Automate Deep Research with Scrapegraphai, Gpt-4 & Google Sheets

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 →

{
  "id": "VhEwspDqzu7ssFVE",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "My workflow 2",
  "tags": [],
  "nodes": [
    {
      "id": "48a84828-73de-4f4b-beb1-60e668342c11",
      "name": "Research Request Webhook",
      "type": "n8n-nodes-base.webhook",
      "position": [
        -2048,
        624
      ],
      "parameters": {
        "path": "research-trigger",
        "options": {},
        "httpMethod": "POST",
        "responseMode": "responseNode"
      },
      "typeVersion": 1.1
    },
    {
      "id": "5d8a05fa-1528-4dc4-95cd-d99625a2221b",
      "name": "Research Configuration Processor",
      "type": "n8n-nodes-base.code",
      "position": [
        -1760,
        624
      ],
      "parameters": {
        "jsCode": "// Extract and validate research parameters\nconst body = $input.all()[0].json.body;\n\n// Default research configuration\nconst researchConfig = {\n  topic: body.topic || 'artificial intelligence trends',\n  depth: body.depth || 'comprehensive', // basic, detailed, comprehensive\n  sources: body.sources || ['web', 'academic', 'news'],\n  timeframe: body.timeframe || '6months',\n  language: body.language || 'en',\n  maxSources: body.maxSources || 10,\n  analysisType: body.analysisType || 'summary' // summary, detailed, comparative\n};\n\n// Generate search queries based on topic\nconst baseQueries = [\n  `${researchConfig.topic} latest developments`,\n  `${researchConfig.topic} research findings`,\n  `${researchConfig.topic} market analysis`,\n  `${researchConfig.topic} expert opinions`,\n  `${researchConfig.topic} case studies`\n];\n\n// Add specific queries based on depth\nif (researchConfig.depth === 'comprehensive') {\n  baseQueries.push(\n    `${researchConfig.topic} academic papers`,\n    `${researchConfig.topic} industry reports`,\n    `${researchConfig.topic} statistical data`,\n    `${researchConfig.topic} future predictions`\n  );\n}\n\nreturn [{\n  json: {\n    ...researchConfig,\n    searchQueries: baseQueries,\n    timestamp: new Date().toISOString(),\n    sessionId: `research_${Date.now()}`\n  }\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "19e3c76b-f0fb-4324-b212-585ab132bde5",
      "name": "Split Search Queries",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -1456,
        624
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "6eb0ff10-aaf6-430f-aea0-7c0cbe950b95",
      "name": "Query Selector",
      "type": "n8n-nodes-base.code",
      "position": [
        -1152,
        624
      ],
      "parameters": {
        "jsCode": "// Get current batch data\nconst items = $input.all();\nconst currentItem = items[0].json;\nconst queries = currentItem.searchQueries;\nconst currentBatch = $('Split Search Queries').item.json;\n\n// Get current query\nconst currentQuery = queries[currentBatch.index];\n\nreturn [{\n  json: {\n    ...currentItem,\n    currentQuery: currentQuery,\n    batchIndex: currentBatch.index\n  }\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "99f73593-0ddd-4fc9-810f-8b1793cd8476",
      "name": "AI Research Scraper",
      "type": "n8n-nodes-scrapegraphai.scrapegraphAi",
      "position": [
        -848,
        624
      ],
      "parameters": {
        "userPrompt": "Research and extract comprehensive information about this topic. Provide: 1) Key findings and insights, 2) Important statistics or data points, 3) Expert quotes or opinions, 4) Recent developments, 5) Source credibility assessment. Format as structured JSON with fields: title, summary, keyPoints, statistics, quotes, sources, credibilityScore, datePublished, relevanceScore.",
        "websiteUrl": "={{ $json.currentQuery }}"
      },
      "typeVersion": 1
    },
    {
      "id": "da52e96d-0aa2-41ef-886e-bd396e0f42f2",
      "name": "News Sources Scraper",
      "type": "n8n-nodes-scrapegraphai.scrapegraphAi",
      "position": [
        -848,
        832
      ],
      "parameters": {
        "userPrompt": "Extract recent news articles about this topic. For each article provide: headline, publication date, source, brief summary, and direct URL. Focus on credible news sources and recent publications within the last 6 months.",
        "websiteUrl": "https://www.google.com/search?q={{ encodeURIComponent($json.currentQuery) }}&tbm=nws"
      },
      "typeVersion": 1
    },
    {
      "id": "0ee6cf16-02e5-4a3b-b068-dd76a1351718",
      "name": "Academic Sources Scraper",
      "type": "n8n-nodes-scrapegraphai.scrapegraphAi",
      "position": [
        -848,
        1024
      ],
      "parameters": {
        "userPrompt": "Extract academic papers and research studies. For each paper provide: title, authors, publication year, journal/conference, citation count, abstract summary, and DOI/URL if available. Focus on peer-reviewed sources and recent publications.",
        "websiteUrl": "https://scholar.google.com/scholar?q={{ encodeURIComponent($json.currentQuery) }}"
      },
      "typeVersion": 1
    },
    {
      "id": "3228908f-f816-4a0c-889b-abf756281eb8",
      "name": "Merge Research Sources",
      "type": "n8n-nodes-base.merge",
      "position": [
        -560,
        832
      ],
      "parameters": {
        "mode": "combine",
        "options": {},
        "mergeByFields": {
          "values": [
            {}
          ]
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "90b55ee1-3404-4db2-aec1-6d6219043c09",
      "name": "Research Data Processor",
      "type": "n8n-nodes-base.code",
      "position": [
        -256,
        832
      ],
      "parameters": {
        "jsCode": "// Combine and process all research data\nconst allItems = $input.all();\nconst researchData = allItems[0].json;\nconst newsData = allItems[1]?.json || {};\nconst academicData = allItems[2]?.json || {};\n\n// Extract and structure the research findings\nconst processedData = {\n  sessionId: researchData.sessionId,\n  query: researchData.currentQuery,\n  batchIndex: researchData.batchIndex,\n  timestamp: new Date().toISOString(),\n  \n  // General research findings\n  generalFindings: {\n    title: researchData.result?.title || 'Research Findings',\n    summary: researchData.result?.summary || '',\n    keyPoints: researchData.result?.keyPoints || [],\n    statistics: researchData.result?.statistics || [],\n    credibilityScore: researchData.result?.credibilityScore || 0\n  },\n  \n  // News findings\n  newsFindings: {\n    articles: newsData.result?.articles || [],\n    totalArticles: newsData.result?.articles?.length || 0\n  },\n  \n  // Academic findings\n  academicFindings: {\n    papers: academicData.result?.papers || [],\n    totalPapers: academicData.result?.papers?.length || 0\n  },\n  \n  // Meta information\n  sourceTypes: ['general', 'news', 'academic'],\n  totalSources: (researchData.result?.sources?.length || 0) + \n                (newsData.result?.articles?.length || 0) + \n                (academicData.result?.papers?.length || 0)\n};\n\nreturn [{\n  json: processedData\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "7eb34b80-f6d2-4e80-83f5-529d4748cbec",
      "name": "Research Data Storage",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        352,
        832
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "sessionId",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Session ID",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "query",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Research Query",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "timestamp",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Timestamp",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "analysis",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "AI Analysis",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "totalSources",
              "type": "number",
              "display": true,
              "required": false,
              "displayName": "Total Sources",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": []
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "name",
          "value": "Research_Data"
        },
        "documentId": {
          "__rl": true,
          "mode": "url",
          "value": ""
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "d093ce1d-9716-4254-89b7-4b8bffd23b48",
      "name": "Research Complete Response",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        656,
        832
      ],
      "parameters": {
        "options": {},
        "respondWith": "json",
        "responseBody": "={{ JSON.stringify({\n  status: 'completed',\n  sessionId: $json.sessionId,\n  message: 'Research analysis completed successfully',\n  totalSources: $json.totalSources,\n  timestamp: $json.timestamp\n}) }}"
      },
      "typeVersion": 1.1
    },
    {
      "id": "8398d709-67b8-4ad4-90f0-d2c041d4678e",
      "name": "Webhook Trigger Guide",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2160,
        -448
      ],
      "parameters": {
        "color": 2,
        "width": 520,
        "height": 1732,
        "content": "# Step 1: Research Request Webhook \ud83c\udfaf\n\nThis webhook endpoint receives research requests and initiates the deep research process.\n\n## Request Format\n```json\n{\n  \"topic\": \"artificial intelligence in healthcare\",\n  \"depth\": \"comprehensive\",\n  \"sources\": [\"web\", \"academic\", \"news\"],\n  \"timeframe\": \"6months\",\n  \"maxSources\": 15,\n  \"analysisType\": \"detailed\"\n}\n```\n\n## Configuration\n- **Method**: POST\n- **Path**: /research-trigger\n- **Authentication**: Optional API key\n- **Rate Limiting**: Configurable\n\n## Depth Levels\n- **Basic**: Quick overview with 3-5 sources\n- **Detailed**: Comprehensive analysis with 8-12 sources\n- **Comprehensive**: Deep dive with 15+ sources and academic papers\n\n## Source Types\n- **Web**: General web content and industry sites\n- **News**: Recent news articles and press releases\n- **Academic**: Peer-reviewed papers and research studies"
      },
      "typeVersion": 1
    },
    {
      "id": "965963f7-6f98-4954-a0f0-916ab00477be",
      "name": "Configuration Guide",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1600,
        -448
      ],
      "parameters": {
        "color": 2,
        "width": 520,
        "height": 1748,
        "content": "# Step 2: Research Configuration Processor \ud83d\udd27\n\nThis node processes and validates the incoming research request, setting up the research parameters.\n\n## What it does\n- Validates and sanitizes input parameters\n- Sets default values for missing parameters\n- Generates multiple search queries based on topic\n- Creates unique session ID for tracking\n- Configures research depth and scope\n\n## Query Generation Strategy\n- **Base Queries**: Core topic searches\n- **Depth-Specific**: Additional queries for comprehensive research\n- **Time-Sensitive**: Recent developments and trends\n- **Multi-Angle**: Different perspectives and viewpoints\n\n## Customization Options\n- Modify query generation logic\n- Add industry-specific search patterns\n- Implement custom validation rules\n- Configure default research parameters"
      },
      "typeVersion": 1
    },
    {
      "id": "47a160d4-d829-4133-93fa-aa4dbd41f785",
      "name": "AI Scraping Guide",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1040,
        -448
      ],
      "parameters": {
        "color": 3,
        "width": 520,
        "height": 1748,
        "content": "# Step 3: Multi-Source AI Scraping \ud83e\udd16\n\nThree parallel AI-powered scrapers collect data from different source types for comprehensive research coverage.\n\n## AI Research Scraper\n- **Purpose**: General web research and industry insights\n- **Focus**: Key findings, statistics, expert opinions\n- **Output**: Structured insights with credibility scores\n\n## News Sources Scraper\n- **Purpose**: Recent news and current developments\n- **Focus**: Headlines, publication dates, credible sources\n- **Output**: Timestamped news articles with summaries\n\n## Academic Sources Scraper\n- **Purpose**: Peer-reviewed research and scholarly articles\n- **Focus**: Academic papers, citations, research studies\n- **Output**: Scientific literature with metadata\n\n## ScrapeGraphAI Benefits\n- **AI-Powered**: Intelligent content extraction\n- **Structured Output**: Consistent data format\n- **Source Validation**: Credibility assessment\n- **Multi-Language**: Global research capability"
      },
      "typeVersion": 1
    },
    {
      "id": "503cdf42-cee7-4b44-a2fd-4f4a4a134f60",
      "name": "Processing & Analysis Guide",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -464,
        -448
      ],
      "parameters": {
        "color": 3,
        "width": 520,
        "height": 1748,
        "content": "# Step 4: Data Processing & AI Analysis \ud83e\udde0\n\nAdvanced data processing and AI-powered analysis to generate actionable insights from collected research data.\n\n## Research Data Processor\n- **Combines**: All source types into unified structure\n- **Validates**: Data quality and completeness\n- **Enriches**: Metadata and source attribution\n- **Structures**: For optimal analysis and storage\n\n## AI Research Analyst\n- **Model**: GPT-4 for sophisticated analysis\n- **Analysis Types**: Summary, trends, conflicts, reliability\n- **Output**: Executive summary with actionable insights\n- **Temperature**: Low (0.3) for consistent, factual analysis\n\n## Analysis Components\n1. **Executive Summary**: High-level overview\n2. **Key Insights**: Major findings and trends\n3. **Reliability Assessment**: Source credibility evaluation\n4. **Recommendations**: Actionable next steps\n5. **Further Research**: Suggested investigation areas"
      },
      "typeVersion": 1
    },
    {
      "id": "0105d893-94ce-465d-9ef8-8f144280f0c9",
      "name": "Storage & Response Guide",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        144,
        -432
      ],
      "parameters": {
        "color": 4,
        "width": 840,
        "height": 1716,
        "content": "# Step 5: Data Storage & Response \ud83d\udcca\n\nSecure storage of research findings and structured response delivery for seamless integration with other systems.\n\n## Google Sheets Storage\n- **Sheet Structure**: Research_Data with comprehensive columns\n- **Data Retention**: Historical research for trend analysis\n- **Access Control**: Secure OAuth2 authentication\n- **Format**: Structured data ready for analysis and reporting\n\n## Response Delivery\n- **Format**: JSON with status and metadata\n- **Content**: Session ID, completion status, source count\n- **Integration**: Ready for webhook consumers and APIs\n- **Tracking**: Unique session IDs for research correlation\n\n## Data Management Features\n- **Versioning**: Track research iterations\n- **Export**: Multiple format support\n- **Sharing**: Team collaboration capabilities\n- **Analytics**: Built-in Google Sheets analysis tools\n\n## Use Cases\n- **Market Research**: Competitive analysis and trends\n- **Academic Research**: Literature reviews and citations\n- **Business Intelligence**: Industry insights and reports"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "076dd376-d6cb-4851-b335-e074cd47911c",
  "connections": {
    "Query Selector": {
      "main": [
        [
          {
            "node": "AI Research Scraper",
            "type": "main",
            "index": 0
          },
          {
            "node": "News Sources Scraper",
            "type": "main",
            "index": 0
          },
          {
            "node": "Academic Sources Scraper",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI Research Scraper": {
      "main": [
        [
          {
            "node": "Merge Research Sources",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "News Sources Scraper": {
      "main": [
        [
          {
            "node": "Merge Research Sources",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Split Search Queries": {
      "main": [
        [
          {
            "node": "Query Selector",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Research Data Storage": {
      "main": [
        [
          {
            "node": "Research Complete Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Merge Research Sources": {
      "main": [
        [
          {
            "node": "Research Data Processor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Research Data Processor": {
      "main": [
        [
          {
            "node": "Research Data Storage",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Research Request Webhook": {
      "main": [
        [
          {
            "node": "Research Configuration Processor",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Research Configuration Processor": {
      "main": [
        [
          {
            "node": "Split Search Queries",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

About this workflow

Market researchers and analysts Business intelligence teams Academic researchers and students Content creators and journalists Product managers conducting market research Consultants performing competitive analysis Data scientists gathering research data Marketing teams…

Source: https://n8n.io/workflows/6437/ — original creator credit. Request a take-down →

More Data & Sheets workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.