中文网

网站地图页面提取器

高级

这是一个Market Research、Multimodal AI领域的自动化工作流，包含 19 个节点。主要使用 If、Set、Code、Filter、FormTrigger 等节点。 网站地图页面提取器：发现、清理并将网站 URL 保存至 Google Sheets

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

使用的节点 (19 个)

If
Set
Code
Filter
StickyNote
FormTrigger
HttpRequest
GoogleSheets
SplitInBatches

分类

Market Research
Multimodal 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
{
  "id": "ytgCDUiHYhFkJqlY",
  "meta": {
    "instanceId": "bc8ca75c203589705ae2e446cad7181d6f2a7cc1766f958ef9f34810e53b8cb2",
    "templateCredsSetupCompleted": true
  },
  "name": "网站地图页面提取器",
  "tags": [],
  "nodes": [
    {
      "id": "2464b9f1-f0fe-41df-9941-acad5d5dedb9",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -256,
        928
      ],
      "parameters": {
        "color": 2,
        "height": 336,
        "content": "## 构建网站地图 URL："
      },
      "typeVersion": 1
    },
    {
      "id": "1b1b00a9-6825-4bae-b74a-6c86d8972299",
      "name": "便签 1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        304,
        560
      ],
      "parameters": {
        "color": 2,
        "width": 400,
        "height": 432,
        "content": "## 筛选和提取网站地图文件"
      },
      "typeVersion": 1
    },
    {
      "id": "e0c1c670-5e7f-4146-a605-e5972d786cf8",
      "name": "便签 2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        720,
        560
      ],
      "parameters": {
        "color": 2,
        "width": 432,
        "height": 432,
        "content": "## 获取网站地图 XML 并提取页面 URL"
      },
      "typeVersion": 1
    },
    {
      "id": "c95c2d0b-2a6b-471a-b168-1f33d4dd6cb4",
      "name": "便签 3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1488,
        688
      ],
      "parameters": {
        "color": 2,
        "width": 208,
        "height": 304,
        "content": "将每个爬取的页面 URL 附加到 List_Of_All_URLs 工作表中，通过自动匹配现有条目避免重复。"
      },
      "typeVersion": 1
    },
    {
      "id": "1b2c2bde-4edc-4dee-97c1-28f1b1ee8b94",
      "name": "便签 5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        288,
        1152
      ],
      "parameters": {
        "color": 2,
        "width": 256,
        "height": 304,
        "content": "向每个生成的网站地图 URL 发送 HTTP 请求并获取原始响应，以检查网站地图是否存在且包含有效数据。"
      },
      "typeVersion": 1
    },
    {
      "id": "c9f75b84-334a-4926-bdc4-62e59e605b97",
      "name": "便签6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1184,
        640
      ],
      "parameters": {
        "color": 2,
        "width": 272,
        "height": 352,
        "content": "## 排除网站地图 URL："
      },
      "typeVersion": 1
    },
    {
      "id": "5ae6ec48-76f1-44ca-8387-ce5f9a84ac9d",
      "name": "便签7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1248,
        784
      ],
      "parameters": {
        "width": 464,
        "height": 640,
        "content": "## 📌 自动化摘要："
      },
      "typeVersion": 1
    },
    {
      "id": "342fb312-ba7a-427e-907e-b57a206b6252",
      "name": "便签 4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -672,
        928
      ],
      "parameters": {
        "color": 2,
        "width": 400,
        "height": 336,
        "content": "## 表单输入与 URL 准备"
      },
      "typeVersion": 1
    },
    {
      "id": "e69d955f-2212-4e5b-afa8-998cd18e11f1",
      "name": "输入网站 URL",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        -640,
        1088
      ],
      "webhookId": "8a207eb4-74f2-4577-9fe6-98e87f2e9a0d",
      "parameters": {
        "options": {},
        "formTitle": "Sitemap Page Extractor",
        "formFields": {
          "values": [
            {
              "fieldLabel": "Website URL"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "4d33e736-fb1d-462f-bad2-46a68bc1b837",
      "name": "准备网站 URL",
      "type": "n8n-nodes-base.set",
      "position": [
        -432,
        1088
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "2a310b45-ec77-41dd-9436-f3b58b7df477",
              "name": "url",
              "type": "string",
              "value": "={{ $json[\"Website URL\"] }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "604a9837-436b-4701-9d17-cb59cb2a2099",
      "name": "构建网站地图 URL",
      "type": "n8n-nodes-base.code",
      "position": [
        -192,
        1088
      ],
      "parameters": {
        "jsCode": "const inputData = $input.first().json;\nlet baseUrl = inputData.url || inputData.website_url || '';\n\nif (!baseUrl) {\n  throw new Error(\"No URL provided\");\n}\n\nbaseUrl = baseUrl.replace(/\\/$/, '');\n\nlet domain = '';\nif (baseUrl.includes('://')) {\n  const parts = baseUrl.split('/');\n  domain = parts[0] + '//' + parts[2];\n} else {\n  domain = 'https://' + baseUrl;\n}\n\nconst urls = [\n  `${domain}/robots.txt`,\n  `${domain}/sitemap.xml`,\n  `${domain}/sitemap_index.xml`,\n  `${domain}/sitemap-index.xml`,\n  `${domain}/sitemap1.xml`,\n  `${domain}/sitemap/sitemap.xml`,\n  `${domain}/sitemaps/sitemap.xml`\n];\n\nreturn urls.map(url => ({ sitemap_url: url }));"
      },
      "typeVersion": 2
    },
    {
      "id": "ad781031-ef3e-4378-92d0-837d3e8fbaf2",
      "name": "网站地图 URL 检查",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        80,
        1088
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "8ca63a55-44bc-4e72-906b-a6e2ed5f9c31",
      "name": "获取网站地图数据",
      "type": "n8n-nodes-base.httpRequest",
      "onError": "continueRegularOutput",
      "position": [
        368,
        1280
      ],
      "parameters": {
        "url": "={{ $json.sitemap_url }}",
        "options": {
          "response": {
            "response": {
              "responseFormat": "text"
            }
          }
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "02698f76-9606-426d-b953-3f2adfd80a6f",
      "name": "筛选非空网站地图响应",
      "type": "n8n-nodes-base.if",
      "position": [
        336,
        832
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "bf0c94e8-a8c6-4419-9b18-cf5d1a01e577",
              "operator": {
                "type": "string",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.data }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "2554e396-8d0b-44c5-ab1e-91a192751acd",
      "name": "提取网站地图 URL",
      "type": "n8n-nodes-base.code",
      "position": [
        560,
        816
      ],
      "parameters": {
        "jsCode": "const allUrls = [];\n\n$input.all().forEach(item => {\n  const content = item.json.data || '';\n\n  const robotMatches = [...content.matchAll(/Sitemap:\\s*(\\S+)/gi)];\n  robotMatches.forEach(match => {\n    allUrls.push(match[1]);\n  });\n\n  const locMatches = [...content.matchAll(/<loc>\\s*(.*?)\\s*<\\/loc>/gi)];\n  locMatches.forEach(match => {\n    allUrls.push(match[1]);\n  });\n});\n\nconst uniqueUrls = [...new Set(allUrls)];\n\nreturn uniqueUrls.map(url => ({ json: { sitemap_url: url }}));"
      },
      "typeVersion": 2
    },
    {
      "id": "95f24edc-bef3-481d-954c-f4245af73faa",
      "name": "获取网站地图页面 XML",
      "type": "n8n-nodes-base.httpRequest",
      "onError": "continueRegularOutput",
      "position": [
        784,
        816
      ],
      "parameters": {
        "url": "={{ $json.sitemap_url }}",
        "method": "=GET",
        "options": {
          "response": {
            "response": {
              "responseFormat": "text"
            }
          }
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "134f2ded-0200-44a7-8df1-343d76cf16d0",
      "name": "从网站地图提取页面 URL",
      "type": "n8n-nodes-base.code",
      "position": [
        1008,
        816
      ],
      "parameters": {
        "jsCode": "const urls = new Set();\n\n$input.all().forEach(item => {\n  const content = item.json.data || '';\n\n  const xmlMatches = [...content.matchAll(/<loc>(.*?)<\\/loc>/gi)];\n  xmlMatches.forEach(match => {\n    const url = match[1].trim();\n    urls.add(url);\n  });\n\n  const htmlMatches = [...content.matchAll(/<a\\s[^>]*href=[\"']([^\"']+)[\"']/gi)];\n  htmlMatches.forEach(match => {\n    const url = match[1].trim();\n    if (url.startsWith('/') || url.startsWith('http')) {\n      urls.add(url);\n    }\n  });\n});\n\nif (urls.size === 0) {\n  return [{ json: { message: \"No URLs found in XML or HTML content\" }}];\n}\n\nreturn Array.from(urls).map(url => ({\n  json: { page_url: url }\n}));"
      },
      "typeVersion": 2
    },
    {
      "id": "9708b71a-34c3-42fd-9a3c-15ad7d4cd7c3",
      "name": "排除网站地图 URL",
      "type": "n8n-nodes-base.filter",
      "position": [
        1296,
        816
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "303d0665-ac2d-452b-8678-a05e53a7372b",
              "operator": {
                "type": "string",
                "operation": "notContains"
              },
              "leftValue": "={{ $json.page_url }}",
              "rightValue": "sitemap"
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "535579fc-dcad-4386-920c-6f8857a0bd70",
      "name": "将页面 URL 保存到工作表",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        1568,
        816
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [],
          "mappingMode": "defineBelow",
          "matchingColumns": [
            "List URLs"
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "appendOrUpdate",
        "sheetName": "List_Of_All_URLs",
        "documentId": "YOUR_GOOGLE_SHEET_URL"
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "Aam5AW9oxNhvIGd2",
          "name": "Shiv@incrementors.com - Google Sheets"
        }
      },
      "typeVersion": 4.6
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "callerPolicy": "any",
    "executionOrder": "v1"
  },
  "versionId": "ff2c3009-f913-4cd2-9042-a36d056b6f90",
  "connections": {
    "Input Website URL": {
      "main": [
        [
          {
            "node": "Prepare website URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Sitemap URL Check": {
      "main": [
        [
          {
            "node": "Filter Non-Empty Sitemap Responses",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Fetch Sitemap Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Build sitemap URLs": {
      "main": [
        [
          {
            "node": "Sitemap URL Check",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Sitemap Data": {
      "main": [
        [
          {
            "node": "Sitemap URL Check",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Prepare website URL": {
      "main": [
        [
          {
            "node": "Build sitemap URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Sitemap URLs": {
      "main": [
        [
          {
            "node": "Fetch Sitemap Pages XML",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Sitemap Pages XML": {
      "main": [
        [
          {
            "node": "Extract Page URLs from Sitemap",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Exclude the Sitemap URLs": {
      "main": [
        [
          {
            "node": "Save Page URLs to Sheet",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Page URLs from Sitemap": {
      "main": [
        [
          {
            "node": "Exclude the Sitemap URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Filter Non-Empty Sitemap Responses": {
      "main": [
        [
          {
            "node": "Extract Sitemap URLs",
            "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？

这是一个高级难度的工作流，适用于Market Research、Multimodal AI等场景。适合高级用户，包含 16+ 个节点的复杂工作流

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

多平台价格查找器：使用 Bright Data 和 Telegram 抓取价格
多平台价格查找器：使用 Bright Data、Claude AI 和 Telegram 抓取价格
If
Code
Wait
+9
85 节点Incrementors
Market Research
博客发布器 – 完整的AI驱动内容研究、创作、优化与发布自动化
使用 Gemini、Ideogram AI 和 WordPress 自动化博客创建与发布
If
Set
Code
+9
35 节点Incrementors
Content Creation
基于AI的潜在客户生成（Apollo、LinkedIn研究和4步个性化邮件）
基于AI的潜在客户生成：使用Apollo、LinkedIn研究和4步个性化邮件
If
Set
Code
+8
30 节点Gain FLow AI
Lead Generation
WordPress博客自动化专业版（深度研究）v2.1市场
使用GPT-4o、Perplexity AI和多语言支持自动化SEO优化的博客创建
If
Set
Xml
+27
125 节点Daniel Ng
Content Creation
MetaAds创意洞察研究员v1.4
使用Google Vision和Video Intelligence API分析Meta广告创意
If
Set
Code
+9
32 节点Kirill Khatkevich
Market Research
使用GPT-5 nano和Google Sheets抓取网站并回答问题
使用GPT-5 nano和Google Sheets抓取网站并回答问题
If
Set
Xml
+17
44 节点Oriol Seguí
Market Research
工作流信息
难度等级
高级
节点数量19
分类2
节点类型9
难度说明

适合高级用户，包含 16+ 个节点的复杂工作流

作者
Incrementors

Incrementors

@incrementors
外部链接
在 n8n.io 上查看 →

分享此工作流