{ "id": "c5nWQIik9zbV5gHF", "meta": { "templateCredsSetupCompleted": true }, "name": "SEO Page Auditing with Decodo Scraper, GPT and Gmail Report", "tags": [], "nodes": [ { "id": "a03e179c-c098-4509-87bb-666963a91c63", "name": "When clicking \u2018Execute workflow\u2019", "type": "n8n-nodes-base.manualTrigger", "position": [ 640, 496 ], "parameters": {}, "typeVersion": 1 }, { "id": "4a313de4-ee02-46c8-b403-05cd52262d28", "name": "\ud83d\udcdd OVERVIEW", "type": "n8n-nodes-base.stickyNote", "position": [ -48, -64 ], "parameters": { "color": "#E6F4EA", "width": 520, "height": 864, "content": "## AI SEO Watchdog \u2014 Overview & Configuration\n\nThis workflow automatically audits web pages for SEO and generates an **executive-friendly SEO summary** for each page.\n\nIt reads URLs from Google Sheets, scrapes the page content using **Decodo**, reduces the raw HTML to key SEO elements, and analyzes them with an AI Agent. \nThe result is a structured SEO report with issues, quick wins, and recommendations, which is then:\n- Stored in Google Sheets\n- Sent by email as a formatted executive summary (Gmail)\n\n### How to configure it\n\n1. **Google Sheets**\n - Create one sheet with input URLs (one URL per row)\n - Create another sheet to store SEO results\n\n2. **Decodo**\n - Add your Decodo API credentials\n - The URL field is automatically taken from the input sheet \n[Decodo \u2013 Web Scraper for n8n](https://visit.decodo.com/raqXGD)\n\n3. **AI Agent**\n - Connect your LLM credentials (e.g. OpenAI or Gemini)\n - The prompt is already optimized for executive SEO summaries\n\n4. **Gmail**\n - Connect your Gmail account\n - Set the recipient email address\n - The email is sent in HTML format with clear formatting\n\nThe workflow can be executed manually or scheduled for continuous SEO monitoring." }, "typeVersion": 1 }, { "id": "02243c4d-7527-4de7-b40b-eb9f884ccb33", "name": "\ud83d\udcdd DECODE NOTE", "type": "n8n-nodes-base.stickyNote", "position": [ 656, 336 ], "parameters": { "color": 7, "width": 420, "height": 124, "content": "### Content Extraction \nURLs are read from Google Sheets.\nEach page is scraped using Decodo to reliably fetch the HTML content." }, "typeVersion": 1 }, { "id": "9a92dfdf-2d42-458b-bbd2-d4e0981057ff", "name": "\ud83d\udcdd AI AGENT NOTE", "type": "n8n-nodes-base.stickyNote", "position": [ 1264, 208 ], "parameters": { "color": 7, "width": 564, "height": 96, "content": "### AI Analysis\nJavaScript reduces the HTML to key SEO elements.\nThe AI Agent analyzes the data and generates an executive SEO summary." }, "typeVersion": 1 }, { "id": "25abeabc-5c44-48be-9fa3-612ed7c758df", "name": "\ud83d\udcdd PARSE & REPAIR", "type": "n8n-nodes-base.stickyNote", "position": [ 1936, 208 ], "parameters": { "color": 7, "width": 520, "height": 116, "content": "### Data Output \n\nResults are saved to Google Sheets.\nA formatted SEO summary is sent by email using Gmail.\n\n" }, "typeVersion": 1 }, { "id": "8b53cb51-5e11-4583-8564-f96771149446", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 1840, 592 ], "parameters": { "model": { "__rl": true, "mode": "list", "value": "gpt-4.1-mini", "cachedResultName": "gpt-4.1-mini" }, "options": {}, "builtInTools": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.3 }, { "id": "ebf24d14-429d-4dd3-b92f-587929c411d2", "name": "Decodo", "type": "@decodo/n8n-nodes-decodo.decodo", "position": [ 1312, 368 ], "parameters": { "url": "={{ $('Fetch URLs from Google Sheet').item.json.urls }}" }, "credentials": { "decodoApi": { "name": "" } }, "typeVersion": 1 }, { "id": "1df70380-51cb-4043-997f-9a9117e6491d", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ 608, -64 ], "parameters": { "color": 7, "width": 336, "height": 352, "content": "## Input![txt](https://ik.imagekit.io/agbb7sr41/input.png)" }, "typeVersion": 1 }, { "id": "9663551a-828e-400a-a1f1-fe0cdf1e8679", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ 2560, -240 ], "parameters": { "color": 7, "width": 832, "height": 512, "content": "## Email\n![txt](https://ik.imagekit.io/agbb7sr41/send_email.png)" }, "typeVersion": 1 }, { "id": "6a5b45be-938f-4f91-9ac3-687293dabf38", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ 2624, 320 ], "parameters": { "color": 7, "width": 800, "height": 240, "content": "## Google sheet\n\n![txt](https://ik.imagekit.io/agbb7sr41/output_seo_watachdog.png)" }, "typeVersion": 1 }, { "id": "01bb0573-68c1-4fb9-bada-5cd757be4097", "name": "Process URLs one by one", "type": "n8n-nodes-base.splitInBatches", "position": [ 1088, 496 ], "parameters": { "options": {} }, "typeVersion": 3 }, { "id": "bdcf3fce-7872-4776-b41b-7bc7ff37e7db", "name": "Extract SEO Elements from HTML", "type": "n8n-nodes-base.code", "position": [ 1536, 368 ], "parameters": { "jsCode": "/**\n * PRE-EXTRACT SEO (HTML -> compact payload)\n * Reads: $json.results[0].content\n * Returns: seo_compact_text + seo_fields\n */\n\nfunction decodeHtml(s) {\n if (!s || typeof s !== \"string\") return s;\n return s\n .replace(/&/g, \"&\")\n .replace(/"/g, '\"')\n .replace(/'/g, \"'\")\n .replace(/</g, \"<\")\n .replace(/>/g, \">\")\n .replace(/>/g, \">\")\n .replace(/&#(\\d+);/g, (_, code) => String.fromCharCode(Number(code)));\n}\n\nfunction cleanSpaces(s) {\n return (s || \"\")\n .replace(/\\s+/g, \" \")\n .trim();\n}\n\nfunction stripTags(html) {\n return cleanSpaces(\n (html || \"\")\n .replace(//gi, \" \")\n .replace(//gi, \" \")\n .replace(//g, \" \")\n .replace(/<[^>]*>/g, \" \")\n );\n}\n\nfunction getFirstMatch(html, regex) {\n const m = html.match(regex);\n return m ? decodeHtml(m[1]).trim() : null;\n}\n\nfunction getAllMatches(html, regex, limit = 20) {\n const out = [];\n let m;\n while ((m = regex.exec(html)) !== null) {\n out.push(decodeHtml(m[1]).trim());\n if (out.length >= limit) break;\n }\n return out;\n}\n\nfunction truncate(s, maxChars) {\n if (!s) return \"\";\n return s.length > maxChars ? s.slice(0, maxChars) + \"\u2026\" : s;\n}\n\nconst html = $json?.results?.[0]?.content;\nif (!html || typeof html !== \"string\") {\n return [{\n json: {\n seo_compact_text: \"NO_HTML_INPUT\",\n seo_fields: { title: null, meta_description: null, h1: null, h2: [], canonical: null, og_title: null, og_description: null, text_excerpt: \"\" }\n }\n }];\n}\n\n// Basic head elements\nconst title = getFirstMatch(html, /]*>([\\s\\S]*?)<\\/title>/i);\nconst meta_description =\n getFirstMatch(html, /]*name=[\"']description[\"'][^>]*content=[\"']([^\"']*)[\"']/i) ||\n getFirstMatch(html, /]*content=[\"']([^\"']*)[\"'][^>]*name=[\"']description[\"']/i);\n\nconst canonical =\n getFirstMatch(html, /]*rel=[\"']canonical[\"'][^>]*href=[\"']([^\"']+)[\"']/i) ||\n getFirstMatch(html, /]*href=[\"']([^\"']+)[\"'][^>]*rel=[\"']canonical[\"']/i);\n\n// OG tags\nconst og_title =\n getFirstMatch(html, /]*property=[\"']og:title[\"'][^>]*content=[\"']([^\"']*)[\"']/i) ||\n getFirstMatch(html, /]*content=[\"']([^\"']*)[\"'][^>]*property=[\"']og:title[\"']/i);\n\nconst og_description =\n getFirstMatch(html, /]*property=[\"']og:description[\"'][^>]*content=[\"']([^\"']*)[\"']/i) ||\n getFirstMatch(html, /]*content=[\"']([^\"']*)[\"'][^>]*property=[\"']og:description[\"']/i);\n\n// H1/H2 (simple regex extraction)\nconst h1 = getFirstMatch(html, /]*>([\\s\\S]*?)<\\/h1>/i);\nconst h2 = getAllMatches(html, /]*>([\\s\\S]*?)<\\/h2>/gi, 15).map(x => cleanSpaces(stripTags(x))).filter(Boolean);\n\n// Visible text excerpt (limited)\nconst visibleText = stripTags(html);\nconst text_excerpt = truncate(visibleText, 6000);\n\n// Build compact text for LLM\nconst lines = [];\nlines.push(\"SEO_PAGE_EXTRACT\");\nlines.push(\"---\");\nlines.push(`TITLE: ${title || \"null\"}`);\nlines.push(`META_DESCRIPTION: ${meta_description || \"null\"}`);\nlines.push(`CANONICAL: ${canonical || \"null\"}`);\nlines.push(`H1: ${h1 ? cleanSpaces(stripTags(h1)) : \"null\"}`);\nlines.push(`H2: ${h2.length ? h2.join(\" | \") : \"null\"}`);\nlines.push(`OG_TITLE: ${og_title || \"null\"}`);\nlines.push(`OG_DESCRIPTION: ${og_description || \"null\"}`);\nlines.push(\"---\");\nlines.push(\"VISIBLE_TEXT_EXCERPT:\");\nlines.push(text_excerpt || \"\");\n\nreturn [{\n json: {\n seo_compact_text: lines.join(\"\\n\"),\n seo_fields: {\n title,\n meta_description,\n canonical,\n h1: h1 ? cleanSpaces(stripTags(h1)) : null,\n h2,\n og_title,\n og_description,\n text_excerpt\n }\n }\n}];\n" }, "typeVersion": 2 }, { "id": "3d561a6f-3b1b-481b-a50c-416a25092b6d", "name": "Generate AI SEO Executive Summary", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ 1760, 368 ], "parameters": { "text": "={{ $json.seo_compact_text }}", "options": { "systemMessage": "You are an SEO auditor producing an executive summary for non-technical stakeholders.\n\nInput is a compact SEO extract:\nTITLE, META_DESCRIPTION, CANONICAL, H1/H2, and a short visible-text excerpt.\n\nReturn ONLY valid JSON:\n{\n \"overall_status\": \"good\"|\"needs_attention\"|\"critical\",\n \"top_issues\": [string], // max 5 bullets, short\n \"quick_wins\": [string], // max 5 bullets, actionable\n \"title_recommendation\": string|null,\n \"meta_description_recommendation\": string|null,\n \"notes\": string|null // 1\u20132 lines\n}\n\nRules:\n- Keep it short and executive-friendly.\n- No markdown, no emojis.\n- If info is missing, explain briefly in notes.\n" }, "promptType": "define" }, "typeVersion": 3 }, { "id": "7ee090c1-de05-4a8e-a501-69854521d0ce", "name": "Parse & Validate AI JSON Output", "type": "n8n-nodes-base.code", "position": [ 2112, 368 ], "parameters": { "jsCode": "// Input esperado: items[0].json.output (string con ```json ... ```)\n// Output: 1 item con el JSON ya parseado en items[0].json\n\nfunction stripCodeFences(s) {\n if (!s || typeof s !== 'string') return s;\n // Quita ```json ... ``` o ``` ... ```\n return s.replace(/^```(?:json)?\\s*/i, '').replace(/\\s*```$/i, '').trim();\n}\n\nfunction extractFirstJSONObject(s) {\n // Extrae el primer bloque {...} v\u00e1lido\n const start = s.indexOf('{');\n const end = s.lastIndexOf('}');\n if (start === -1 || end === -1 || end <= start) throw new Error('No JSON object braces found');\n return s.slice(start, end + 1);\n}\n\nconst out = [];\nfor (const item of items) {\n let raw = item.json.output ?? item.json ?? '';\n if (typeof raw !== 'string') raw = JSON.stringify(raw);\n\n // Si viene envuelto en array tipo [ { output: \"...\" } ], deshazlo\n // (por si te llega el array entero aqu\u00ed)\n if (Array.isArray(item.json) && item.json.length && item.json[0].output) {\n raw = item.json[0].output;\n }\n\n raw = stripCodeFences(raw);\n const jsonStr = extractFirstJSONObject(raw);\n\n let parsed;\n try {\n parsed = JSON.parse(jsonStr);\n } catch (e) {\n // Intento de \u201crepair\u201d sencillo: elimina BOM y comas colgantes comunes\n const repaired = jsonStr\n .replace(/^\\uFEFF/, '')\n .replace(/,\\s*}/g, '}')\n .replace(/,\\s*]/g, ']');\n parsed = JSON.parse(repaired);\n }\n\n out.push({ json: parsed });\n}\nreturn out;\n" }, "typeVersion": 2 }, { "id": "1e82b9a5-ddc6-4b4e-84df-0dc201ebdd00", "name": "Save SEO Report to Google Sheets1", "type": "n8n-nodes-base.googleSheets", "position": [ 2560, 496 ], "parameters": { "columns": { "value": { "notes": "={{ $('Parse & Validate AI JSON Output').item.json.notes }}", "status": "={{ $('Parse & Validate AI JSON Output').item.json.overall_status }}", "brand_url": "={{ $('Fetch URLs from Google Sheet').item.json.urls }}", "quick_wins": "={{ $('Parse & Validate AI JSON Output').item.json.quick_wins }}", "top_issues": "={{ $('Parse & Validate AI JSON Output').item.json.top_issues }}", "meta_description": "={{ $('Parse & Validate AI JSON Output').item.json.meta_description_recommendation }}", "title_recommendation": "={{ $('Parse & Validate AI JSON Output').item.json.title_recommendation }}" }, "schema": [ { "id": "brand_url", "type": "string", "display": true, "removed": false, "required": false, "displayName": "brand_url", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "status", "type": "string", "display": true, "removed": false, "required": false, "displayName": "status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "top_issues", "type": "string", "display": true, "removed": false, "required": false, "displayName": "top_issues", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "quick_wins", "type": "string", "display": true, "removed": false, "required": false, "displayName": "quick_wins", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "title_recommendation", "type": "string", "display": true, "removed": false, "required": false, "displayName": "title_recommendation", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "meta_description", "type": "string", "display": true, "removed": false, "required": false, "displayName": "meta_description", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "notes", "type": "string", "display": true, "removed": false, "required": false, "displayName": "notes", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "append", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1LPYN31Dtt5ZFF39yB4mJDvRG40Ga2sow_MlLcNx_DOg/edit#gid=0", "cachedResultName": "Hoja 1" }, "documentId": { "__rl": true, "mode": "list", "value": "1LPYN31Dtt5ZFF39yB4mJDvRG40Ga2sow_MlLcNx_DOg", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1LPYN31Dtt5ZFF39yB4mJDvRG40Ga2sow_MlLcNx_DOg/edit?usp=drivesdk", "cachedResultName": "SEO Analyzer" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "a53ecfff-8e78-4ee0-8b76-6fe32ec92e71", "name": "Send SEO Report by Email", "type": "n8n-nodes-base.gmail", "position": [ 2336, 368 ], "parameters": { "sendTo": "user@example.com", "message": "=

Hi,

\n\n

\nHere is the latest SEO Watchdog executive summary for:\n
\nthis page\n

\n\n
\n\n

\nStatus:\nNeeds attention\n

\n\n

\ud83d\udd0e Top issues

\n
    \n
  • Title is too long and may be truncated in search results
    • \n
  • Meta description is lengthy and lacks clear calls-to-action
    • \n
  • H1 is generic and does not strongly reflect primary keywords
    • \n
  • Canonical URL points only to homepage, no specific page URL provided
    • \n
  • H2 headings are numerous and unfocused, reducing clarity
    • \n
\n\n

\u26a1 Quick wins

\n
    \n
  • Shorten the title to under 60 characters focusing on the main keyword
    • \n
  • Rewrite the meta description to under 160 characters with clear benefits and CTAs
    • \n
  • Refine the H1 to better reflect primary keywords and user intent
    • \n
  • Ensure the canonical URL matches the specific page URL
    • \n
  • Consolidate H2 tags to emphasize main offerings and keywords
    • \n
\n\n

\ud83c\udff7\ufe0f Recommended title

\n

\nBest API for Historical Stock Market Prices & Financial Data | Free Trial\n

\n\n

\ud83d\udcdd Recommended meta description

\n

\nAccess historical and real-time stock prices for 150,000+ tickers with flexible plans.\nStart your free trial today.\n

\n\n

\ud83d\udccc Notes

\n

\nSEO elements are present but need refinement for optimal search visibility and user engagement.\nVisible text content is comprehensive but dense.\n

\n\n
\n\n

\n\u2014 Sent automatically by n8n SEO Watchdog
\nhttps://n8n.io\n

", "options": {}, "subject": "=SEO Watchdog Report \u2014 {{$now}}" }, "credentials": { "gmailOAuth2": { "name": "" } }, "typeVersion": 2.2 }, { "id": "47b3a83e-ec11-47b7-9eaa-6ed5b2057ccb", "name": "Fetch URLs from Google Sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 864, 496 ], "parameters": { "options": { "dataLocationOnSheet": { "values": { "rangeDefinition": "specifyRange" } } }, "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mIVyGQXXVR92IhlvaQfdlGqJEU0lsJHHmlZONyMzU9c/edit#gid=0", "cachedResultName": "Hoja 1" }, "documentId": { "__rl": true, "mode": "list", "value": "1mIVyGQXXVR92IhlvaQfdlGqJEU0lsJHHmlZONyMzU9c", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1mIVyGQXXVR92IhlvaQfdlGqJEU0lsJHHmlZONyMzU9c/edit?usp=drivesdk", "cachedResultName": "urls_to_scrape" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "d848ed4c-1a33-4f90-bc5a-890b9638fce1", "connections": { "Decodo": { "main": [ [ { "node": "Extract SEO Elements from HTML", "type": "main", "index": 0 } ] ] }, "OpenAI Chat Model": { "ai_languageModel": [ [ { "node": "Generate AI SEO Executive Summary", "type": "ai_languageModel", "index": 0 } ] ] }, "Process URLs one by one": { "main": [ [], [ { "node": "Decodo", "type": "main", "index": 0 } ] ] }, "Send SEO Report by Email": { "main": [ [ { "node": "Save SEO Report to Google Sheets1", "type": "main", "index": 0 } ] ] }, "Fetch URLs from Google Sheet": { "main": [ [ { "node": "Process URLs one by one", "type": "main", "index": 0 } ] ] }, "Extract SEO Elements from HTML": { "main": [ [ { "node": "Generate AI SEO Executive Summary", "type": "main", "index": 0 } ] ] }, "Parse & Validate AI JSON Output": { "main": [ [ { "node": "Send SEO Report by Email", "type": "main", "index": 0 } ] ] }, "Generate AI SEO Executive Summary": { "main": [ [ { "node": "Parse & Validate AI JSON Output", "type": "main", "index": 0 } ] ] }, "Save SEO Report to Google Sheets1": { "main": [ [ { "node": "Process URLs one by one", "type": "main", "index": 0 } ] ] }, "When clicking \u2018Execute workflow\u2019": { "main": [ [ { "node": "Fetch URLs from Google Sheet", "type": "main", "index": 0 } ] ] } } }