{ "edges": [ { "to": "fetch-pages", "from": "check-has-stale", "toPort": "0", "fromPort": "0" }, { "to": "send-digest", "from": "build-email-body", "toPort": "0", "fromPort": "0" }, { "to": "save-report", "from": "build-report", "toPort": "0", "fromPort": "0" }, { "to": "build-email-body", "from": "aggregate-for-email", "toPort": "0", "fromPort": "0" }, { "to": "ai-content-review", "from": "extract-text", "toPort": "0", "fromPort": "0" }, { "to": "parse-sitemap", "from": "fetch-sitemap", "toPort": "0", "fromPort": "0" }, { "to": "ai-content-review", "from": "openai-model-3", "toPort": "0", "fromPort": "ai_languageModel" }, { "to": "extract-text", "from": "fetch-pages", "toPort": "0", "fromPort": "0" }, { "to": "check-has-stale", "from": "parse-sitemap", "toPort": "0", "fromPort": "0" }, { "to": "fetch-sitemap", "from": "config", "toPort": "0", "fromPort": "0" }, { "to": "config", "from": "weekly-trigger", "toPort": "0", "fromPort": "0" }, { "to": "aggregate-for-email", "from": "save-report", "toPort": "0", "fromPort": "0" }, { "to": "build-report", "from": "ai-content-review", "toPort": "0", "fromPort": "0" } ], "nodes": [ { "id": "weekly-trigger", "name": "Weekly Scan (Monday 7 AM)", "type": "trigger", "params": { "kind": "n8n-nodes-base.scheduleTrigger", "rule": { "interval": [ { "field": "cronExpression", "expression": "0 7 * * 1" } ] } }, "position": [ -16, 240 ] }, { "id": "config", "name": "Site Configuration", "type": "set", "params": { "options": {}, "assignments": { "assignments": [ { "id": "sitemap-url", "name": "sitemapUrl", "type": "string", "value": "https://yoursite.com/sitemap.xml" }, { "id": "stale-days", "name": "staleDays", "type": "number", "value": 180 }, { "id": "alert-email", "name": "alertEmail", "type": "string", "value": "user@example.com" } ] } }, "position": [ 208, 240 ] }, { "id": "fetch-sitemap", "name": "Fetch Sitemap XML", "type": "http", "params": { "url": "={{ $json.sitemapUrl }}", "options": { "response": { "response": { "responseFormat": "text" } } } }, "position": [ 432, 240 ] }, { "id": "parse-sitemap", "name": "Parse Sitemap URLs", "type": "code", "params": { "jsCode": "const xml = $input.first().json.data || $input.first().json.body || '';\nconst staleDays = $('Site Configuration').first().json.staleDays || 180;\nconst alertEmail = $('Site Configuration').first().json.alertEmail;\n\n// Parse URLs and lastmod dates from sitemap XML\nconst urlRegex = /([\\s\\S]*?)<\\/url>/g;\nconst locRegex = /([^<]+)<\\/loc>/;\nconst lastmodRegex = /([^<]+)<\\/lastmod>/;\n\nconst pages = [];\nlet match;\n\nwhile ((match = urlRegex.exec(xml)) !== null) {\n const block = match[1];\n const locMatch = block.match(locRegex);\n const lastmodMatch = block.match(lastmodRegex);\n \n if (locMatch) {\n const url = locMatch[1];\n const lastmod = lastmodMatch ? lastmodMatch[1] : null;\n \n let isStale = false;\n let daysSinceUpdate = null;\n \n if (lastmod) {\n const lastModDate = new Date(lastmod);\n const now = new Date();\n daysSinceUpdate = Math.floor((now - lastModDate) / (1000 * 60 * 60 * 24));\n isStale = daysSinceUpdate > staleDays;\n } else {\n // No lastmod = potentially stale, flag for review\n isStale = true;\n daysSinceUpdate = -1; // Unknown\n }\n \n if (isStale) {\n pages.push({\n json: {\n url,\n lastModified: lastmod || 'unknown',\n daysSinceUpdate,\n staleDays,\n alertEmail\n }\n });\n }\n }\n}\n\n// Sort by staleness (most stale first)\npages.sort((a, b) => b.json.daysSinceUpdate - a.json.daysSinceUpdate);\n\n// Limit to top 20 for AI analysis\nreturn pages.slice(0, 20);" }, "position": [ 656, 240 ] }, { "id": "check-has-stale", "name": "Any Stale Pages?", "type": "if", "params": { "options": {}, "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "loose" }, "combinator": "and", "conditions": [ { "id": "has-pages", "operator": { "type": "number", "operation": "gt" }, "leftValue": "={{ $input.all().length }}", "rightValue": 0 } ] }, "looseTypeValidation": true }, "position": [ 864, 240 ] }, { "id": "fetch-pages", "name": "Fetch Page Content", "type": "http", "params": { "url": "={{ $json.url }}", "options": { "timeout": 10000, "response": { "response": { "responseFormat": "text" } } } }, "position": [ 1088, 176 ] }, { "id": "extract-text", "name": "Extract Page Text", "type": "passthrough", "params": { "mode": "noOp", "options": {}, "operation": "extractHtmlContent", "extractionValues": { "values": [ { "key": "title", "cssSelector": "title" }, { "key": "body", "cssSelector": "body" } ] } }, "position": [ 1312, 176 ] }, { "id": "ai-content-review", "name": "AI Content Freshness Analyzer", "type": "llm", "params": { "text": "=Review this webpage for content freshness. The page was last updated {{ $('Parse Sitemap URLs').item.json.daysSinceUpdate }} days ago.\n\nURL: {{ $('Parse Sitemap URLs').item.json.url }}\nTitle: {{ $json.title || 'No title found' }}\nContent preview (first 1000 chars): {{ ($json.body || 'Could not extract content').substring(0, 1000) }}\n\nAnalyze:\n1. Does the content contain outdated references (old dates, deprecated tools, old pricing, dead links)?\n2. Is the topic still relevant or has the industry moved on?\n3. Priority level for refresh: LOW (still accurate), MEDIUM (some outdated elements), HIGH (significantly outdated), CRITICAL (misleading or wrong)\n4. Specific suggestions for what to update\n\nKeep your response to 4-5 sentences max.", "prompt": "=Review this webpage for content freshness. The page was last updated {{ $('Parse Sitemap URLs').item.json.daysSinceUpdate }} days ago.\n\nURL: {{ $('Parse Sitemap URLs').item.json.url }}\nTitle: {{ $json.title || 'No title found' }}\nContent preview (first 1000 chars): {{ ($json.body || 'Could not extract content').substring(0, 1000) }}\n\nAnalyze:\n1. Does the content contain outdated references (old dates, deprecated tools, old pricing, dead links)?\n2. Is the topic still relevant or has the industry moved on?\n3. Priority level for refresh: LOW (still accurate), MEDIUM (some outdated elements), HIGH (significantly outdated), CRITICAL (misleading or wrong)\n4. Specific suggestions for what to update\n\nKeep your response to 4-5 sentences max.", "options": { "systemMessage": "You are a content strategist who audits web pages for freshness and accuracy. Be practical and specific in your recommendations. Only flag things that genuinely need updating." }, "provider": "openai", "promptType": "define", "approximated": true, "systemMessage": "You are a content strategist who audits web pages for freshness and accuracy. Be practical and specific in your recommendations. Only flag things that genuinely need updating." }, "position": [ 1520, 176 ] }, { "id": "openai-model-3", "name": "OpenAI Chat Model", "type": "llm", "params": { "model": "gpt-4o-mini", "options": {}, "provider": "openai", "builtInTools": {} }, "position": [ 1536, 400 ] }, { "id": "build-report", "name": "Build Report Row", "type": "set", "params": { "options": {}, "assignments": { "assignments": [ { "id": "url", "name": "pageUrl", "type": "string", "value": "={{ $('Parse Sitemap URLs').item.json.url }}" }, { "id": "last-mod", "name": "lastModified", "type": "string", "value": "={{ $('Parse Sitemap URLs').item.json.lastModified }}" }, { "id": "days-stale", "name": "daysSinceUpdate", "type": "number", "value": "={{ $('Parse Sitemap URLs').item.json.daysSinceUpdate }}" }, { "id": "ai-review", "name": "aiReview", "type": "string", "value": "={{ $json.output }}" } ] } }, "position": [ 1824, 176 ] }, { "id": "save-report", "name": "Save to Content Audit Sheet", "type": "integration", "params": { "columns": { "value": { "page_url": "={{ $json.pageUrl }}", "ai_review": "={{ $json.aiReview }}", "scan_date": "={{ $now.toISO() }}", "last_modified": "={{ $json.lastModified }}", "days_since_update": "={{ $json.daysSinceUpdate }}" }, "schema": [ { "id": "scan_date", "type": "string", "display": true, "required": false, "displayName": "scan_date" }, { "id": "page_url", "type": "string", "display": true, "required": false, "displayName": "page_url" }, { "id": "last_modified", "type": "string", "display": true, "required": false, "displayName": "last_modified" }, { "id": "days_since_update", "type": "string", "display": true, "required": false, "displayName": "days_since_update" }, { "id": "ai_review", "type": "string", "display": true, "required": false, "displayName": "ai_review" } ], "mappingMode": "defineBelow", "matchingColumns": [] }, "options": {}, "service": "googleSheets", "operation": "append", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1QUsgMCHaiJ7mfnVhMUYqHA9_2YEIUKXRxNvOfwFsgYE/edit#gid=0", "cachedResultName": "ContentAudit" }, "documentId": { "__rl": true, "mode": "url", "value": "https://docs.google.com/spreadsheets/d/1QUsgMCHaiJ7mfnVhMUYqHA9_2YEIUKXRxNvOfwFsgYE/edit?gid=0#gid=0" } }, "position": [ 2032, 176 ] }, { "id": "send-digest", "name": "Email Content Audit Report", "type": "integration", "params": { "sendTo": "={{ $('Site Configuration').first().json.alertEmail }}", "message": "={{ $json.emailBody }}", "options": {}, "service": "gmail", "subject": "=Weekly Stale Content Report - {{ $now.format('yyyy-MM-dd') }}", "operation": "read" }, "position": [ 2624, 176 ] }, { "id": "aggregate-for-email", "name": "Combine Into One", "type": "passthrough", "params": { "mode": "aggregate", "options": {}, "aggregate": "aggregateAllItemData" }, "position": [ 2240, 176 ] }, { "id": "build-email-body", "name": "Build Email Body", "type": "code", "params": { "jsCode": "const items = $input.first().json.data || [];\nconst staleDays = $('Site Configuration').first().json.staleDays || 180;\nconst totalPages = items.length;\n\nlet html = `\n

Stale Content Audit Report

Pages flagged for review: ${totalPages}

\n`;\n\nif (totalPages === 0) {\n html += '

No stale pages found. Your content is looking fresh!

';\n} else {\n for (let i = 0; i < totalPages; i++) {\n const page = items[i];\n const url = page.page_url || 'Unknown';\n const urlPath = url.replace(/^https?:\\/\\/[^/]+/, '') || '/';\n const days = page.days_since_update;\n const daysText = days && days > 0 ? `${days} days ago` : 'Unknown';\n const review = page.ai_review || 'No review available';\n \n // Color code by staleness\n let badgeColor = '#e67e22'; // orange default\n if (days > 365) badgeColor = '#e74c3c'; // red\n else if (days > 270) badgeColor = '#e67e22'; // orange\n else badgeColor = '#f1c40f'; // yellow\n \n html += `\n

${i + 1}. ${urlPath}

Last updated: ${daysText}

${review}

`;\n }\n}\n\nhtml += `\n

This report checks all pages in your sitemap not updated in over ${staleDays} days.
Full details with AI analysis are in your Google Sheet.

Generated by Stale Content Detector

`;\n\nreturn [{ json: { emailBody: html, totalPages } }];" }, "position": [ 2400, 176 ] } ] }

Detect stale website content with OpenAI, Google Sheets, and Gmail