Bright Data：为 AI 视频与多模态数据采集打造企业级基础设施

{  "nodes": [    {      "parameters": {        "promptType": "define",        "text": "=你是一个YouTube数据分析助手。当用户请求搜索特定关键词相关的YouTube频道资料时\n\n请遵循以下流程：\n1.  识别用户查询中的关键词，例如“popular music”。\n2.  用用户查询中的关键词查询youtube中对应的其中一个视频的video_url；如https://www.youtube.com/watch?v=fuhE6PYnRMc，自己去网上搜索，不要用我举出的例子\n3.  获得结果\n4.  提取结果中视频链接如：https://www.youtube.com/watch?v=fuhE6PYnRMc\n\n当前用户请求：获取youtube中当前最热的流行游戏视频信息",        "options": {}      },      "type": "@n8n/n8n-nodes-langchain.agent",      "typeVersion": 2.2,      "position": [        -768,        400      ],      "id": "0c0b292a-25cb-4221-837a-e9f344919ed3",      "name": "AI Agent"    },    {      "parameters": {        "options": {}      },      "type": "@n8n/n8n-nodes-langchain.lmChatDeepSeek",      "typeVersion": 1,      "position": [        -816,        624      ],      "id": "48d23d70-e2c2-4731-892e-28f8c38c7adf",      "name": "DeepSeek Chat Model",      "credentials": {        "deepSeekApi": {          "id": "FIy2f0QvFHXX13et",          "name": "DeepSeek account"        }      }    },    {      "parameters": {        "method": "POST",        "url": "https://api.brightdata.com/datasets/v3/trigger",        "authentication": "predefinedCredentialType",        "nodeCredentialType": "httpBearerAuth",        "sendQuery": true,        "queryParameters": {          "parameters": [            {              "name": "dataset_id",              "value": "gd_lk56epmy2i5g7lzu0k"            },            {              "name": "include_errors",              "value": "true"            }          ]        },        "sendHeaders": true,        "headerParameters": {          "parameters": [            {              "name": "Content-Type",              "value": "application/json"            }          ]        },        "sendBody": true,        "specifyBody": "json",        "jsonBody": "=[\n\t{\"url\":\"{{ $json.extracted_url[0] }}\",\"country\":\"\",\"transcription_language\":\"\"}\n] ",        "options": {}      },      "id": "212291b1-4eb8-4692-9c4e-da37adbd8580",      "name": "Trigger Dataset Collection",      "type": "n8n-nodes-base.httpRequest",      "typeVersion": 4.2,      "position": [        -128,        400      ],      "credentials": {        "httpBearerAuth": {          "id": "Cj45MZf8S88fRooJ",          "name": "Bearer Auth account"        }      }    },    {      "parameters": {        "jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nfor (const item of $input.all()) {\n  item.json.myNewField = 1;\n}\n\nreturn $input.all();"      },      "id": "919de066-4a81-4557-9617-a6add19028a3",      "name": "Extract Snapshot ID",      "type": "n8n-nodes-base.code",      "typeVersion": 2,      "position": [        112,        400      ]    },    {      "parameters": {        "unit": "minutes"      },      "id": "664e1cf6-3ab2-4c51-9db9-ad1b1d39b945",      "name": "Wait for Processing",      "type": "n8n-nodes-base.wait",      "typeVersion": 1,      "position": [        320,        400      ],      "webhookId": "3c5f037d-542f-4c3f-8631-0b700c13fde2"    },    {      "parameters": {        "url": "=https://api.brightdata.com/datasets/v3/snapshot/{{ $json.snapshot_id }}",        "authentication": "predefinedCredentialType",        "nodeCredentialType": "httpBearerAuth",        "sendQuery": true,        "queryParameters": {          "parameters": [            {              "name": "format",              "value": "json"            }          ]        },        "sendHeaders": true,        "headerParameters": {          "parameters": [            {              "name": "Content-Type",              "value": "application/json"            }          ]        },        "options": {          "timeout": 30000        }      },      "id": "64454888-8b16-43a2-ac63-c09eb59c9819",      "name": "Get Snapshot Results",      "type": "n8n-nodes-base.httpRequest",      "typeVersion": 4.2,      "position": [        528,        400      ],      "credentials": {        "httpBearerAuth": {          "id": "Cj45MZf8S88fRooJ",          "name": "Bearer Auth account"        }      }    },    {      "parameters": {        "jsCode": "// 从上一节点获取输入的文本，这里假设是完整JSON中的第一个条目\nconst inputText = $input.first().json.output;\n\n// 使用正则表达式匹配URL\n// 这个正则表达式可以匹配常见的HTTP/HTTPS链接\nconst urlRegex  = /https?:\\/\\/[^\\s\\]\\)]+/g;\n\nconst urls = inputText.match(urlRegex);\n\n// 如果没有找到URL，返回提示信息\nif (!urls) {\n  return [{ json: { message: \"未在文本中找到URL\", original_text: inputText } }];\n}\n\n// 将提取到的所有URL（数组）作为输出\n// 如果文本中有多个URL，这里会全部返回；如果只需要第一个，可以用 urls[0]\nreturn [{ json: { extracted_url: urls } }];"      },      "type": "n8n-nodes-base.code",      "typeVersion": 2,      "position": [        -416,        400      ],      "id": "0e14cd33-5a6c-49e9-afbd-2d6101cc4a20",      "name": "Code in JavaScript"    },    {      "parameters": {        "endpointUrl": "https://mcp.brightdata.com/sse?token=",        "serverTransport": "sse",        "options": {}      },      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",      "typeVersion": 1.2,      "position": [        -608,        624      ],      "id": "0b63ad99-efb0-4456-98a8-084d74864bcc",      "name": "亮数据MCP"    },    {      "parameters": {        "rule": {          "interval": [            {}          ]        }      },      "type": "n8n-nodes-base.scheduleTrigger",      "typeVersion": 1.2,      "position": [        -1072,        416      ],      "id": "210d7995-e381-48a8-b1ea-18e58153774b",      "name": "Schedule Trigger"    },    {      "parameters": {        "operation": "write",        "fileName": "={{ $json.title }}.json",        "dataPropertyName": "={{ $json.video_url }}",        "options": {          "append": true        }      },      "type": "n8n-nodes-base.readWriteFile",      "typeVersion": 1,      "position": [        768,        400      ],      "id": "e2f3e0cd-b84d-4766-98fe-3a5df9a490d8",      "name": "Read/Write Files from Disk",      "executeOnce": true,      "alwaysOutputData": false    }  ],  "connections": {    "AI Agent": {      "main": [        [          {            "node": "Code in JavaScript",            "type": "main",            "index": 0          }        ]      ]    },    "DeepSeek Chat Model": {      "ai_languageModel": [        [          {            "node": "AI Agent",            "type": "ai_languageModel",            "index": 0          }        ]      ]    },    "Trigger Dataset Collection": {      "main": [        [          {            "node": "Extract Snapshot ID",            "type": "main",            "index": 0          }        ]      ]    },    "Extract Snapshot ID": {      "main": [        [          {            "node": "Wait for Processing",            "type": "main",            "index": 0          }        ]      ]    },    "Wait for Processing": {      "main": [        [          {            "node": "Get Snapshot Results",            "type": "main",            "index": 0          }        ]      ]    },    "Get Snapshot Results": {      "main": [        [          {            "node": "Read/Write Files from Disk",            "type": "main",            "index": 0          }        ]      ]    },    "Code in JavaScript": {      "main": [        [          {            "node": "Trigger Dataset Collection",            "type": "main",            "index": 0          }        ]      ]    },    "亮数据MCP": {      "ai_tool": [        [          {            "node": "AI Agent",            "type": "ai_tool",            "index": 0          }        ]      ]    },    "Schedule Trigger": {      "main": [        [          {            "node": "AI Agent",            "type": "main",            "index": 0          }        ]      ]    }  },  "pinData": {},  "meta": {    "templateCredsSetupCompleted": true,    "instanceId": "c327b70663d6181004e2fbb9e290d0271d26bc9c1fa4f18664baa3234e1536c4"  }}