Keyword-Cannibalismus mit GPT-4o und Google Search Console erkennen
Experte
Dies ist ein Content Creation, Multimodal AI-Bereich Automatisierungsworkflow mit 27 Nodes. Hauptsächlich werden If, Code, Merge, HttpRequest, GoogleSheets und andere Nodes verwendet. Keyword-Kannibalisierung mit GPT-4o und Google Search Console erkennen
Voraussetzungen
- •Möglicherweise sind Ziel-API-Anmeldedaten erforderlich
- •Google Sheets API-Anmeldedaten
- •OpenAI API Key
Verwendete Nodes (27)
Kategorie
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
"meta": {
"instanceId": "bc8ca75c203589705ae2e446cad7181d6f2a7cc1766f958ef9f34810e53b8cb2"
},
"nodes": [
{
"id": "90168f30-8e88-4b5a-9a80-586ad28f5a8f",
"name": "GSC-Daten nach Keyword gruppieren (Kunde 2)",
"type": "n8n-nodes-base.code",
"notes": "Groups Google Search Console data by keyword for Client 2. Takes raw GSC response and organizes it by keyword, with each keyword containing an array of URLs that rank for it, including position, clicks, impressions, and CTR data.",
"position": [
336,
464
],
"parameters": {
"jsCode": "const grouped = {};\n\nfor (const row of items[0].json.rows) {\n const query = row.keys[0]; // keyword\n const url = row.keys[1]; // page\n \n if (!grouped[query]) grouped[query] = [];\n \n grouped[query].push({\n url,\n position: row.position,\n clicks: row.clicks,\n impressions: row.impressions,\n ctr: row.ctr // CTR added here\n });\n}\n\n// Convert grouped object into array of items for next node\nreturn Object.entries(grouped).map(([keyword, urls]) => ({\n json: { keyword, urls }\n}));"
},
"typeVersion": 2
},
{
"id": "866dd165-dd86-43b9-b24e-e54ade95c42c",
"name": "GSC-Daten nach Keyword gruppieren (Kunde 3)",
"type": "n8n-nodes-base.code",
"notes": "Groups Google Search Console data by keyword for Client 3. Transforms the GSC API response into a keyword-centric structure where each keyword has associated URLs with their ranking metrics.",
"position": [
336,
848
],
"parameters": {
"jsCode": "const grouped = {};\n\nfor (const row of items[0].json.rows) {\n const query = row.keys[0]; // keyword\n const url = row.keys[1]; // page\n \n if (!grouped[query]) grouped[query] = [];\n \n grouped[query].push({\n url,\n position: row.position,\n clicks: row.clicks,\n impressions: row.impressions,\n ctr: row.ctr // CTR added here\n });\n}\n\n// Convert grouped object into array of items for next node\nreturn Object.entries(grouped).map(([keyword, urls]) => ({\n json: { keyword, urls }\n}));"
},
"typeVersion": 2
},
{
"id": "e679fffe-fb2b-4cff-b5a0-104179212ac0",
"name": "GSC-Daten nach Keyword gruppieren (Kunde 4)",
"type": "n8n-nodes-base.code",
"notes": "Groups Google Search Console data by keyword for Client 4. Processes raw GSC data and restructures it to group all URLs ranking for each keyword together with their performance metrics.",
"position": [
336,
1040
],
"parameters": {
"jsCode": "const grouped = {};\n\nfor (const row of items[0].json.rows) {\n const query = row.keys[0]; // keyword\n const url = row.keys[1]; // page\n \n if (!grouped[query]) grouped[query] = [];\n \n grouped[query].push({\n url,\n position: row.position,\n clicks: row.clicks,\n impressions: row.impressions,\n ctr: row.ctr // CTR added here\n });\n}\n\n// Convert grouped object into array of items for next node\nreturn Object.entries(grouped).map(([keyword, urls]) => ({\n json: { keyword, urls }\n}));"
},
"typeVersion": 2
},
{
"id": "7f125793-0b03-4466-b25b-1ef3bb4a76d4",
"name": "GSC-Daten nach Keyword gruppieren (Kunde 1)",
"type": "n8n-nodes-base.code",
"notes": "Groups Google Search Console data by keyword for Client 1. Converts the flat GSC response into a grouped structure where each keyword contains all its ranking URLs with position, clicks, impressions, and CTR.",
"position": [
336,
272
],
"parameters": {
"jsCode": "const grouped = {};\n\nfor (const row of items[0].json.rows) {\n const query = row.keys[0]; // keyword\n const url = row.keys[1]; // page\n \n if (!grouped[query]) grouped[query] = [];\n \n grouped[query].push({\n url,\n position: row.position,\n clicks: row.clicks,\n impressions: row.impressions,\n ctr: row.ctr // CTR added here\n });\n}\n\n// Convert grouped object into array of items for next node\nreturn Object.entries(grouped).map(([keyword, urls]) => ({\n json: { keyword, urls }\n}));"
},
"typeVersion": 2
},
{
"id": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"name": "Alle Kunden-GSC-Daten zusammenführen",
"type": "n8n-nodes-base.merge",
"notes": "Combines GSC data from all 4 clients plus the target keywords from the Google Sheet. This creates a unified dataset containing both the keyword targets and actual GSC performance data.",
"position": [
800,
608
],
"parameters": {
"numberInputs": 5
},
"typeVersion": 3.2
},
{
"id": "d79e5c22-ac7a-43f9-af04-0997fc7af3ce",
"name": "Keywords aus Tabelle mit GSC-Daten abgleichen",
"type": "n8n-nodes-base.code",
"notes": "Cross-references target keywords from the Google Sheet with actual GSC performance data. Identifies which target keywords are ranking in GSC and which are missing, adding status flags for tracking.",
"position": [
1056,
656
],
"parameters": {
"jsCode": "const out = [];\n\n// Step 1: Collect all Google Sheet keywords\nconst sheetKeywords = items\n .filter(i => i.json.Targetted_Keywords) // from Sheets\n .map(i => (i.json.Targetted_Keywords || \"\").toLowerCase().trim());\n\n// Deduplicate\nconst uniqueSheetKeywords = [...new Set(sheetKeywords)];\n\n// Step 2: Collect all GSC keywords\nconst gscData = items.filter(i => i.json.keyword);\n\n// Step 3: Match - GSC keywords found in sheet\nconst foundKeywords = new Set();\n\nfor (const item of gscData) {\n const gscKeyword = (item.json.keyword || \"\").toLowerCase().trim();\n \n if (uniqueSheetKeywords.includes(gscKeyword)) {\n foundKeywords.add(gscKeyword); // Track found keywords\n \n // Make sure URLs array includes CTR for each URL\n const urlsWithCtr = (item.json.urls || []).map(urlObj => ({\n url: urlObj.url,\n position: urlObj.position,\n clicks: urlObj.clicks,\n impressions: urlObj.impressions,\n ctr: urlObj.ctr // CTR included here\n }));\n \n out.push({\n json: {\n keyword: item.json.keyword,\n urls: urlsWithCtr,\n status: 'found_in_gsc' // Optional: to identify matched keywords\n }\n });\n }\n}\n\n// Step 4: Add sheet keywords that were NOT found in GSC\nfor (const sheetKeyword of uniqueSheetKeywords) {\n if (!foundKeywords.has(sheetKeyword)) {\n out.push({\n json: {\n keyword: sheetKeyword,\n urls: [], // No URLs since not found in GSC\n status: 'not_found_in_gsc' // Optional: to identify missing keywords\n }\n });\n }\n}\n\nreturn out;"
},
"typeVersion": 2
},
{
"id": "2f8ae342-1586-4f0f-8cd5-d650c4a62b30",
"name": "Keyword-Kannibalisierungsrisiko analysieren",
"type": "@n8n/n8n-nodes-langchain.agent",
"notes": "Uses AI to analyze keyword cannibalization risk by examining how many pages from the same domain rank for each keyword. Categorizes risk as High, Moderate, Low, or No risk based on page count and performance distribution.",
"position": [
1744,
352
],
"parameters": {
"text": "=You are a Keyword Cannibalization Risk Detector.\n\nYou will receive:\n\n{{ $json.keyword }}\n{{ JSON.stringify($json.urls) }}\n\n\n\n\nYour Tasks:\n\nExtract the domain from each URL and group the pages by domain.\n\nFor each domain, analyze whether multiple pages are competing for the same keyword.\n\nHigh → 5 or more pages from the same domain rank for the keyword.\n\nModerate → 3 pages from the same domain rank closely in the top 10.\n\nLow → 2 pages rank, but one clearly dominates in clicks/impressions.\n\nNo → Only 1 page from that domain ranks.\n\nIf the main domain's homepage is ranking at position 1 AND other URLs from the same domain are also ranking, still classify as appropriate risk level based on total page count (don't give them No Risk just because the homepage ranks #1).\n\nIf multiple different domains rank for the same keyword, highlight cross-domain competition separately.\n\nReturn your findings in structured and concise form, showing the keyword, domains, and their respective risk levels.",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.2
},
{
"id": "0957bb5f-6200-40a4-a61a-002c965b53ee",
"name": "OpenAI GPT-4o-Modell",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"notes": "Provides the AI language model (GPT-4o) for the cannibalization analysis agent. Handles the natural language processing to understand keyword competition patterns.",
"position": [
1728,
544
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "gpt-4o"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "503e683a-53c1-4aed-a86d-49ccdecd8b84",
"name": "KI-Analyse in strukturierte JSON parsen",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"notes": "Converts the AI agent's natural language response into a structured JSON format with specific fields for keyword, domain, URLs, risk level, reasoning, observations, summary, and remediation steps.",
"position": [
1904,
544
],
"parameters": {
"jsonSchemaExample": "{\n \"Keyword\": \"\",\n \"Domain\": \"\",\n \"URLs for Keyword\": [\n {\n \"url\": \"\",\n \"position\": \"\",\n \"clicks\": \"\",\n \"impressions\": \"\",\n \"ctr\": \"\"\n }\n ],\n \"Risk Level\": \"\",\n \"Reasoning\": \"\",\n \"Observation\": \"\",\n \"Summary\": \"\",\n \"Remediation steps\": \"\"\n}\n"
},
"typeVersion": 1.3
},
{
"id": "7ab77205-1560-45ae-8a94-fb088dcfa62e",
"name": "Keyword-Tabelle auf Änderungen überwachen",
"type": "n8n-nodes-base.googleSheetsTrigger",
"notes": "Monitors the Keywords Google Sheet for any changes and triggers the workflow when modifications are detected. Polls every minute to ensure real-time processing of keyword updates.",
"maxTries": 5,
"position": [
-944,
656
],
"parameters": {
"options": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1256649775,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit#gid=1256649775",
"cachedResultName": "Keywords"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit?gid=1256649775#gid=1256649775"
}
},
"retryOnFail": true,
"typeVersion": 1
},
{
"id": "6dbee777-42fc-4576-a27b-4650af47455e",
"name": "Kannibalisierungsanalyse-Ergebnisse speichern",
"type": "n8n-nodes-base.googleSheets",
"notes": "Writes the final cannibalization analysis results back to Google Sheets. Updates or appends rows with risk levels, reasoning, observations, remediation steps, and all associated keyword data.",
"position": [
2272,
672
],
"parameters": {
"columns": {
"value": {
"Data": "={{ $json.output['URLs for Keyword'].map(i => `${i.url} | Position: ${i.position} | Clicks: ${i.clicks} | Impressions: ${i.impressions} | CTR: ${i.ctr}`).join('\n') }}",
"Date": "={{ $now.format('yyyy-MM-dd') }}",
"Domain": "={{ $json.output.Domain }}",
"Status": "={{ $('Match Keywords from Sheet with GSC Data').item.json.status }}",
"Summary": "={{ $json.output.Summary }}",
"Reasoning": "={{ $json.output.Reasoning }}",
"Risk Level": "={{ $json.output['Risk Level'] }}",
"Observation": "={{ $json.output.Observation }}",
"Target page": "={{ $json.output['URLs for Keyword'].map(u => u.url).join(', ') }}\n",
"remediation steps": "={{ $json.output['remediation steps'] }}",
"Targetted_Keywords": "={{ $json.output.Keyword }}\n{{ $json.keyword }}"
},
"schema": [
{
"id": "Targetted_Keywords",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Targetted_Keywords",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Domain",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Domain",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Date",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "Date",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Target page",
"type": "string",
"display": true,
"required": false,
"displayName": "Target page",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Data",
"type": "string",
"display": true,
"required": false,
"displayName": "Data",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Risk Level",
"type": "string",
"display": true,
"required": false,
"displayName": "Risk Level",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Reasoning",
"type": "string",
"display": true,
"required": false,
"displayName": "Reasoning",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Observation",
"type": "string",
"display": true,
"required": false,
"displayName": "Observation",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Summary",
"type": "string",
"display": true,
"required": false,
"displayName": "Summary",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "remediation steps",
"type": "string",
"display": true,
"required": false,
"displayName": "remediation steps",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"Targetted_Keywords"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1761789723,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit#gid=1761789723",
"cachedResultName": "data"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit?gid=1256649775#gid=1256649775"
}
},
"typeVersion": 4.7
},
{
"id": "f78e179c-dedd-4d79-9f96-ab40fbe40f3f",
"name": "An Kunde 1 weiterleiten",
"type": "n8n-nodes-base.if",
"notes": "Routes workflow execution to Client 1's GSC data fetching if the client website matches the specified URL pattern. Acts as a conditional switch for multi-client processing.",
"position": [
-288,
288
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "or",
"conditions": [
{
"id": "9e1de819-aebf-4242-8f79-7262e422eb57",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $json['Client Website'].trimStart().trimEnd() }}",
"rightValue": "https://theshroomgroove.com/"
}
]
},
"looseTypeValidation": true
},
"executeOnce": false,
"typeVersion": 2.2
},
{
"id": "f44239f6-1831-4546-a829-2abf27d4eb2e",
"name": "An Kunde 2 weiterleiten",
"type": "n8n-nodes-base.if",
"notes": "Routes workflow execution to Client 2's GSC data fetching when the client website matches the specified domain. Enables parallel processing of multiple clients.",
"position": [
-288,
480
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "9e1de819-aebf-4242-8f79-7262e422eb57",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $json['Client Website'].trimStart().trimEnd() }}",
"rightValue": "grooveguide.io"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "fc7efa81-5870-4bc7-bd21-2181214976ff",
"name": "An Kunde 3 weiterleiten",
"type": "n8n-nodes-base.if",
"notes": "Directs the workflow to fetch GSC data for Client 3 when the website URL matches the condition. Part of the multi-client routing logic to handle different domains.",
"position": [
-288,
864
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "9e1de819-aebf-4242-8f79-7262e422eb57",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $json['Client Website'].trimStart().trimEnd() }}",
"rightValue": "https://groovegrillwellness.com/"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "c91f5ab4-29a1-4f83-b570-3fdf4b3e7c1a",
"name": "An Kunde 4 weiterleiten",
"type": "n8n-nodes-base.if",
"notes": "Routes to Client 4's GSC data collection process when the website URL condition is met. Completes the multi-client routing system for parallel data processing.",
"position": [
-288,
1056
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "9e1de819-aebf-4242-8f79-7262e422eb57",
"operator": {
"type": "string",
"operation": "contains"
},
"leftValue": "={{ $json['Client Website'].trimStart().trimEnd() }}",
"rightValue": "https://example.com/"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "2c0ba70f-00df-4be9-98a2-7969653e10db",
"name": "Kunden-Website-URLs abrufen",
"type": "n8n-nodes-base.googleSheets",
"notes": "Retrieves the list of client website URLs from the Google Sheet. This data is used to determine which clients to process and route them to their respective GSC data collection paths.",
"position": [
-656,
656
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 146956146,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit#gid=146956146",
"cachedResultName": "URL"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit?usp=drivesdk",
"cachedResultName": "Client URLs"
}
},
"executeOnce": false,
"typeVersion": 4.7
},
{
"id": "a6a60ba4-3b48-4750-af64-bf19c22f6b5c",
"name": "Ziel-Keywords aus Tabelle abrufen",
"type": "n8n-nodes-base.googleSheets",
"notes": "Reads the target keywords from the Google Sheet that need to be analyzed for cannibalization. These keywords serve as the reference list to match against actual GSC performance data.",
"position": [
-288,
656
],
"parameters": {
"options": {},
"sheetName": {
"__rl": true,
"mode": "list",
"value": 1256649775,
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit#gid=1256649775",
"cachedResultName": "Keywords"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1UfQvam8UhT58LSBobnyFsd3fi1dk7ilzvbQ57rFTIIo/edit?usp=drivesdk",
"cachedResultName": "Client URLs"
}
},
"executeOnce": true,
"typeVersion": 4.7
},
{
"id": "5a72cf8f-cf73-4811-9b55-807f7966e826",
"name": "GSC-Daten abrufen (Kunde 1)",
"type": "n8n-nodes-base.httpRequest",
"notes": "Makes API call to Google Search Console for Client 1 to retrieve the last 30 days of search performance data. Gets keyword-page combinations with position, clicks, impressions, and CTR metrics.",
"onError": "continueRegularOutput",
"position": [
48,
272
],
"parameters": {
"url": "=https://www.googleapis.com/webmasters/v3/sites/{{ encodeURIComponent($json['Client Website']) }}/searchAnalytics/query",
"method": "POST",
"options": {},
"jsonBody": "={\n \"startDate\": \"{{ $now.minus(30, 'days').format('yyyy-MM-dd') }}\",\n \"endDate\": \"{{ $now.format('yyyy-MM-dd') }}\",\n \"dimensions\": [\"query\", \"page\"]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googleOAuth2Api"
},
"executeOnce": true,
"typeVersion": 4.2
},
{
"id": "03e271fe-0bfd-4f75-85af-cfdf0bcb8ac0",
"name": "In GSC gefundene Keywords filtern",
"type": "n8n-nodes-base.if",
"notes": "Filters out keywords that were not found in GSC data, only passing through keywords that actually have ranking performance data. Prevents AI analysis of keywords with no GSC presence.",
"position": [
1424,
656
],
"parameters": {
"options": {
"ignoreCase": true
},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "ccec25a9-75f6-4c82-a93f-aafb28aa3633",
"operator": {
"type": "string",
"operation": "notEquals"
},
"leftValue": "={{ $json.status }}",
"rightValue": "not_found_in_gsc"
}
]
},
"looseTypeValidation": true
},
"typeVersion": 2.2
},
{
"id": "df3c0be2-7000-4821-8eb2-bbd9fee541f6",
"name": "GSC-Daten abrufen (Kunde 2)",
"type": "n8n-nodes-base.httpRequest",
"notes": "Retrieves Google Search Console data for Client 2 using domain property format. Collects 30 days of search analytics data including keywords, pages, positions, and engagement metrics.",
"onError": "continueRegularOutput",
"position": [
48,
464
],
"parameters": {
"url": "=https://www.googleapis.com/webmasters/v3/sites/sc-domain:{{ $json['Client Website'] }}/searchAnalytics/query",
"method": "POST",
"options": {},
"jsonBody": "={\n \"startDate\": \"{{ $now.minus(30, 'days').format('yyyy-MM-dd') }}\",\n \"endDate\": \"{{ $now.format('yyyy-MM-dd') }}\",\n \"dimensions\": [\"query\", \"page\"]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googleOAuth2Api"
},
"executeOnce": true,
"typeVersion": 4.2
},
{
"id": "88d5018c-546f-4299-9ad9-d77065450cb6",
"name": "GSC-Daten abrufen (Kunde 3)",
"type": "n8n-nodes-base.httpRequest",
"notes": "Connects to Google Search Console API for Client 3 to extract search performance data. Gathers keyword rankings, page URLs, positions, clicks, impressions, and CTR for the past 30 days.",
"onError": "continueRegularOutput",
"position": [
48,
848
],
"parameters": {
"url": "=https://www.googleapis.com/webmasters/v3/sites/{{ encodeURIComponent($json['Client Website']) }}/searchAnalytics/query",
"method": "POST",
"options": {},
"jsonBody": "={\n \"startDate\": \"{{ $now.minus(30, 'days').format('yyyy-MM-dd') }}\",\n \"endDate\": \"{{ $now.format('yyyy-MM-dd') }}\",\n \"dimensions\": [\"query\", \"page\"]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googleOAuth2Api"
},
"executeOnce": true,
"typeVersion": 4.2
},
{
"id": "a7f0a16a-ca27-4bb2-b5ba-5b74759f5f70",
"name": "GSC-Daten abrufen (Kunde 4)",
"type": "n8n-nodes-base.httpRequest",
"notes": "Pulls Google Search Console analytics data for Client 4 covering the last 30 days. Retrieves comprehensive search performance metrics including keyword-page relationships and ranking positions.",
"onError": "continueRegularOutput",
"position": [
48,
1040
],
"parameters": {
"url": "=https://www.googleapis.com/webmasters/v3/sites/{{ encodeURIComponent($json['Client Website']) }}/searchAnalytics/query",
"method": "POST",
"options": {},
"jsonBody": "={\n \"startDate\": \"{{ $now.minus(30, 'days').format('yyyy-MM-dd') }}\",\n \"endDate\": \"{{ $now.format('yyyy-MM-dd') }}\",\n \"dimensions\": [\"query\", \"page\"]\n}",
"sendBody": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "googleOAuth2Api"
},
"executeOnce": true,
"typeVersion": 4.2
},
{
"id": "9d911368-b656-4519-8a24-36220cb9f4e0",
"name": "Notizzettel",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1008,
416
],
"parameters": {
"width": 480,
"height": 416,
"content": "## Monitor Keywords Sheet for Changes\nMonitors the Keywords Google Sheet for any changes and triggers the workflow when modifications are detected. Polls every minute to ensure real-time processing of keyword updates.\n\n## Fetch Client Website URLs\nRetrieves the list of client website URLs from the Google Sheet. This data is used to determine which clients to process and route them to their respective GSC data collection paths.\n"
},
"typeVersion": 1
},
{
"id": "ddd27041-06de-475b-bb47-2d1a6032be6c",
"name": "Notizzettel 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-64,
-48
],
"parameters": {
"width": 656,
"height": 1248,
"content": "## Fetch GSC Data (Client 1-4)\nMakes API call to Google Search Console for Client [X] to retrieve the last 30 days of search performance data. Gets keyword-page combinations with position, clicks, impressions, and CTR metrics.\n\n## Group GSC Data by Keyword (Client 1-4)\nGroups Google Search Console data by keyword for Client [X]. Takes raw GSC response and organizes it by keyword, with each keyword containing an array of URLs that rank for it, including position, clicks, impressions, and CTR data.\n"
},
"typeVersion": 1
},
{
"id": "581173a3-79e0-415d-99d2-a971bb5318d1",
"name": "Notizzettel 4",
"type": "n8n-nodes-base.stickyNote",
"position": [
992,
368
],
"parameters": {
"height": 448,
"content": "## Match Keywords from Sheet with GSC Data\nCross-references target keywords from the Google Sheet with actual GSC performance data. Identifies which target keywords are ranking in GSC and which are missing, adding status flags for tracking."
},
"typeVersion": 1
},
{
"id": "f6343388-a09f-433d-94dc-a6c7d9195eec",
"name": "Notizzettel 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1360,
64
],
"parameters": {
"width": 1104,
"height": 816,
"content": "## Filter Keywords Found in GSC\nFilters out keywords that were not found in GSC data, only passing through keywords that actually have ranking performance data. Prevents AI analysis of keywords with no GSC presence.\n## Analyze Keyword Cannibalization Risk\nUses AI to analyze keyword cannibalization risk by examining how many pages from the same domain rank for each keyword. Categorizes risk as High, Moderate, Low, or No risk based on page count and performance distribution.\n## Save Cannibalization Analysis Results\nWrites the final cannibalization analysis results back to Google Sheets. Updates or appends rows with risk levels, reasoning, observations, remediation steps, and all associated keyword data.\n"
},
"typeVersion": 1
},
{
"id": "2e15b4f3-f8ac-41f6-a50f-beb2af6f384d",
"name": "Notizzettel 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1664,
64
],
"parameters": {
"width": 432,
"height": 1040,
"content": "## Keyword Cannibalization Detection Workflow Summary\n### Overview\nThis n8n workflow is an automated keyword cannibalization detection system that monitors multiple client websites and analyzes their search performance using Google Search Console data and AI-powered risk assessment.\n\n### Workflow Process\n🔄 Automated Trigger: The workflow monitors a Google Sheets document for keyword changes, triggering execution every minute when modifications are detected to ensure real-time processing.\n\n📊 Multi-Client Data Collection: The system simultaneously processes up to 4 different client websites through intelligent routing nodes that direct each client's data to dedicated processing paths based on URL pattern matching.\n\n🔍 GSC Data Extraction: For each client, the workflow makes API calls to Google Search Console to retrieve 30 days of search performance data, collecting keyword rankings, page URLs, positions, clicks, impressions, and CTR metrics.\n\n⚙️ Data Transformation: Raw GSC API responses are processed through JavaScript code nodes that group flat data by keywords, creating structured datasets where each keyword contains all competing URLs with their complete performance metrics.\n\n🔗 Data Integration: A merge node combines GSC data from all clients with target keywords from the Google Sheet, then cross-references to identify which keywords are actually ranking versus those missing from search results.\n\n🤖 AI-Powered Analysis: The system uses GPT-4o to analyze keyword cannibalization risk by examining how many pages from the same domain compete for each keyword, automatically categorizing risk levels as High (5+ pages), Moderate (3+ pages), Low (2 pages with clear dominance), or No Risk (single page).\n\n💾 Automated Reporting: Final analysis results are written back to Google Sheets with comprehensive data including risk assessments, detailed reasoning, observations, actionable remediation steps, and complete performance metrics for client reporting."
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"f78e179c-dedd-4d79-9f96-ab40fbe40f3f": {
"main": [
[
{
"node": "5a72cf8f-cf73-4811-9b55-807f7966e826",
"type": "main",
"index": 0
}
]
]
},
"f44239f6-1831-4546-a829-2abf27d4eb2e": {
"main": [
[
{
"node": "df3c0be2-7000-4821-8eb2-bbd9fee541f6",
"type": "main",
"index": 0
}
]
]
},
"fc7efa81-5870-4bc7-bd21-2181214976ff": {
"main": [
[
{
"node": "88d5018c-546f-4299-9ad9-d77065450cb6",
"type": "main",
"index": 0
}
]
]
},
"c91f5ab4-29a1-4f83-b570-3fdf4b3e7c1a": {
"main": [
[
{
"node": "a7f0a16a-ca27-4bb2-b5ba-5b74759f5f70",
"type": "main",
"index": 0
}
]
]
},
"0957bb5f-6200-40a4-a61a-002c965b53ee": {
"ai_languageModel": [
[
{
"node": "2f8ae342-1586-4f0f-8cd5-d650c4a62b30",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"2c0ba70f-00df-4be9-98a2-7969653e10db": {
"main": [
[
{
"node": "f78e179c-dedd-4d79-9f96-ab40fbe40f3f",
"type": "main",
"index": 0
},
{
"node": "f44239f6-1831-4546-a829-2abf27d4eb2e",
"type": "main",
"index": 0
},
{
"node": "fc7efa81-5870-4bc7-bd21-2181214976ff",
"type": "main",
"index": 0
},
{
"node": "c91f5ab4-29a1-4f83-b570-3fdf4b3e7c1a",
"type": "main",
"index": 0
}
]
]
},
"5a72cf8f-cf73-4811-9b55-807f7966e826": {
"main": [
[
{
"node": "7f125793-0b03-4466-b25b-1ef3bb4a76d4",
"type": "main",
"index": 0
}
]
]
},
"df3c0be2-7000-4821-8eb2-bbd9fee541f6": {
"main": [
[
{
"node": "90168f30-8e88-4b5a-9a80-586ad28f5a8f",
"type": "main",
"index": 0
}
]
]
},
"88d5018c-546f-4299-9ad9-d77065450cb6": {
"main": [
[
{
"node": "866dd165-dd86-43b9-b24e-e54ade95c42c",
"type": "main",
"index": 0
}
]
]
},
"a7f0a16a-ca27-4bb2-b5ba-5b74759f5f70": {
"main": [
[
{
"node": "e679fffe-fb2b-4cff-b5a0-104179212ac0",
"type": "main",
"index": 0
}
]
]
},
"94c42a7f-50aa-48c9-9643-58eeaddd8ff8": {
"main": [
[
{
"node": "d79e5c22-ac7a-43f9-af04-0997fc7af3ce",
"type": "main",
"index": 0
}
]
]
},
"03e271fe-0bfd-4f75-85af-cfdf0bcb8ac0": {
"main": [
[
{
"node": "2f8ae342-1586-4f0f-8cd5-d650c4a62b30",
"type": "main",
"index": 0
}
],
[
{
"node": "6dbee777-42fc-4576-a27b-4650af47455e",
"type": "main",
"index": 0
}
]
]
},
"a6a60ba4-3b48-4750-af64-bf19c22f6b5c": {
"main": [
[
{
"node": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"type": "main",
"index": 2
}
]
]
},
"7ab77205-1560-45ae-8a94-fb088dcfa62e": {
"main": [
[
{
"node": "2c0ba70f-00df-4be9-98a2-7969653e10db",
"type": "main",
"index": 0
},
{
"node": "a6a60ba4-3b48-4750-af64-bf19c22f6b5c",
"type": "main",
"index": 0
}
]
]
},
"2f8ae342-1586-4f0f-8cd5-d650c4a62b30": {
"main": [
[
{
"node": "6dbee777-42fc-4576-a27b-4650af47455e",
"type": "main",
"index": 0
}
]
]
},
"7f125793-0b03-4466-b25b-1ef3bb4a76d4": {
"main": [
[
{
"node": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"type": "main",
"index": 0
}
]
]
},
"90168f30-8e88-4b5a-9a80-586ad28f5a8f": {
"main": [
[
{
"node": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"type": "main",
"index": 1
}
]
]
},
"866dd165-dd86-43b9-b24e-e54ade95c42c": {
"main": [
[
{
"node": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"type": "main",
"index": 3
}
]
]
},
"e679fffe-fb2b-4cff-b5a0-104179212ac0": {
"main": [
[
{
"node": "94c42a7f-50aa-48c9-9643-58eeaddd8ff8",
"type": "main",
"index": 4
}
]
]
},
"503e683a-53c1-4aed-a86d-49ccdecd8b84": {
"ai_outputParser": [
[
{
"node": "2f8ae342-1586-4f0f-8cd5-d650c4a62b30",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"d79e5c22-ac7a-43f9-af04-0997fc7af3ce": {
"main": [
[
{
"node": "03e271fe-0bfd-4f75-85af-cfdf0bcb8ac0",
"type": "main",
"index": 0
}
]
]
}
}
}Häufig gestellte Fragen
Wie verwende ich diesen Workflow?
Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.
Für welche Szenarien ist dieser Workflow geeignet?
Experte - Content-Erstellung, Multimodales KI
Ist es kostenpflichtig?
Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.
Verwandte Workflows
Blog-Publisher – vollständige Automatisierung der KI-gesteuerten Inhaltserstellung, -optimierung und -veröffentlichung
Automatisierung der Blog-Erstellung und -Veröffentlichung mit Gemini, Ideogram AI und WordPress
If
Set
Code
+
If
Set
Code
35 NodesIncrementors
Content-Erstellung
WordPress-Blog-Automatisierung Professional Edition (Deep Research) v2.1 Markt
Automatisierung der Erstellung von SEO-optimierten Blogs mit GPT-4o, Perplexity AI und mehrsprachiger Unterstützung
If
Set
Xml
+
If
Set
Xml
125 NodesDaniel Ng
Content-Erstellung
1. Playlist-Details-Einstellungen für Roboter-Kopie
Erstelle KI-generierte YouTube-Musik-Playlists mit Suno, GPT-4, Runway und Creatomate
If
Set
Code
+
If
Set
Code
203 NodesJoseph
Content-Erstellung
Mein Workflow 9_Alte Version
Erstellen Sie täglich YouTube-Videos mit MagicHour, Gemini und Google Sheets
If
Set
Code
+
If
Set
Code
31 NodesDivyansh Chauhan
Content-Erstellung
💥 Automatisierung von Videoanzeigen mit NanoBanana, Seedream 4, ChatGPT Image und Veo 3 - VIDE
Automatisierung und Veröffentlichung von Video-Werbekampagnen mit KI (NanoBanana, Seedream, GPT-4o, Veo 3)
Set
Code
Wait
+
Set
Code
Wait
63 NodesDr. Firas
Content-Erstellung
Automatisierung von Gesicht-videos mit OpenAI, RunwayML und ElevenLabs
Automatisierung von Gesichtsvideos ohne Gesicht mit OpenAI, RunwayML und ElevenLabs: Von Skript bis Social Media
Set
Code
Wait
+
Set
Code
Wait
56 NodesLeeWei
Content-Erstellung
Workflow-Informationen
Schwierigkeitsgrad
Experte
Anzahl der Nodes27
Kategorie2
Node-Typen10
Autor
Incrementors
@incrementorsExterne Links
Auf n8n.io ansehen →
Diesen Workflow teilen