8
n8n 中文网amn8n.com

使用 Bright Data 抓取和 Google Gemini 自动化 Etsy 数据挖掘

高级

这是一个Product, AI, Marketing领域的自动化工作流,包含 19 个节点。主要使用 Set, Function, SplitOut, HttpRequest, ManualTrigger 等节点,结合人工智能技术实现智能自动化。 使用 Bright Data 抓取和 Google Gemini 实现 Etsy 数据挖掘自动化

前置要求
  • 可能需要目标 API 的认证凭证
  • OpenAI API Key
  • Google Gemini API Key
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
{
  "id": "UuuCIDvTNnloIlvq",
  "meta": {
    "instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
    "templateCredsSetupCompleted": true
  },
  "name": "使用 Bright Data 抓取和 Google Gemini 自动化 Etsy 数据挖掘",
  "tags": [
    {
      "id": "Kujft2FOjmOVQAmJ",
      "name": "Engineering",
      "createdAt": "2025-04-09T01:31:00.558Z",
      "updatedAt": "2025-04-09T01:31:00.558Z"
    },
    {
      "id": "ddPkw7Hg5dZhQu2w",
      "name": "AI",
      "createdAt": "2025-04-13T05:38:08.053Z",
      "updatedAt": "2025-04-13T05:38:08.053Z"
    }
  ],
  "nodes": [
    {
      "id": "f369feaf-4782-4411-9d08-fe91b9ffd97e",
      "name": "当点击\"测试工作流\"时",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        200,
        -555
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "231bae3c-c27e-49fc-b878-2d5cc1e14c5a",
      "name": "便签",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        200,
        -1020
      ],
      "parameters": {
        "width": 400,
        "height": 300,
        "content": "## 注意"
      },
      "typeVersion": 1
    },
    {
      "id": "f568de40-b389-41f9-afe9-5e09a291c367",
      "name": "便签1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        640,
        -1020
      ],
      "parameters": {
        "width": 480,
        "height": 300,
        "content": "## LLM 使用情况"
      },
      "typeVersion": 1
    },
    {
      "id": "4f1db865-a0cb-4978-9c7d-fde448bd978a",
      "name": "设置 Etsy 搜索查询",
      "type": "n8n-nodes-base.set",
      "position": [
        420,
        -555
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "3aedba66-f447-4d7a-93c0-8158c5e795f9",
              "name": "url",
              "type": "string",
              "value": "https://www.etsy.com/search?q=wall+art+for+mum&order=date_desc&page=1&ref=pagination"
            },
            {
              "id": "4e7ee31d-da89-422f-8079-2ff2d357a0ba",
              "name": "zone",
              "type": "string",
              "value": "web_unlocker1"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "4cb51368-bb69-4d99-a0b6-e8e8013f1dfd",
      "name": "执行 Etsy 网络请求",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        640,
        -680
      ],
      "parameters": {
        "url": "https://api.brightdata.com/request",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "zone",
              "value": "={{ $json.zone }}"
            },
            {
              "name": "url",
              "value": "={{ $json.url }}?product=unlocker&method=api"
            },
            {
              "name": "format",
              "value": "raw"
            },
            {
              "name": "data_format",
              "value": "markdown"
            }
          ]
        },
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "kdbqXuxIR8qIxF7y",
          "name": "Header Auth account"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "9fb7bdc5-ba64-4df4-89b4-a3207e7f6d0e",
      "name": "Google Gemini 聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        948,
        -460
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash-exp"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "YeO7dHZnuGBVQKVZ",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "1f95576d-e243-481d-9d5f-308764d8ea4b",
      "name": "遍历项目",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        1460,
        -680
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "47f23aa1-63ee-49e3-a465-283c7ab71b76",
      "name": "在循环上执行 Etsy 网络请求",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1680,
        -560
      ],
      "parameters": {
        "url": "https://api.brightdata.com/request",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "zone",
              "value": "=web_unlocker1"
            },
            {
              "name": "url",
              "value": "={{ $json.url }}&product=unlocker"
            },
            {
              "name": "format",
              "value": "raw"
            },
            {
              "name": "data_format",
              "value": "markdown"
            }
          ]
        },
        "genericAuthType": "httpHeaderAuth",
        "headerParameters": {
          "parameters": [
            {}
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "kdbqXuxIR8qIxF7y",
          "name": "Header Auth account"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "0b5ea206-a5a0-49b5-8f53-10b4dec5806c",
      "name": "为提取的数据发起 Webhook 通知",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        2320,
        -560
      ],
      "parameters": {
        "url": "https://webhook.site/3c36d7d1-de1b-4171-9fd3-643ea2e4dd76",
        "options": {},
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "summary",
              "value": "={{ $json.output }}"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "a164b90b-f44c-4862-b010-d515926774c7",
      "name": "提取包含产品信息的商品列表",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        1920,
        -560
      ],
      "parameters": {
        "text": "=Extract the product info in JSON\n\n{{ $json.data }}",
        "options": {},
        "schemaType": "fromJson",
        "jsonSchemaExample": "[{\n    \"image\": \"https://i.etsystatic.com/34923795/r/il/8f3bba/5855230678/il_fullxfull.5855230678_n9el.jpg\",\n    \"name\": \"Custom Coffee Mug with Photo\",\n    \"url\": \"https://www.etsy.com/listing/1193808036/custom-coffee-mug-with-photo\",\n    \"brand\": {\n        \"@type\": \"Brand\",\n        \"name\": \"TheGiftBucks\"\n    },\n    \"offers\": {\n        \"@type\": \"Offer\",\n        \"price\": \"14.99\",\n        \"priceCurrency\": \"USD\"\n    }\n}]"
      },
      "typeVersion": 1
    },
    {
      "id": "c3798c64-ac53-44c8-ba91-8fe33377113d",
      "name": "用于产品信息的 Google Gemini 聊天模型",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        2000,
        -300
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash-exp"
      },
      "credentials": {
        "googlePalmApi": {
          "id": "YeO7dHZnuGBVQKVZ",
          "name": "Google Gemini(PaLM) Api account"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "11e4ae42-d2e1-4a4b-adcf-382f9e494431",
      "name": "提取分页结果集",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        860,
        -680
      ],
      "parameters": {
        "text": "=Analyze and Extract the below content. Make sure to produce a unique resultset. Exclude page_numbers which are not numbers.\n\n {{ $json.data }}",
        "options": {},
        "schemaType": "manual",
        "inputSchema": "{\n  \"$schema\": \"http://json-schema.org/schema#\",\n  \"title\": \"PagedResultSetSchema\",\n  \"type\": \"array\",\n  \"items\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"page_number\": {\n        \"type\": \"string\",\n        \"description\": \"Page number, typically a string (e.g., '1', '2', 'next').\"\n      },\n      \"url\": {\n        \"type\": \"string\",\n        \"format\": \"uri\",\n        \"description\": \"URL pointing to the page.\"\n      }\n    },\n    \"required\": [\"page_number\", \"url\"],\n    \"additionalProperties\": false\n  }\n}\n"
      },
      "typeVersion": 1
    },
    {
      "id": "28c1822b-d51c-4f8e-b98e-2e12324397be",
      "name": "便签 2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1400,
        -780
      ],
      "parameters": {
        "color": 5,
        "width": 1340,
        "height": 620,
        "content": "## 循环并执行分页 Etsy 数据提取"
      },
      "typeVersion": 1
    },
    {
      "id": "d4f18f2b-9825-4320-addb-c02bfdc4da97",
      "name": "将抓取的内容写入磁盘",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        2560,
        -760
      ],
      "parameters": {
        "options": {},
        "fileName": "=d:\\Esty-Scraped-Content-{{ $('Loop Over Items').item.json.page_number }}.json",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "5555407d-c7dd-4e5c-83ab-ef6ba9c46da3",
      "name": "创建二进制数据",
      "type": "n8n-nodes-base.function",
      "position": [
        2360,
        -760
      ],
      "parameters": {
        "functionCode": "items[0].binary = {\n  data: {\n    data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n  }\n};\nreturn items;"
      },
      "typeVersion": 1
    },
    {
      "id": "2f7a5fab-a2f4-422e-8f83-ce50fbe2a738",
      "name": "拆分输出",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        1240,
        -680
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "output"
      },
      "typeVersion": 1
    },
    {
      "id": "3d7a8992-b8d4-4a86-b60b-a92a7d63e31b",
      "name": "使用 OpenAI 提取分页结果集",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        880,
        -120
      ],
      "parameters": {
        "text": "=Analyze and Extract the below content. Make sure to produce a unique resultset. Exclude page_numbers which are not numbers.\n\n {{ $json.data }}",
        "options": {},
        "schemaType": "manual",
        "inputSchema": "{\n  \"$schema\": \"http://json-schema.org/schema#\",\n  \"title\": \"PagedResultSetSchema\",\n  \"type\": \"array\",\n  \"items\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"page_number\": {\n        \"type\": \"string\",\n        \"description\": \"Page number, typically a string (e.g., '1', '2', 'next').\"\n      },\n      \"url\": {\n        \"type\": \"string\",\n        \"format\": \"uri\",\n        \"description\": \"URL pointing to the page.\"\n      }\n    },\n    \"required\": [\"page_number\", \"url\"],\n    \"additionalProperties\": false\n  }\n}\n"
      },
      "typeVersion": 1
    },
    {
      "id": "aa42d335-67bc-4dc5-a68a-4ce93e05464a",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        880,
        80
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "vPKynKbDzJ5ZU4cU",
          "name": "OpenAi account"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "82df0ccc-3065-4bb5-a48e-90e4dbf2162f",
      "name": "便签 3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        640,
        -260
      ],
      "parameters": {
        "color": 6,
        "width": 660,
        "height": 460,
        "content": "## Open AI 提取(可选)"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "40a1bbd5-05b2-41c2-8b3c-72e3f16fd13a",
  "connections": {
    "Split Out": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Over Items": {
      "main": [
        [],
        [
          {
            "node": "Perform Esty web request over the loop",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Extract Paginated Resultset With OpenAI",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Create a binary data": {
      "main": [
        [
          {
            "node": "Write the scraped content to disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set Esty Search Query": {
      "main": [
        [
          {
            "node": "Perform Esty Web Request",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Extract Paginated Resultset",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Perform Esty Web Request": {
      "main": [
        [
          {
            "node": "Extract Paginated Resultset",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Paginated Resultset": {
      "main": [
        [
          {
            "node": "Split Out",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Set Esty Search Query",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Perform Esty web request over the loop": {
      "main": [
        [
          {
            "node": "Extract Item List with the Product Info",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Item List with the Product Info": {
      "main": [
        [
          {
            "node": "Initiate a Webhook Notification for the extracted data",
            "type": "main",
            "index": 0
          },
          {
            "node": "Create a binary data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model for product info": {
      "ai_languageModel": [
        [
          {
            "node": "Extract Item List with the Product Info",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Initiate a Webhook Notification for the extracted data": {
      "main": [
        [
          {
            "node": "Loop Over Items",
            "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 - 产品, 人工智能, 营销

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
高级
节点数量19
分类3
节点类型11
难度说明

适合高级用户,包含 16+ 个节点的复杂工作流

外部链接
在 n8n.io 查看

分享此工作流