8
n8n 中文网amn8n.com

使用Scrape.do提取Zillow房产数据到Google Sheets

中级

这是一个Content Creation, Multimodal AI领域的自动化工作流,包含 6 个节点。主要使用 If, Code, HttpRequest, GoogleSheets, ManualTrigger 等节点。 使用Scrape.do提取Zillow房产数据到Google Sheets

前置要求
  • 可能需要目标 API 的认证凭证
  • Google Sheets API 凭证
工作流预览
可视化展示节点连接关系,支持缩放和平移
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": "02e782574ebb30fbddb2c3fd832c946466d718819d25f6fe4b920124ff3fc2c1",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "1562d037-9fa3-488f-a5e5-5aceaba3d3a1",
      "name": "当点击\"测试工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -160,
        -160
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "873e06bf-4862-4d40-9b77-f08f1cf889c3",
      "name": "从 Google Sheets 读取 Zillow URL",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        64,
        -160
      ],
      "parameters": {
        "options": {
          "returnFirstMatch": false
        },
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": "gid=0",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU/edit#gid=0",
          "cachedResultName": "URLs"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU/edit?usp=drivesdk",
          "cachedResultName": "outcome"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "mXr7C0bnwDQsB9Pd",
          "name": "VisaTrack Sheets"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "9dc0d92a-e56f-4b83-9dc5-986507a17eaf",
      "name": "通过 Scrape.do 抓取 Zillow URL",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        288,
        -160
      ],
      "parameters": {
        "url": "={{ \"https://api.scrape.do/?url=\" + encodeURIComponent($json.URLs) + \"&super=true\" }}",
        "options": {
          "timeout": 120000,
          "redirect": {
            "redirect": {
              "followRedirects": false
            }
          }
        },
        "authentication": "genericCredentialType",
        "genericAuthType": "httpQueryAuth"
      },
      "credentials": {
        "httpQueryAuth": {
          "id": "HvTIKFnwg8rzo3iP",
          "name": "Query Auth account 2"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "a7cabb4d-1b33-46c4-a9e0-e70fe70e2ec2",
      "name": "解析 Zillow 数据",
      "type": "n8n-nodes-base.code",
      "position": [
        512,
        -160
      ],
      "parameters": {
        "jsCode": "// Parse HTML and extract Zillow property data\nconst item = $input.first();\n\n// Get HTML from Scrape.do response\nconst html = item.json.data || item.json.body || item.json;\n\n// Skip if no HTML content\nif (!html || typeof html !== 'string') {\n  return [];\n}\n\n// Get the original URL\nconst originalUrl = $('Read Zillow URLs from Google Sheets').first().json.URLs || 'N/A';\n\n// Extract Price - improved regex\nlet price = 'N/A';\n// Try multiple patterns\nconst pricePattern1 = html.match(/data-testid=\"price\"[^>]*>\\s*\\$?([0-9,]+)\\s*</)\nconst pricePattern2 = html.match(/\"price\"[^}]*\"value\"\\s*:\\s*\"?\\$?([0-9,]+)\"?/)\nconst pricePattern3 = html.match(/\\$([0-9]{3},[0-9]{3}(?:,[0-9]{3})?)(?!\\d)/)\n\nif (pricePattern1) {\n  price = '$' + pricePattern1[1].trim();\n} else if (pricePattern2) {\n  price = '$' + pricePattern2[1].trim();\n} else if (pricePattern3) {\n  price = pricePattern3[0].trim();\n}\n\n// Extract Address, City, and State\nlet street = 'N/A';\nlet city = 'N/A';\nlet state = 'N/A';\n\nconst addressMatch = html.match(/(\\d+\\s+[^,]+),\\s*([^,]+),\\s*(\\w{2})\\s+\\d{5}/);\nif (addressMatch) {\n  street = addressMatch[1].trim();\n  city = addressMatch[2].trim();\n  state = addressMatch[3].trim();\n}\n\n// Extract Days on Zillow\nlet daysOnZillow = 'N/A';\nconst daysMatch = html.match(/(\\d+)\\s+days?\\s*on\\s+Zillow/i);\nif (daysMatch) {\n  daysOnZillow = daysMatch[1];\n}\n\n// Extract Zestimate\nlet zestimate = 'N/A';\nconst zestimateMatch = html.match(/\\$[\\d,]+(?=\\s*Zestimate)/);\nif (zestimateMatch) {\n  zestimate = zestimateMatch[0];\n}\n\n// Return ONLY structured data\nreturn [{\n  json: {\n    URL: originalUrl,\n    Price: price,\n    Address: street,\n    City: city,\n    State: state,\n    'Days on Zillow': daysOnZillow,\n    Zestimate: zestimate,\n    'Scraped At': new Date().toISOString()\n  }\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "436fbea1-b770-4ef3-8995-c79c6adf46a1",
      "name": "将结果写入 Google Sheets",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        720,
        -160
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "data",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "data",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": 2048497939,
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU/edit#gid=2048497939",
          "cachedResultName": "Outcome"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1D2cU-NoW4ubx_IQ6piRRO3_d0Fx7jzdpWxKkBqEq7HU/edit?usp=drivesdk",
          "cachedResultName": "outcome"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "mXr7C0bnwDQsB9Pd",
          "name": "VisaTrack Sheets"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "00a73a1f-faf5-421e-abc4-a75b2b132c4a",
      "name": "检查抓取是否成功",
      "type": "n8n-nodes-base.if",
      "position": [
        288,
        32
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "string": [
            {
              "value1": "={{ $json.statusCode }}",
              "value2": "200",
              "operation": "equals"
            }
          ]
        }
      },
      "typeVersion": 2
    }
  ],
  "pinData": {},
  "connections": {
    "Parse Zillow Data": {
      "main": [
        [
          {
            "node": "Write Results to Google Sheets",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check if Scraping Succeeded": {
      "main": [
        [
          {
            "node": "Parse Zillow Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking 'Test workflow'": {
      "main": [
        [
          {
            "node": "Read Zillow URLs from Google Sheets",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Scrape Zillow URL via Scrape.do": {
      "main": [
        [
          {
            "node": "Check if Scraping Succeeded",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read Zillow URLs from Google Sheets": {
      "main": [
        [
          {
            "node": "Scrape Zillow URL via Scrape.do",
            "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 - 内容创作, 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。

工作流信息
难度等级
中级
节点数量6
分类2
节点类型5
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

Hello, I'm Onur I've been working as a freelance software developer for about four years. In addition, I develop my own projects. For some time, I have been improving myself and providing various services related to AI and AI workflows. Both by writing low code and code. If you have any questions, don't hesitate to contact me.

外部链接
在 n8n.io 查看

分享此工作流