8
n8n 中文网amn8n.com

💡🌐 基于Jina.ai的多页面网站爬虫

高级

这是一个AI领域的自动化工作流，包含 16 个节点。主要使用 Set, Xml, Code, Wait, Limit 等节点，结合人工智能技术实现智能自动化。 💡🌐 使用Jina.ai的多页面网站爬虫工具

前置要求
  • •Google Drive API 凭证
  • •可能需要目标 API 的认证凭证

使用的节点 (16)

Set
Xml
Code
Wait
Limit
Filter
SplitOut
StickyNote
GoogleDrive
HttpRequest
ManualTrigger
SplitInBatches

分类

人工智能
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
{
  "id": "xEij0kj2I1DHbL3I",
  "meta": {
    "instanceId": "31e69f7f4a77bf465b805824e303232f0227212ae922d12133a0f96ffeab4fef",
    "templateCredsSetupCompleted": true
  },
  "name": "💡🌐 基于 Jina.ai 的必备多页面网站爬虫",
  "tags": [],
  "nodes": [
    {
      "id": "3a503859-ef0a-492d-81c6-37e4f0c4c25e",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -840,
        0
      ],
      "parameters": {
        "color": 3,
        "width": 340,
        "height": 320,
        "content": "## Jina.ai 网络爬虫"
      },
      "typeVersion": 1
    },
    {
      "id": "c5217a1a-f074-409b-8340-72afdc5fc8b5",
      "name": "当点击\"测试工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -1500,
        -300
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "72af3b00-2632-4877-a0b6-7477e2f468f7",
      "name": "遍历项目",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        -1080,
        20
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "11f0fa02-51f8-41cc-b789-5c452b6899aa",
      "name": "等待",
      "type": "n8n-nodes-base.wait",
      "position": [
        80,
        220
      ],
      "webhookId": "081ce124-0cbf-4a21-a1e7-2c465f460448",
      "parameters": {},
      "typeVersion": 1.1
    },
    {
      "id": "cf3b5887-8ff2-46e0-ab33-384ab0987cbb",
      "name": "限制",
      "type": "n8n-nodes-base.limit",
      "position": [
        80,
        -300
      ],
      "parameters": {
        "maxItems": 20
      },
      "typeVersion": 1
    },
    {
      "id": "c4f04d82-aa33-46cf-a8e2-0b4e717e754a",
      "name": "获取网站 URL 列表",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -780,
        -300
      ],
      "parameters": {
        "url": "={{ $json.sitemap_url }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "7f507c38-1e9e-4c46-8dea-bd6daf65dc55",
      "name": "转换为 JSON",
      "type": "n8n-nodes-base.xml",
      "position": [
        -560,
        -300
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1
    },
    {
      "id": "e21b55c2-8b0d-4c7c-ba91-a2d563a4c966",
      "name": "创建网站 URL 列表",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        -340,
        -300
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "urlset.url"
      },
      "typeVersion": 1
    },
    {
      "id": "61555239-8a16-424e-8a60-700f6ebaa270",
      "name": "按主题或页面筛选",
      "type": "n8n-nodes-base.filter",
      "position": [
        -120,
        -300
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "or",
          "conditions": [
            {
              "id": "d66c304d-879a-4dc4-908f-ab0665093672",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "={{ $json.loc }}",
              "rightValue": "=https://ai.pydantic.dev/"
            },
            {
              "id": "3c930950-bee4-442b-82e6-4437fd39a933",
              "operator": {
                "type": "string",
                "operation": "contains"
              },
              "leftValue": "={{ $json.loc.toLowerCase() }}",
              "rightValue": "agent"
            },
            {
              "id": "aaeaf34e-ad5a-4673-b3bd-8bddf3500988",
              "operator": {
                "type": "string",
                "operation": "contains"
              },
              "leftValue": "={{ $json.loc.toLowerCase() }}",
              "rightValue": "tool"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "dd25fb57-64a3-4c47-be04-6eb66d16520a",
      "name": "设置网站 URL",
      "type": "n8n-nodes-base.set",
      "position": [
        -1080,
        -300
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "1601dc3e-8024-4e19-b592-93a4e4f77641",
              "name": "sitemap_url",
              "type": "string",
              "value": "https://ai.pydantic.dev/sitemap.xml"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "14ac1c87-29fe-44c8-9c1e-f247a292dde5",
      "name": "Jina.ai 网络爬虫",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        -720,
        120
      ],
      "parameters": {
        "url": "=https://r.jina.ai/{{ $json.loc }}",
        "options": {}
      },
      "typeVersion": 4.2
    },
    {
      "id": "be253ec2-f088-4895-8ef2-61a3720cf68b",
      "name": "将网页内容保存到 Google Drive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        -120,
        120
      ],
      "parameters": {
        "name": "={{ $('Loop Over Items').item.json.loc }} - {{ $json.title }}",
        "content": "={{ $json.markdown }}",
        "driveId": {
          "__rl": true,
          "mode": "list",
          "value": "My Drive"
        },
        "options": {},
        "folderId": {
          "__rl": true,
          "mode": "list",
          "value": "root",
          "cachedResultName": "/ (Root folder)"
        },
        "operation": "createFromText"
      },
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "UhdXGYLTAJbsa0xX",
          "name": "Google Drive account"
        }
      },
      "typeVersion": 3
    },
    {
      "id": "95d808c7-a3ca-4f59-a385-cc77bdff322e",
      "name": "提取标题和 Markdown 内容",
      "type": "n8n-nodes-base.code",
      "position": [
        -380,
        120
      ],
      "parameters": {
        "jsCode": "// Get the text output from the previous node\nconst data = $input.first().json.data;\n\n// Regular expression to capture the title line\nconst titleRegex = /^Title:\\s*(.+)$/m;\n// Regular expression to capture everything after \"Markdown Content:\"\nconst markdownRegex = /Markdown Content:\\n([\\s\\S]+)/;\n\n// Extract the title using the first capture group\nconst titleMatch = data.match(titleRegex);\nconst title = titleMatch ? titleMatch[1].trim() : '';\n\n// Extract the markdown content using the first capture group\nconst markdownMatch = data.match(markdownRegex);\nconst markdown = markdownMatch ? markdownMatch[1].trim() : '';\n\n// Return a single object with title and markdown as unique values\nreturn { title, markdown };"
      },
      "typeVersion": 2
    },
    {
      "id": "2fb86c81-c144-4450-908c-559855deadef",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1240,
        -580
      ],
      "parameters": {
        "color": 7,
        "width": 1540,
        "height": 1080,
        "content": "# 💡🌐 基于 Jina.ai 的必备多页面网站爬虫"
      },
      "typeVersion": 1
    },
    {
      "id": "b470b294-95d0-4e51-a9cc-2fe17316a771",
      "name": "便签2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1580,
        -400
      ],
      "parameters": {
        "color": 4,
        "width": 280,
        "height": 300,
        "content": "## 👍试试我！"
      },
      "typeVersion": 1
    },
    {
      "id": "fafd0623-a423-4e73-9609-cee8e81f5c13",
      "name": "便签3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1180,
        -400
      ],
      "parameters": {
        "width": 300,
        "height": 300,
        "content": "## 👇添加网站站点地图 URL"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "2e815787-d83b-4ab7-a959-2f33006a37a5",
  "connections": {
    "Wait": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Limit": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to JSON": {
      "main": [
        [
          {
            "node": "Create List of Website URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Jina.ai Web Scraper",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set Website URL": {
      "main": [
        [
          {
            "node": "Get List of Website URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Jina.ai Web Scraper": {
      "main": [
        [
          {
            "node": "Extract Title & Markdown Content",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get List of Website URLs": {
      "main": [
        [
          {
            "node": "Convert to JSON",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Filter By Topics or Pages": {
      "main": [
        [
          {
            "node": "Limit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create List of Website URLs": {
      "main": [
        [
          {
            "node": "Filter By Topics or Pages",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Title & Markdown Content": {
      "main": [
        [
          {
            "node": "Save Webpage Contents to Google Drive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Set Website URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Save Webpage Contents to Google Drive": {
      "main": [
        [
          {
            "node": "Wait",
            "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？

高级 - 人工智能

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

（Duc）深度研究市场模板
集成PerplexityAI研究和OpenAI内容的多层级WordPress博客生成器
If
Set
Xml
+28
132 节点Daniel Ng
人工智能
WordPress博客自动化专业版（SEO主题）v2
WordPress自动博客专业版 - SEO主题内容自动化机器
If
Set
Xml
+21
63 节点Daniel Ng
人工智能
WordPress博客自动化专业版（深度研究）v1
WordPress自动博客专业版 - 含深度研究的内容自动化机器
If
Set
Xml
+24
77 节点Daniel Ng
人工智能
API架构提取器
API架构提取器
If
Set
Code
+22
88 节点Polina Medvedieva
工程
[模板] AI宠物店 v8
🐶 AI宠物店助手 - 集成GPT-4o、Google日历和WhatsApp/Instagram/Facebook
If
N8n
Set
+38
244 节点Amanda Benks
销售
AI 代理餐厅 [模板]
🤖 WhatsApp、Instagram 和 Messenger 的 AI 餐厅助手
If
N8n
Set
+37
239 节点Amanda Benks
其他
工作流信息
难度等级
高级
节点数量16
分类1
节点类型12
难度说明

适合高级用户，包含 16+ 个节点的复杂工作流

作者
Joseph LePage

Joseph LePage

@joe

As an AI Automation consultant based in Canada, I partner with forward-thinking organizations to implement AI solutions that streamline operations and drive growth.

外部链接
在 n8n.io 查看 →

分享此工作流