PDF 인보이스 데이터 추출하여 JSON에 저장

• •특별한 사전 요구사항 없이 가져와 바로 사용 가능합니다

{
  "meta": {
    "instanceId": "d1451097bf16b4787e3f6ede2b364ece110261879ec2f0efaeba689056c0a1ab"
  },
  "nodes": [
    {
      "id": "3a0d9a6f-6e6e-44a3-9eb0-1755b01fed0c",
      "name": "양식 제출 시",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        672,
        -480
      ],
      "webhookId": "0387941a-9e42-44ab-96ac-dde230418ac3",
      "parameters": {
        "options": {},
        "formTitle": "Test",
        "formFields": {
          "values": [
            {
              "fieldType": "file",
              "fieldLabel": "data"
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "d510fda8-ceaa-4d57-8946-39a97b23f3e1",
      "name": "파일에서 추출",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        832,
        -480
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "e070def8-b13a-49fa-ae4a-e366d1f474da",
      "name": "모델에 메시지",
      "type": "@n8n/n8n-nodes-langchain.googleGemini",
      "position": [
        704,
        -240
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "models/gemma-3n-e4b-it",
          "cachedResultName": "models/gemma-3n-e4b-it"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "content": "=Considera la transcripcion del invoice adjunta, reescribela como un XML siguiendo este esquema:\n\n{{ $json.estructuraXML }}\n\nInvoice:\n\n{{ $json.text_limpio }}"
            }
          ]
        }
      },
      "credentials": {
        "googlePalmApi": {
          "id": "d4exk6UjdeHXH93h",
          "name": "Google Gemini(PaLM) Api account 2"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "4e435b5b-95da-4b6a-a888-c2f74cd96cd1",
      "name": "Limpio 데이터",
      "type": "n8n-nodes-base.set",
      "position": [
        1104,
        -480
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "ad0e7b3d-4011-4bfb-851e-c049883dc00a",
              "name": "text_limpio",
              "type": "string",
              "value": "={{ $json.text.replace(/\\n/g, ' ') }}"
            },
            {
              "id": "e0b6ea3e-17d6-4c18-a5f5-1b2cf98b4ddb",
              "name": "estructuraXML",
              "type": "string",
              "value": "<invoice>\n    <invoice_number>[invoice_number]</invoice_number>\n    <date_of_issue>[date_of_issue]</date_of_issue>\n    <due_date>[due_date]</due_date>\n\n    <billed_to>\n        <company_name>[billed_to.company_name]</company_name>\n        <contact_name>[billed_to.contact_name]</contact_name>\n        <address>[billed_to.address]</address>\n        <postal_code>[billed_to.postal_code]</postal_code>\n        <city>[billed_to.city]</city>\n        <state>[billed_to.state]</state>\n        <country>[billed_to.country]</country>\n        <rfc>[billed_to.rfc]</rfc>\n    </billed_to>\n\n    <from>\n        <company_name>[from.company_name]</company_name>\n        <address>[from.address]</address>\n        <postal_code>[from.postal_code]</postal_code>\n        <city>[from.city]</city>\n        <state>[from.state]</state>\n        <country>[from.country]</country>\n        <rfc>[from.rfc]</rfc>\n    </from>\n\n    <purchase_order>[purchase_order]</purchase_order>\n\n    <items>\n        <item>\n            <description>[item.description]</description>\n            <unit_cost>[item.unit_cost]</unit_cost>\n            <quantity>[item.quantity]</quantity>\n            <amount>[item.amount]</amount>\n        </item>\n        </items>\n\n    <bank_account_details>\n        <account_holder_name>[bank_account_details.account_holder_name]</account_holder_name>\n        <account_number>[bank_account_details.account_number]</account_number>\n        <routing_number>[bank_account_details.routing_number]</routing_number>\n        <swift_code>[bank_account_details.swift_code]</swift_code>\n        <bank_name>[bank_account_details.bank_name]</bank_name>\n        <currency>[bank_account_details.currency]</currency>\n    </bank_account_details>\n\n    <financials>\n        <subtotal>[subtotal]</subtotal>\n        <tax_rate>[tax_rate]</tax_rate>\n        <tax_amount>[tax_amount]</tax_amount>\n        <shipping_cost>[shipping_cost]</shipping_cost>\n        <invoice_total>[invoice_total]</invoice_total>\n    </financials>\n</invoice>"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "93fd56a6-33f9-4ac2-88b2-72157beb871f",
      "name": "Limpio XML",
      "type": "n8n-nodes-base.set",
      "position": [
        1040,
        -240
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "ddaad091-c54e-44d9-bf05-604e3bf43caa",
              "name": "factura_limpia",
              "type": "string",
              "value": "={{ $json.content.parts[0].text.replace('```xml', '').replace('```', '').replace(/(\\n|\\s{2,})/g, '').replace(/(\\s<)/g, '<').replace(/(>\\s)/g, '>') }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "9d96dd97-9048-4a6f-b11c-52c30a6d3fa3",
      "name": "XML에서 JSON으로",
      "type": "n8n-nodes-base.xml",
      "position": [
        1200,
        -240
      ],
      "parameters": {
        "options": {
          "trim": false,
          "normalize": false,
          "normalizeTags": false
        },
        "dataPropertyName": "factura_limpia"
      },
      "typeVersion": 1
    },
    {
      "id": "ee4365f4-08b5-42de-afb7-6a187272fabb",
      "name": "스티커 노트",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        624,
        -544
      ],
      "parameters": {
        "color": 4,
        "width": 352,
        "height": 240,
        "content": "## PDF to text"
      },
      "typeVersion": 1
    },
    {
      "id": "e6bdaed7-1cee-4412-86c8-c7409ac1231e",
      "name": "스티커 노트1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        976,
        -544
      ],
      "parameters": {
        "color": 2,
        "width": 368,
        "height": 240,
        "content": "## Clean data and XML structure definition"
      },
      "typeVersion": 1
    },
    {
      "id": "26faacbb-3464-46fe-8e1f-cd105942d179",
      "name": "스티커 노트2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        624,
        -304
      ],
      "parameters": {
        "color": 3,
        "width": 352,
        "height": 256,
        "content": "## Generate XML string"
      },
      "typeVersion": 1
    },
    {
      "id": "33493f4d-a615-4a80-8727-7ebba208f215",
      "name": "스티커 노트3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        976,
        -304
      ],
      "parameters": {
        "color": 5,
        "width": 368,
        "height": 256,
        "content": "## String to XML to Json"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "93fd56a6-33f9-4ac2-88b2-72157beb871f": {
      "main": [
        [
          {
            "node": "9d96dd97-9048-4a6f-b11c-52c30a6d3fa3",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "4e435b5b-95da-4b6a-a888-c2f74cd96cd1": {
      "main": [
        [
          {
            "node": "e070def8-b13a-49fa-ae4a-e366d1f474da",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "e070def8-b13a-49fa-ae4a-e366d1f474da": {
      "main": [
        [
          {
            "node": "93fd56a6-33f9-4ac2-88b2-72157beb871f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d510fda8-ceaa-4d57-8946-39a97b23f3e1": {
      "main": [
        [
          {
            "node": "4e435b5b-95da-4b6a-a888-c2f74cd96cd1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "3a0d9a6f-6e6e-44a3-9eb0-1755b01fed0c": {
      "main": [
        [
          {
            "node": "d510fda8-ceaa-4d57-8946-39a97b23f3e1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}