Extracción de datos de sitios web a partir de entradas de formularios (Gemini 2.5 flash + Gmail)

• •Cuenta de Google y credenciales de API de Gmail
• •Pueden requerirse credenciales de autenticación para la API de destino
• •Clave de API de Google Gemini

{
  "meta": {
    "instanceId": "d1786ab0d745a7498abf13a9c2cdabb1374c006e889b79eef64ce0386b8f8a41",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "6d85bf32-59a5-4644-b5b0-d31aaf677bda",
      "name": "Analizador de salida estructurada",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        640,
        200
      ],
      "parameters": {
        "jsonSchemaExample": "{\n    \"result\": \"extracted value(s)\"\n}"
      },
      "typeVersion": 1.2
    },
    {
      "id": "d011794a-d4bf-4750-9ad1-3cb0df662aff",
      "name": "Obtener HTML desde URL fuente",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        40,
        0
      ],
      "parameters": {
        "url": "={{ $json['Source URL'] }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "389ac2ce-39d8-4bc9-a1af-7ea3dba0240d",
      "name": "Cadena LLM de extractor de datos",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        460,
        0
      ],
      "parameters": {
        "text": "=Your task is to extract the exact information specified by the user.\n\nUser’s extraction request:\n\"{{ $('Web Scraper form submission').item.json['Data to extract'] }}\"\n\nRules:\n1. Extract ONLY the requested information.\n2. If multiple matches exist, combine them into a single string separated by commas.\n3. Do NOT add explanations or extra text—output only the extracted data.\n4. Maintain the original values unless formatting is requested.\n5. If no matches are found, return: { \"result\": \"No data found\" }.\n6. Always return the response in this format:\n{\n    \"result\": \"extracted value(s)\"\n}\n\nHere is the source data:\n{{ $json.body }}\n",
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.6
    },
    {
      "id": "a73e7657-4a79-4b50-973f-e27d406f0278",
      "name": "Gmail - Enviar resultado",
      "type": "n8n-nodes-base.gmail",
      "position": [
        880,
        0
      ],
      "webhookId": "fa29cdcc-e8e9-449a-a6a4-88a874e2a0c5",
      "parameters": {
        "sendTo": " template_data_extactor_replace_me@yopmail.com",
        "message": "=Your web scraping task has been completed.\n\nSource URL:\n{{ $('Web Scraper form submission').item.json['Source URL'] }}\n\nData Requested:\n{{ $('Web Scraper form submission').item.json['Data to extract'] }}\n\nExtracted Result:\n{{ $json.output.result }}\n\nThank you for using our web scraping automation.",
        "options": {
          "appendAttribution": false
        },
        "subject": "=✅ Web Scraping Result for {{ $('Web Scraper form submission').item.json['Source URL'] }}",
        "emailType": "text"
      },
      "credentials": {
        "gmailOAuth2": {
          "id": "CeBpTZBQSAMKVKJY",
          "name": "Gmail account (Billy Email 2)"
        }
      },
      "typeVersion": 2.1
    },
    {
      "id": "ec13f750-6015-4c17-b062-9036b0ae8697",
      "name": "Envío de formulario con raspador web",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        -160,
        0
      ],
      "webhookId": "a757a352-5ab2-4fa7-a8ee-08bb5d3448cc",
      "parameters": {
        "options": {},
        "formTitle": "Web Scraper Form",
        "formFields": {
          "values": [
            {
              "fieldLabel": "Source URL"
            },
            {
              "fieldLabel": "Data to extract"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "1ed56fc9-5124-454c-8b4d-ee2c9e72076c",
      "name": "Nota adhesiva4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1100,
        -260
      ],
      "parameters": {
        "color": 4,
        "width": 380,
        "height": 760,
        "content": "# 👋 Hi, I’m Billy!\n\nI help businesses build **n8n workflows** & **AI automation projects**.  \nNeed help with n8n or AI Automation projects? \nContact me and let’s build your automation together.\n\n📩 **Email:** billychartanto@gmail.com  \n🤝 **n8n Creator:** [n8n.io/creators/billy](https://n8n.io/creators/billy/)\n🌐 **My n8n Projects:** [billychristi.com/n8n](https://www.billychristi.com/n8n)  \n\n\n\n---\n💡 Feel free to get in touch if you’d like help on your next automation project or if you have any feedback or thoughts to share.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "4b1b75f3-95fa-4a42-8180-cb47ef7c3a02",
      "name": "Nota adhesiva",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -760,
        -80
      ],
      "parameters": {
        "color": 4,
        "width": 500,
        "height": 360,
        "content": "## SETUP REQUIRED\n\nWorkflow Configurations:\n- Update the email recipient in the Gmail node (currently set to template_data_extactor_replace_me@yopmail.com)\n- Adjust the JSON schema in the Structured Output Parser if you need different output formats\n- Modify the LLM prompt in the Data Extractor LLM Chain based on your specific extraction requirements\n\nRequired Credentials:\n- Google Gemini API Key (Google PaLM API account)\n- Gmail Credential for sending result emails"
      },
      "typeVersion": 1
    },
    {
      "id": "35116b5c-c3ab-4c47-9914-c6cecdf3e3b4",
      "name": "Nota adhesiva1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -860,
        420
      ],
      "parameters": {
        "color": 4,
        "width": 600,
        "height": 400,
        "content": "## 🔍Extract Specific Website Data with Form Input, Gemini 2.5 flash and Gmail Delivery\n\nWhat This Template Does:\n\n- Provides a web form interface for users to submit scraping requests\n- Accepts any website URL and custom data extraction requirements\n- Fetches HTML content from the specified source URL\n- Uses Google Gemini AI to intelligently extract only the requested information\n- Processes raw HTML content and returns structured JSON results\n- Automatically sends extraction results via Gmail with detailed reporting\n- Handles various data types and formats while maintaining original values unless formatting is requested\n"
      },
      "typeVersion": 1
    },
    {
      "id": "b1526d24-29c6-4552-8964-84953933494b",
      "name": "Nota adhesiva2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -220,
        420
      ],
      "parameters": {
        "color": 4,
        "width": 1000,
        "height": 300,
        "content": "## 📋 WORKFLOW PROCESS OVERVIEW\n\nStep 1: 📝 Web Scraper Form Submission triggers the workflow when users submit URL and extraction requirements\nStep 2: 🌐 Get HTML from Source URL fetches the complete HTML content from the provided website\nStep 3: 🔧 HTML Extractor processes the raw HTML and extracts the body content for analysis\nStep 4: 🤖 Data Extractor LLM Chain uses Google Gemini AI to analyze content and extract only the specific data requested by the user\nStep 5: 📊 Structured Output Parser formats the AI response into clean JSON structure with standardized format\nStep 6: 📧 Gmail Send Result delivers the extraction results via email including:\n  - Original source URL\n  - Data extraction request details  \n  - Clean extracted results\n  - Professional formatting with success confirmation"
      },
      "typeVersion": 1
    },
    {
      "id": "461e0675-1755-41eb-b445-20fd0d733d8c",
      "name": "Nota adhesiva3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        380,
        -180
      ],
      "parameters": {
        "color": 4,
        "width": 400,
        "height": 560,
        "content": "## Data Extractor LLM Chain  \nThis is where we extract the content based on the user request  \n\nConfiguration:  \nYou can update the prompt and the model here to adjust to your use case.  \n"
      },
      "typeVersion": 1
    },
    {
      "id": "e147282c-51f0-4f76-8416-bfeb00a47f64",
      "name": "Nota adhesiva5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        800,
        -160
      ],
      "parameters": {
        "color": 4,
        "width": 260,
        "height": 340,
        "content": "## Gmail - Send Results  \n\nConfiguration:  \nUpdate the target email  \nUpdate the email subject and body  \n"
      },
      "typeVersion": 1
    },
    {
      "id": "adb7c780-8210-4dab-ad4f-9e7fc366cd16",
      "name": "Modelo de chat Google Gemini",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        440,
        200
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.5-flash"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "gdaO8lU3HwsldifM",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "25e49c2a-9018-4503-8ce1-a95699e9941c",
      "name": "Extractor HTML",
      "type": "n8n-nodes-base.html",
      "position": [
        220,
        0
      ],
      "parameters": {
        "options": {},
        "operation": "extractHtmlContent",
        "extractionValues": {
          "values": [
            {
              "key": "body",
              "cssSelector": "body"
            }
          ]
        }
      },
      "typeVersion": 1.2
    }
  ],
  "pinData": {},
  "connections": {
    "25e49c2a-9018-4503-8ce1-a95699e9941c": {
      "main": [
        [
          {
            "node": "389ac2ce-39d8-4bc9-a1af-7ea3dba0240d",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "389ac2ce-39d8-4bc9-a1af-7ea3dba0240d": {
      "main": [
        [
          {
            "node": "a73e7657-4a79-4b50-973f-e27d406f0278",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d011794a-d4bf-4750-9ad1-3cb0df662aff": {
      "main": [
        [
          {
            "node": "25e49c2a-9018-4503-8ce1-a95699e9941c",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "adb7c780-8210-4dab-ad4f-9e7fc366cd16": {
      "ai_languageModel": [
        [
          {
            "node": "389ac2ce-39d8-4bc9-a1af-7ea3dba0240d",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "6d85bf32-59a5-4644-b5b0-d31aaf677bda": {
      "ai_outputParser": [
        [
          {
            "node": "389ac2ce-39d8-4bc9-a1af-7ea3dba0240d",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "ec13f750-6015-4c17-b062-9036b0ae8697": {
      "main": [
        [
          {
            "node": "d011794a-d4bf-4750-9ad1-3cb0df662aff",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}