This workflow follows the Google Drive → Googlegemini recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "AI-Literature-Metadata-Extractor",
"nodes": [
{
"parameters": {
"authentication": "",
"operation": "download",
"fileId": {
"__rl": true,
"value": "={{ $json.id }}",
"mode": "id"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
624,
16
],
"id": "cbfba097-48e1-4e54-a85a-38c6d0396d19",
"name": "Download file",
"credentials": {
"googleApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "pdf",
"binaryPropertyName": "={{ $('Download file').item.binary.data }}",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
1200,
16
],
"id": "c35e9b33-aaa1-4b3b-af9c-f0bf38320549",
"name": "Extract from File"
},
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
416,
0
],
"id": "c1d8815d-1094-4838-b34b-95e46c1237cd",
"name": "Loop Over Items"
},
{
"parameters": {},
"type": "n8n-nodes-base.noOp",
"name": "Replace Me",
"typeVersion": 1,
"position": [
2176,
16
],
"id": "8bbabc79-23b4-41a2-9d8d-fb4ce42d7bc9"
},
{
"parameters": {
"authentication": "serviceAccount",
"operation": "appendOrUpdate",
"documentId": {
"__rl": true,
"value": "18Ai6qOIsSaSTBPKE6FMQ99rUYw-tInM0aio58UUlqmI",
"mode": "list",
"cachedResultName": "LITERATUR OZETI",
"cachedResultUrl": ""
},
"sheetName": {
"__rl": true,
"value": "gid=0",
"mode": "list",
"cachedResultName": "OZET",
"cachedResultUrl": ""
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"YAZARLAR": "={{\n (\n Array.isArray($json.metadata?.['dc:creator'])\n ? $json.metadata['dc:creator'].join(', ')\n : ($json.metadata?.['dc:creator'] || '')\n )\n ||\n (\n Array.isArray($('Code in JavaScript').item.json.extracted.yazarlar)\n ? $('Code in JavaScript').item.json.extracted.yazarlar.join(', ')\n : ($('Code in JavaScript').item.json.extracted.yazarlar || '')\n )\n}}\n",
"MAKALE ADI": "={{ $json.metadata['dc:title'] || $('Code in JavaScript').item.json.extracted.makale_adi}}\n",
"TIP": "={{ $('Code in JavaScript').item.json.extracted.kaynak.tip || $json.metadata['prism:aggregationtype'] }}",
"TIP ADI": "={{\n (\n $('Code in JavaScript').item.json.extracted.kaynak\n ? [\n $('Code in JavaScript').item.json.extracted.kaynak.ad || '',\n $('Code in JavaScript').item.json.extracted.kaynak.cilt || '',\n $('Code in JavaScript').item.json.extracted.kaynak.sayi || '',\n $('Code in JavaScript').item.json.extracted.kaynak.sayfa || '',\n $('Code in JavaScript').item.json.extracted.kaynak.ek_bilgi || ''\n ]\n .filter(Boolean)\n .join(' - ')\n : ''\n )\n ||\n (\n $json.metadata && $json.metadata['dc:description']\n ? $json.metadata['dc:description']\n : ''\n )\n}}\n",
"ANAHTAR KEL\u0130MELER": "={{\n (\n Array.isArray($json.metadata && $json.metadata['pdf:keywords'])\n ? $json.metadata['pdf:keywords'].join(', ')\n : ($json.metadata && $json.metadata['pdf:keywords']\n ? $json.metadata['pdf:keywords']\n : '')\n )\n ||\n (\n Array.isArray($('Code in JavaScript').item.json.extracted.anahtar_kelimeler)\n ? $('Code in JavaScript').item.json.extracted.anahtar_kelimeler.join(', ')\n : ($('Code in JavaScript').item.json.extracted.anahtar_kelimeler || '')\n )\n}}\n",
"ID": "={{ $('Loop Over Items').item.json.id }}\n",
"AY/YIL": "={{\n (\n $('Code in JavaScript').item.json.extracted\n && $('Code in JavaScript').item.json.extracted.yayin\n && $('Code in JavaScript').item.json.extracted.yayin.ay\n && $('Code in JavaScript').item.json.extracted.yayin.yil\n && $('Code in JavaScript').item.json.extracted.yayin.ay !== 'belirsiz'\n && $('Code in JavaScript').item.json.extracted.yayin.yil !== 'belirsiz'\n )\n ? (\n $('Code in JavaScript').item.json.extracted.yayin.ay\n + '/' +\n $('Code in JavaScript').item.json.extracted.yayin.yil\n )\n : (\n $json.metadata && $json.metadata['prism:coverdisplaydate']\n ? $json.metadata['prism:coverdisplaydate']\n : ''\n )\n}}\n",
"KAYNAK": "={{ $json.metadata['prism:url'] || $('Code in JavaScript').item.json.citationMetadata?.citationSources[0].uri || $('Code in JavaScript').item.json.extracted?.doi }}",
"ARA\u015eTIRMA SORUSU": "={{ $('Code in JavaScript').item.json.extracted.arastirma_sorusu }}",
"BULGU VE SONUC": "={{ $('Code in JavaScript').item.json.extracted.bulgular_sonuclar }}",
"YONTEM": "={{ $('Code in JavaScript').item.json.extracted.yontem }}"
},
"matchingColumns": [
"ID"
],
"schema": [
{
"id": "ID",
"displayName": "ID",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "KAYNAK",
"displayName": "KAYNAK",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "MAKALE ADI",
"displayName": "MAKALE ADI",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "YAZARLAR",
"displayName": "YAZARLAR",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "AY/YIL",
"displayName": "AY/YIL",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "TIP",
"displayName": "TIP",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "TIP ADI",
"displayName": "TIP ADI",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "ANAHTAR KEL\u0130MELER",
"displayName": "ANAHTAR KEL\u0130MELER",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "ARA\u015eTIRMA SORUSU",
"displayName": "ARA\u015eTIRMA SORUSU",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "YONTEM",
"displayName": "YONTEM",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
},
{
"id": "BULGU VE SONUC",
"displayName": "BULGU VE SONUC",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"canBeUsedToMatch": true,
"removed": false
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.googleSheets",
"typeVersion": 4.7,
"position": [
1376,
16
],
"id": "1880bdbf-d59e-4b0e-9822-3bbd5271ccab",
"name": "Append or update row in sheet",
"credentials": {
"googleApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"resource": "document",
"modelId": {
"__rl": true,
"value": "models/gemini-2.5-flash",
"mode": "list",
"cachedResultName": "models/gemini-2.5-flash"
},
"text": "{\n \"contents\": [{\n \"role\": \"user\",\n \"parts\": [{\n \"text\": \"A\u015fa\u011f\u0131daki makale metninden SADECE belirtilen JSON \u015femas\u0131na uygun veri \u00e7\u0131kar. Girdi d\u00f6k\u00fcman hangi dilde olursa olsun a\u00e7\u0131klamalar\u0131n\u0131 t\u00fcrk\u00e7e yazmal\u0131s\u0131n. Tahmin yapacaksan da a\u00e7\u0131k\u00e7a 'belirsiz' yaz.\\n\\n\u00c7IKTI \u015eEMASI (TAM VE GE\u00c7ERL\u0130 JSON):\\n{\\n \\\"makale_adi\\\": \\\"\\\",\\n \\\"yazarlar\\\": [\\\"\\\"],\\n \\\"yayin\\\": {\\n \\\"ay\\\": \\\"\\\",\\n \\\"yil\\\": 0\\n },\\n \\\"kaynak\\\": {\\n \\\"tip\\\": \\\"Dergi|Konferans|Kitap|ArXiv|Di\u011fer\\\",\\n \\\"ad\\\": \\\"\\\",\\n \\\"cilt\\\": \\\"\\\",\\n \\\"sayi\\\": \\\"\\\",\\n \\\"sayfa\\\": \\\"\\\",\\n \\\"ek_bilgi\\\": \\\"\\\"\\n },\\n \\\"anahtar_kelimeler\\\": [\\\"\\\"],\\n \\\"arastirma_sorusu\\\": \\\"\\\",\\n \\\"yontem\\\": \\\"\\\",\\n \\\"bulgular_sonuclar\\\": \\\"\\\",\\n \\\"doi\\\": \\\"\\\"\\n}\\n\\nKURALLAR:\\n- Sadece yukar\u0131daki anahtarlar\u0131 kullan.\\n- De\u011fer bulamazsan bo\u015f string veya 0 b\u0131rak.\\n- Yazarlar\u0131 [\\\"Ad Soyad\\\", ...] dizisi olarak ver.\\n- Ay T\u00fcrk\u00e7e olabilir (Ocak, \u015eubat, ...). Y\u0131l tamsay\u0131.\\n- Kaynak tipini bu k\u00fcmeden se\u00e7: Dergi|Konferans|Kitap|ArXiv|Di\u011fer.\\n- \u00d6rnek kaynak format\u0131 yol g\u00f6sterici: Dergi - \\\"Computers and Electronics in Agriculture, Volume 217, February 2024, 108629\\\"; bu bilgileri uygun alanlara da\u011f\u0131t.\\n\\nMET\u0130N:\\n{{inputText}}\"\n }]\n }]\n}\n",
"inputType": "binary",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.googleGemini",
"typeVersion": 1,
"position": [
832,
16
],
"id": "167400fb-3558-45a8-b119-68b1283cbd2a",
"name": "Analyze document",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "// Gemini cevab\u0131ndan JSON'u \u00e7ekip item.json.extracted i\u00e7ine koyar.\n// A\u015fa\u011f\u0131daki \u015fekilleri destekler:\n// - Google API: { candidates[0].content.parts[0].text }\n// - Senin \u00f6rnek: { content.parts[0].text } veya [ { content.parts[0].text } ]\n// - D\u00fcz string ya da body/text alan\u0131na d\u00fc\u015fm\u00fc\u015f i\u00e7erik\n\nfunction pickText(obj) {\n if (!obj) return '';\n if (typeof obj === 'string') return obj;\n\n // Google API standard\n if (obj.candidates?.[0]?.content?.parts?.[0]?.text) {\n return obj.candidates[0].content.parts[0].text;\n }\n\n // Senin \u00f6rnek payload'\u0131 tek obje\n if (obj.content?.parts?.[0]?.text) {\n return obj.content.parts[0].text;\n }\n\n // HTTP node baz\u0131 kurulumlarda body/text alt\u0131na koyabiliyor\n if (obj.body) return pickText(obj.body);\n if (obj.text) return obj.text;\n\n // T\u00fcm yan\u0131t komple bir dizi geldiyse (nadir)\n if (Array.isArray(obj)) {\n if (obj[0]?.content?.parts?.[0]?.text) {\n return obj[0].content.parts[0].text;\n }\n // Dizide Google-style varsa\n if (obj[0]?.candidates?.[0]?.content?.parts?.[0]?.text) {\n return obj[0].candidates[0].content.parts[0].text;\n }\n }\n\n return '';\n}\n\nfunction safeParse(jsonStr) {\n try { return JSON.parse(jsonStr); } catch { return null; }\n}\n\nconst out = $input.all().map((item) => {\n const src = item.json ?? item;\n\n // Metni topla\n let text = $input.first().json.content.parts[0].text\n\n // ```json \u00e7itlerini temizle\n let candidate = (text || '').replace(/```json|```/g, '').trim();\n\n // \u00d6nce direkt parse\n let parsed = safeParse(candidate);\n\n // Olmazsa ilk {...} blo\u011funu ay\u0131kla\n if (!parsed) {\n const m = candidate.match(/\\{[\\s\\S]*\\}/);\n if (m) parsed = safeParse(m[0]);\n }\n\n if (!parsed || typeof parsed !== 'object') {\n parsed = {};\n }\n\n item.json.extracted = parsed;\n return item;\n});\n\nreturn out;\n"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1024,
16
],
"id": "8a566468-e90d-46c4-9a48-7fb235dfa47f",
"name": "Code in JavaScript"
},
{
"parameters": {
"authentication": "serviceAccount",
"operation": "update",
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Loop Over Items').item.json.id }}"
},
"newUpdatedFileName": "={{ $json['AY/YIL'] }}-{{ $json['MAKALE ADI'] }}",
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
1584,
16
],
"id": "7685f7e7-b0f7-4b9d-9070-26ce968bfbba",
"name": "Update file",
"credentials": {
"googleApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"authentication": "serviceAccount",
"operation": "move",
"fileId": {
"__rl": true,
"value": "={{ $('Loop Over Items').item.json.id }}",
"mode": "id"
},
"driveId": {
"__rl": true,
"mode": "list",
"value": ""
},
"folderId": {
"__rl": true,
"value": "18_xEz1mortacfC7mptU7WQDADrxEFvqH",
"mode": "list",
"cachedResultName": "",
"cachedResultUrl": ""
}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
1792,
16
],
"id": "51bf64fd-b156-466e-b766-2ab3a6de5578",
"name": "Move file",
"credentials": {
"googleApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-16,
0
],
"id": "0dcf5096-8343-4c56-96d0-7df668e8991d",
"name": "When clicking \u2018Execute workflow\u2019"
},
{
"parameters": {
"authentication": "serviceAccount",
"resource": "fileFolder",
"searchMethod": "query",
"queryString": "'10hY1UHMPud6IxQdVmmFruiPRS4EOpvAu' in parents and mimeType = 'application/pdf' and trashed = false",
"filter": {},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
176,
0
],
"id": "e009ec2a-434d-4a3e-a264-1e04efeeabeb",
"name": "Search files and folders",
"credentials": {
"googleApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"Download file": {
"main": [
[
{
"node": "Analyze document",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Download file",
"type": "main",
"index": 0
}
]
]
},
"Replace Me": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Append or update row in sheet",
"type": "main",
"index": 0
}
]
]
},
"Analyze document": {
"main": [
[
{
"node": "Code in JavaScript",
"type": "main",
"index": 0
}
]
]
},
"Code in JavaScript": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Append or update row in sheet": {
"main": [
[
{
"node": "Update file",
"type": "main",
"index": 0
}
]
]
},
"Update file": {
"main": [
[
{
"node": "Move file",
"type": "main",
"index": 0
}
]
]
},
"Move file": {
"main": [
[
{
"node": "Replace Me",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Search files and folders",
"type": "main",
"index": 0
}
]
]
},
"Search files and folders": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"callerPolicy": "workflowsFromSameOwner",
"availableInMCP": false,
"timeSavedPerExecution": 10
},
"versionId": "bb741cac-31d4-4719-b5ec-921d8c98e277",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "GROCxnrQzpOZ1HHI",
"tags": []
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleApigooglePalmApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI-Literature-Metadata-Extractor. Uses googleDrive, googleSheets, googleGemini. Event-driven trigger; 11 nodes.
Source: https://github.com/abdullahaligun/AI-Literature-Metadata-Extractor/blob/e68f3b2a1fd90730952b9318004ae74af12be57c/workflow.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Use n8n to extract medical test data from diagnostic reports uploaded to Google Drive, automatically detect abnormal values, and generate personalized health advice. Upload a medical report (PDF or im
Google Drive, Google Drive Trigger, Mistral Ai +2
Analyze Amazon product reviews with Gemini and save to Google Sheets
Slack, Google Sheets, Google Gemini +1
Transform your receipt management with this comprehensive n8n workflow that automatically processes receipts through Telegram, extracts transaction data using AI, and stores it across multiple platfor
Telegram Trigger, Telegram, HTTP Request +4
The problem Ever attend a networking event and find yourself taking screenshots of people's LinkedIn? Sounds counter-intuitive because you are connecting on LinkedIn. But you find it hard to keep trac
Google Sheets Trigger, Google Drive, OpenAI +1
This workflow is perfect for eCommerce teams, market researchers, and product analysts who want to track or extract product information from websites that restrict scraping tools. It’s also useful for
Google Sheets Trigger, HTTP Request, Google Drive +2