8
n8n 中文网amn8n.com

PDF发票数据提取到JSON

中级

这是一个Miscellaneous, AI Summarization, Multimodal AI领域的自动化工作流，包含 10 个节点。主要使用 Set, Xml, FormTrigger, ExtractFromFile, GoogleGemini 等节点。 使用Gemini AI和XML转换从PDF中提取发票数据到JSON

前置要求
  • •无特殊前置要求，导入即可使用

使用的节点 (10)

Set
Xml
StickyNote
FormTrigger
ExtractFromFile
GoogleGemini

分类

杂项
AI 摘要总结
多模态 AI
工作流预览
可视化展示节点连接关系，支持缩放和平移
React Flow
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
  "meta": {
    "instanceId": "d1451097bf16b4787e3f6ede2b364ece110261879ec2f0efaeba689056c0a1ab"
  },
  "nodes": [
    {
      "id": "3a0d9a6f-6e6e-44a3-9eb0-1755b01fed0c",
      "name": "表单提交时",
      "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": "从文件提取",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        832,
        -480
      ],
      "parameters": {
        "options": {},
        "operation": "pdf"
      },
      "typeVersion": 1
    },
    {
      "id": "e070def8-b13a-49fa-ae4a-e366d1f474da",
      "name": "消息模型",
      "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": "清理数据",
      "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": "清理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": "XML转JSON",
      "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": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        624,
        -544
      ],
      "parameters": {
        "color": 4,
        "width": 352,
        "height": 240,
        "content": "## PDF转文本"
      },
      "typeVersion": 1
    },
    {
      "id": "e6bdaed7-1cee-4412-86c8-c7409ac1231e",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        976,
        -544
      ],
      "parameters": {
        "color": 2,
        "width": 368,
        "height": 240,
        "content": "## 清理数据和XML结构定义"
      },
      "typeVersion": 1
    },
    {
      "id": "26faacbb-3464-46fe-8e1f-cd105942d179",
      "name": "便签2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        624,
        -304
      ],
      "parameters": {
        "color": 3,
        "width": 352,
        "height": 256,
        "content": "## 生成XML字符串"
      },
      "typeVersion": 1
    },
    {
      "id": "33493f4d-a615-4a80-8727-7ebba208f215",
      "name": "便签3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        976,
        -304
      ],
      "parameters": {
        "color": 5,
        "width": 368,
        "height": 256,
        "content": "## 字符串转XML转Json"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "Limpio XML": {
      "main": [
        [
          {
            "node": "XML to JSON",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Limpio data": {
      "main": [
        [
          {
            "node": "Message a model",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Message a model": {
      "main": [
        [
          {
            "node": "Limpio XML",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from File": {
      "main": [
        [
          {
            "node": "Limpio data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "On form submission": {
      "main": [
        [
          {
            "node": "Extract from File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
常见问题

如何使用这个工作流？

复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。

这个工作流适合什么场景？

中级 - 杂项, AI 摘要总结, 多模态 AI

需要付费吗？

本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。

相关工作流推荐

演示 - 分享模板 - 从职位描述构建候选人短名单
AI招聘流程：使用Apollo和Airtable从职位到候选人短名单
Set
Limit
Switch
+12
40 节点Fabian Herhold
杂项
AI驱动的Telegram发票提取器
基于AI的Telegram发票提取器，数据导出至Airtable
Set
Switch
Telegram
+7
17 节点BizThrive.ai
杂项
使用Gemini 2.5 Pro AI分类自动标记Gmail邮件
使用Gemini 2.5 Pro AI分类自动标记Gmail邮件
Set
Code
Gmail
+4
9 节点Aryan Shinde
杂项
使用 AI 数据提取、Google Drive 和 Sheets 自动化发票处理
通过 AI 数据提取、Google Drive 和 Sheets 实现发票处理的自动化
If
Set
Split Out
+8
29 节点Romain
杂项
动态AI网络研究员：从纯文本到自定义CSV
使用GPT-4和Linkup将纯文本转换为自定义CSV的动态AI网络研究员
Set
Code
Split Out
+7
16 节点Guillaume Duvernay
杂项
使用ScrapeGraph AI提取n8n社区最近添加的工作流
使用ScrapeGraphAI和Gemini提取和存储n8n社区最近添加的工作流
Set
Merge
Split Out
+12
21 节点Davide
杂项
工作流信息
难度等级
中级
节点数量10
分类3
节点类型6
难度说明

适合有一定经验的用户，包含 6-15 个节点的中等复杂度工作流

作者
Mauricio Perera

Mauricio Perera

@rckflr

Automation consultant with over 10 years of experience specializing in AI, no-code, and workflow optimization. I’ve delivered tailored AI and NLP solutions across real estate, healthcare, and more, enhancing efficiency and customer experiences. Proficient in tools like Make, Airtable, and Zapier, I also integrate GPT models to create scalable, innovative automations. Contact me to discuss custom n8n workflows or advanced automations to streamline your processes.

外部链接
在 n8n.io 查看 →

分享此工作流