfunction extractMetadata(html) {\n const metadata = {\n title: '',\n description: '',\n keywords: []\n };\n \n if (typeof html !== 'string') {\n return metadata;\n }\n \n // Extract title\n const titleMatch = html.match(/]*>([^<]+)<\\/title>/i);\n if (titleMatch) {\n metadata.title = titleMatch[1].trim();\n }\n \n // Extract meta description\n const descMatch = html.match(/]*name=[\"']description[\"'][^>]*content=[\"']([^\"']+)[\"']/i);\n if (descMatch) {\n metadata.description = descMatch[1].trim();\n }\n \n // Extract keywords\n const keywordsMatch = html.match(/]*name=[\"']keywords[\"'][^>]*content=[\"']([^\"']+)[\"']/i);\n if (keywordsMatch) {\n metadata.keywords = keywordsMatch[1].split(',').map(k => k.trim()).filter(Boolean);\n }\n \n return metadata;\n}\n\n// Process the HTML\nconst htmlContent = html.body || html.data || html.toString() || '';\nconst metadata = extractMetadata(htmlContent);\nconst cleanedText = cleanHTML(htmlContent);\n\n// Truncate content to avoid token limits (first 3000 chars)\nconst truncatedText = cleanedText.substring(0, 3000);\n\nconsole.log(`Processed ${lead.domain}: ${cleanedText.length} chars cleaned, ${truncatedText.length} used`);\n\nreturn [{\n json: {\n lead_id: lead.id,\n batch_id: lead.batch_id,\n user_id: lead.user_id,\n domain: lead.domain,\n name: lead.name || 'Unknown',\n \n // Metadata\n title: metadata.title || lead.name || 'No title',\n description: metadata.description || 'No description',\n keywords: metadata.keywords,\n \n // Content for analysis\n content: truncatedText,\n content_length: cleanedText.length,\n \n // Original lead data\n original_lead: lead\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -1328, -48 ], "id": "33a27e5d-6ee2-4e08-846b-b39685161507", "name": "Extract & Clean Content" }, { "parameters": { "method": "POST", "url": "https://api.anthropic.com/v1/messages", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "sendHeaders": true, "headerParameters": { "parameters": [ { "name": "anthropic-version", "value": "2023-06-01" } ] }, "sendBody": true, "specifyBody": "json", "jsonBody": "={\n \"model\": \"claude-3-5-sonnet-20241022\",\n \"max_tokens\": 1024,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Analyze this business website and provide a fit score (0-100) based on the following criteria:\\n\\n**Business Information:**\\n- Name: {{ $json.name }}\\n- Domain: {{ $json.domain }}\\n- Website Title: {{ $json.title }}\\n- Description: {{ $json.description }}\\n\\n**Website Content (first 3000 chars):**\\n{{ $json.content }}\\n\\n**Scoring Criteria:**\\n1. Business Legitimacy (0-25): Is this a real, active business?\\n2. Website Quality (0-25): Professional design, updated content?\\n3. Service Relevance (0-25): Do they offer relevant services?\\n4. Contact Information (0-25): Easy to reach, multiple contact methods?\\n\\n**Response Format (JSON only, no markdown):**\\n{\\n \\\"fit_score\\\": <0-100>,\\n \\\"legitimacy_score\\\": <0-25>,\\n \\\"quality_score\\\": <0-25>,\\n \\\"relevance_score\\\": <0-25>,\\n \\\"contact_score\\\": <0-25>,\\n \\\"summary\\\": \\\"<2-3 sentence summary>\\\",\\n \\\"pros\\\": [\\\"\\\", \\\"\\\"],\\n \\\"cons\\\": [\\\"\\\", \\\"\\\"],\\n \\\"recommended_action\\\": \\\"contact|research_more|skip\\\"\\n}\"\n }\n ]\n}", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.1, "position": [ -768, -32 ], "id": "a2afb20f-742c-4c04-8d71-68cb7151e85a", "name": "Claude Analysis", "credentials": { "httpHeaderAuth": { "name": "" } }, "disabled": true }, { "parameters": { "jsCode": "// Get the LLM response and lead data\nconst llmResponse = $input.first().json;\nconst leadData = $('Extract & Clean Content').item.json;\n\n// Extract content from Claude response\nlet analysisText = '';\nif (llmResponse.content && Array.isArray(llmResponse.content)) {\n analysisText = llmResponse.content\n .filter(block => block.type === 'text')\n .map(block => block.text)\n .join('\\n');\n} else if (typeof llmResponse === 'string') {\n analysisText = llmResponse;\n}\n\nconsole.log('LLM Response:', analysisText.substring(0, 200));\n\n// Parse JSON from response\nlet analysis;\ntry {\n // Remove markdown code blocks if present\n let cleanedText = analysisText.replace(/```json\\n?/g, '').replace(/```\\n?/g, '');\n \n // Find JSON object\n const jsonMatch = cleanedText.match(/\\{[\\s\\S]*\\}/);\n if (jsonMatch) {\n analysis = JSON.parse(jsonMatch[0]);\n } else {\n throw new Error('No JSON found in response');\n }\n} catch (e) {\n console.error('Failed to parse LLM response:', e.message);\n \n // Fallback: extract score from text\n const scoreMatch = analysisText.match(/fit[_\\s]*score[:\\s]*(\\d+)/i);\n const score = scoreMatch ? parseInt(scoreMatch[1]) : 50;\n \n analysis = {\n fit_score: score,\n summary: analysisText.substring(0, 500) || 'Analysis failed - using default score',\n pros: ['Unable to extract detailed analysis'],\n cons: ['LLM response parsing failed'],\n recommended_action: 'research_more',\n legitimacy_score: Math.round(score * 0.25),\n quality_score: Math.round(score * 0.25),\n relevance_score: Math.round(score * 0.25),\n contact_score: Math.round(score * 0.25)\n };\n}\n\n// Ensure score is valid (0-100)\nconst fitScore = Math.max(0, Math.min(100, parseInt(analysis.fit_score) || 50));\n\nconsole.log(`Scored ${leadData.domain}: ${fitScore}/100`);\n\nreturn [{\n json: {\n lead_id: leadData.lead_id,\n batch_id: leadData.batch_id,\n domain: leadData.domain,\n \n // Scoring\n fit_score: fitScore,\n legitimacy_score: analysis.legitimacy_score || null,\n quality_score: analysis.quality_score || null,\n relevance_score: analysis.relevance_score || null,\n contact_score: analysis.contact_score || null,\n \n // Analysis\n summary: (analysis.summary || 'No summary available').substring(0, 1000),\n pros: Array.isArray(analysis.pros) ? analysis.pros.slice(0, 5) : [],\n cons: Array.isArray(analysis.cons) ? analysis.cons.slice(0, 5) : [],\n recommended_action: analysis.recommended_action || 'research_more',\n \n // Metadata\n analyzed_at: new Date().toISOString(),\n llm_model: llmResponse.model || 'claude-3-5-sonnet',\n \n // Store full analysis\n full_analysis: analysis\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -560, -32 ], "id": "18303080-9a11-466c-a41d-97b1c2bb94f1", "name": "Parse Analysis" }, { "parameters": { "operation": "update", "tableId": "leads" }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ -368, -32 ], "id": "c53a042d-b2e8-4b77-9484-611c1de814d1", "name": "Update Lead (Scored)", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": { "jsCode": "// Get batch_id from processed lead\nconst batchId = $json.batch_id;\n\nif (!batchId) {\n console.log('No batch_id found, skipping batch check');\n return [];\n}\n\nconsole.log(`Checking completion for batch: ${batchId}`);\n\nreturn [{\n json: {\n batch_id: batchId\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -160, -32 ], "id": "38d827ed-4be3-4d5d-863d-4386b92bc54e", "name": "Check Batch" }, { "parameters": { "operation": "getAll", "tableId": "leads", "returnAll": true, "matchType": "allFilters", "filters": { "conditions": [ { "keyName": "batch_id", "keyValue": "={{ $json.batch_id }}" } ] } }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ 32, -32 ], "id": "1f0a9838-63bc-4bed-a12c-2712fc2aad45", "name": "Query Batch Leads", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": { "jsCode": "// Get all leads in batch\nconst allLeads = $input.all().map(item => item.json);\nconst batchId = $('Check Batch').item.json.batch_id;\n\nif (allLeads.length === 0) {\n console.log('No leads found in batch');\n return [{ json: { complete: false, skip: true } }];\n}\n\n// Count leads by status\nconst statusCounts = {\n raw: 0,\n enriching: 0,\n scored: 0,\n scraping_failed: 0\n};\n\nallLeads.forEach(lead => {\n const status = lead.status || 'unknown';\n if (statusCounts.hasOwnProperty(status)) {\n statusCounts[status]++;\n }\n});\n\n// Batch is complete if no raw or enriching leads remain\nconst isComplete = (statusCounts.raw + statusCounts.enriching) === 0;\n\n// Calculate stats\nconst totalLeads = allLeads.length;\nconst scoredLeads = statusCounts.scored;\n\n// Calculate average score (only for scored leads with valid scores)\nconst scoredLeadsWithScores = allLeads.filter(\n l => l.status === 'scored' && l.fit_score !== null && !isNaN(l.fit_score)\n);\n\nconst avgScore = scoredLeadsWithScores.length > 0\n ? Math.round(\n scoredLeadsWithScores.reduce((sum, l) => sum + parseFloat(l.fit_score), 0) / \n scoredLeadsWithScores.length\n )\n : 0;\n\nconsole.log(`Batch ${batchId}: ${isComplete ? 'COMPLETE' : 'PENDING'}`);\nconsole.log(`Status: Raw=${statusCounts.raw}, Enriching=${statusCounts.enriching}, Scored=${statusCounts.scored}, Failed=${statusCounts.scraping_failed}`);\nconsole.log(`Average score: ${avgScore}`);\n\nreturn [{\n json: {\n batch_id: batchId,\n complete: isComplete,\n total_leads: totalLeads,\n scored_leads: scoredLeads,\n failed_leads: statusCounts.scraping_failed,\n pending_leads: statusCounts.raw + statusCounts.enriching,\n average_score: avgScore,\n status_breakdown: statusCounts\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 240, -32 ], "id": "5384364f-e88e-4ea7-847c-64203923496a", "name": "Calculate Completion" }, { "parameters": { "conditions": { "options": { "caseSensitive": false, "leftValue": "", "typeValidation": "strict" }, "conditions": [ { "id": "batch-complete-check", "leftValue": "={{ $json.complete }}", "rightValue": "true", "operator": { "type": "boolean", "operation": "equals", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2, "position": [ 448, -32 ], "id": "fa695184-8ade-4f63-902e-a5c74b1dde54", "name": "Batch Complete?" }, { "parameters": { "operation": "update", "tableId": "batches" }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ 480, -192 ], "id": "29cd57ff-b91b-49e4-a769-04c011735877", "name": "Update Batch (Complete)", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": {}, "type": "n8n-nodes-base.errorTrigger", "typeVersion": 1, "position": [ -2336, 304 ], "id": "8ff643ac-adb6-4f40-83c2-9b55a5004935", "name": "Error Trigger" }, { "parameters": { "jsCode": "// Handle scraping errors\nconst error = $input.first().json.error || {};\nconst errorNode = error.node || 'unknown';\nconst errorMessage = error.message || 'Unknown error';\n\n// Try to get lead_id from context\nlet leadId = null;\nlet batchId = null;\n\ntry {\n const queryResult = $('Query Raw Leads').item;\n if (queryResult) {\n leadId = queryResult.json.id;\n batchId = queryResult.json.batch_id;\n }\n} catch (e) {\n console.warn('Could not retrieve lead_id from context');\n}\n\nconsole.error('Workflow error:', {\n node: errorNode,\n message: errorMessage,\n lead_id: leadId\n});\n\nreturn [{\n json: {\n lead_id: leadId,\n batch_id: batchId,\n error_node: errorNode,\n error_message: errorMessage.substring(0, 500),\n error_stack: error.stack ? error.stack.substring(0, 1000) : null,\n timestamp: new Date().toISOString()\n }\n}];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ -2128, 304 ], "id": "ac897795-ed5b-4b5f-944c-49e6db00de77", "name": "Log Error" }, { "parameters": { "operation": "update", "tableId": "leads" }, "type": "n8n-nodes-base.supabase", "typeVersion": 1, "position": [ -1936, 304 ], "id": "02ab7e30-15a7-4dde-bdd4-cdd1d18949e2", "name": "Mark Lead Failed", "credentials": { "supabaseApi": { "name": "" } } }, { "parameters": { "modelId": { "__rl": true, "value": "models/gemini-2.5-flash", "mode": "list", "cachedResultName": "models/gemini-2.5-flash" }, "messages": { "values": [ { "content": "=Analyze this business website and provide a fit score (0-100) based on the following criteria:\\n\\n**Business Information:**\\n- Name: {{ $json.name }}\\n- Domain: {{ $json.domain }}\\n- Website Title: {{ $json.title }}\\n- Description: {{ $json.description }}\\n\\n**Website Content (first 3000 chars):**\\n{{ $json.content }}\\n\\n**Scoring Criteria:**\\n1. Business Legitimacy (0-25): Is this a real, active business?\\n2. Website Quality (0-25): Professional design, updated content?\\n3. Service Relevance (0-25): Do they offer relevant services?\\n4. Contact Information (0-25): Easy to reach, multiple contact methods?\\n\\n**Response Format (JSON only, no markdown):**\\n{\\n \\\"fit_score\\\": <0-100>,\\n \\\"legitimacy_score\\\": <0-25>,\\n \\\"quality_score\\\": <0-25>,\\n \\\"relevance_score\\\": <0-25>,\\n \\\"contact_score\\\": <0-25>,\\n \\\"summary\\\": \\\"<2-3 sentence summary>\\\",\\n \\\"pros\\\": [\\\"\\\", \\\"\\\"],\\n \\\"cons\\\": [\\\"\\\", \\\"\\\"],\\n \\\"recommended_action\\\": \\\"contact|research_more|skip\\\"\\n" } ] }, "options": {} }, "type": "@n8n/n8n-nodes-langchain.googleGemini", "typeVersion": 1, "position": [ -1152, -48 ], "id": "636f6354-deb8-4a08-b9ee-6d691cad5274", "name": "Message a model", "credentials": { "googlePalmApi": { "name": "" } } } ], "connections": { "Every 1 Minute": { "main": [ [ { "node": "Query Raw Leads", "type": "main", "index": 0 } ] ] }, "Query Raw Leads": { "main": [ [ { "node": "Leads Exist?", "type": "main", "index": 0 } ] ] }, "Leads Exist?": { "main": [ [ { "node": "Mark as Enriching", "type": "main", "index": 0 } ] ] }, "Mark as Enriching": { "main": [ [ { "node": "Fetch Website", "type": "main", "index": 0 } ] ] }, "Fetch Website": { "main": [ [ { "node": "Extract & Clean Content", "type": "main", "index": 0 } ] ] }, "Extract & Clean Content": { "main": [ [ { "node": "Message a model", "type": "main", "index": 0 } ] ] }, "Claude Analysis": { "main": [ [ { "node": "Parse Analysis", "type": "main", "index": 0 } ] ] }, "Parse Analysis": { "main": [ [ { "node": "Update Lead (Scored)", "type": "main", "index": 0 } ] ] }, "Update Lead (Scored)": { "main": [ [ { "node": "Check Batch", "type": "main", "index": 0 } ] ] }, "Check Batch": { "main": [ [ { "node": "Query Batch Leads", "type": "main", "index": 0 } ] ] }, "Query Batch Leads": { "main": [ [ { "node": "Calculate Completion", "type": "main", "index": 0 } ] ] }, "Calculate Completion": { "main": [ [ { "node": "Batch Complete?", "type": "main", "index": 0 } ] ] }, "Batch Complete?": { "main": [ [ { "node": "Update Batch (Complete)", "type": "main", "index": 0 } ] ] }, "Error Trigger": { "main": [ [ { "node": "Log Error", "type": "main", "index": 0 } ] ] }, "Log Error": { "main": [ [ { "node": "Mark Lead Failed", "type": "main", "index": 0 } ] ] }, "Message a model": { "main": [ [ { "node": "Claude Analysis", "type": "main", "index": 0 } ] ] } }, "settings": { "executionOrder": "v1" }, "staticData": null, "meta": { "templateCredsSetupCompleted": true }, "versionId": "282f42ca-8ae3-4622-9f5c-b9b9eb8e55c5", "activeVersionId": null, "triggerCount": 0, "shared": [ { "updatedAt": "2025-12-24T12:13:53.216Z", "createdAt": "2025-12-24T12:13:53.216Z", "role": "workflow:owner", "workflowId": "iitZ5h0qrXbgxu2R", "projectId": "HHopAZ4lOFgjhBzT" } ], "activeVersion": null, "tags": [] }