Bright Data MCPとGoogle Geminiを使用した法の事例研究抽出ツール、データマイニングツール
上級
これはAI, IT Ops分野の自動化ワークフローで、22個のノードを含みます。主にSet, Code, Wait, Function, McpClientなどのノードを使用、AI技術を活用したスマート自動化を実現。 Bright Data MCPとGoogle Geminiを使用した法のケーススタディ抽出データマイニングツール
前提条件
- •ターゲットAPIの認証情報が必要な場合あり
- •Google Gemini API Key
使用ノード (22)
ワークフロープレビュー
ノード接続関係を可視化、ズームとパンをサポート
ワークフローをエクスポート
以下のJSON設定をn8nにインポートして、このワークフローを使用できます
{
"id": "Qgx75aQeRKXKtqm7",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "Legal Case Research Extractor, Data Miner with Bright Data MCP & Google Gemini",
"tags": [
{
"id": "ZOwtAMLepQaGW76t",
"name": "Building Blocks",
"createdAt": "2025-04-13T15:23:40.462Z",
"updatedAt": "2025-04-13T15:23:40.462Z"
},
{
"id": "ddPkw7Hg5dZhQu2w",
"name": "AI",
"createdAt": "2025-04-13T05:38:08.053Z",
"updatedAt": "2025-04-13T05:38:08.053Z"
}
],
"nodes": [
{
"id": "9e9a27ce-b95c-4ecd-b3c4-97aba420ce45",
"name": "ワークフロー「テスト」クリック時",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-520,
140
],
"parameters": {},
"typeVersion": 1
},
{
"id": "3f9e30b5-7eb3-454d-a831-07be51f7a326",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
-60,
40
],
"parameters": {
"color": 4,
"width": 440,
"height": 320,
"content": "## Bright Data Legal Case Research Scraper"
},
"typeVersion": 1
},
{
"id": "8f1934bf-ccec-4b25-b6cc-7607dcbdf798",
"name": "Bright Data全ツール一覧表示",
"type": "n8n-nodes-mcp.mcpClient",
"position": [
-300,
140
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "f8c4804a-85ad-462c-913d-e0bc5242bc74",
"name": "LinkedIn企業情報抽出用バイナリデータ作成",
"type": "n8n-nodes-base.function",
"position": [
2440,
60
],
"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": "c616db9f-fcf3-4f9d-b60f-a16c9da89456",
"name": "付箋2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1220,
-180
],
"parameters": {
"width": 440,
"height": 120,
"content": "## Disclaimer\nThis template is only available on n8n self-hosted as it's making use of the community node for MCP Client."
},
"typeVersion": 1
},
{
"id": "048c1093-ea88-441c-98fa-a2d003ab6b8d",
"name": "法律ケース研究URL設定",
"type": "n8n-nodes-base.set",
"position": [
-20,
140
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "214e61a0-3587-453f-baf5-eac013990857",
"name": "url",
"type": "string",
"value": "https://www.courtlistener.com/?q=IT%20laws%20for%20cyber%20crime&type=o&order_by=dateFiled%20desc&stat_Published=on"
},
{
"id": "45014942-0a2e-4f46-b395-f82f97bfa93e",
"name": "webhook_url",
"type": "string",
"value": "https://webhook.site/7b5380a0-0544-48dc-be43-0116cb2d52c2"
},
{
"id": "bf011e1f-7032-49db-8f25-31ec4c35b9c5",
"name": "base_url",
"type": "string",
"value": "https://www.courtlistener.com"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "8dc0a8cd-e4d9-4252-9dd2-94ee95d698e9",
"name": "法律ケース研究用Bright Data MCPクライアント",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
200,
140
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $json.url }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "f3ea0d19-703b-4f99-955c-122162065363",
"name": "ケース抽出器",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
600,
140
],
"parameters": {
"text": "=Extract the content in a structured format. Here's the content : {{ $json.result.content[0].text }}",
"messages": {
"messageValues": [
{
"message": "You are an expert structured data extractor"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "a3fe5ce7-3a91-459d-8ef8-17a06fbef12a",
"name": "構造化出力パーサー",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
800,
360
],
"parameters": {
"jsonSchemaExample": "[{\n\"Id\": \"\",\n\"Link\" : \"\",\n\"Title\": \n\"United States v. IXCOLGONZALEZ\"\n}]"
},
"typeVersion": 1.2
},
{
"id": "5fd6d0a3-46ca-4184-bc5c-dfc0966f0538",
"name": "アイテムループ処理",
"type": "n8n-nodes-base.splitInBatches",
"position": [
1320,
140
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "74a02ac0-859d-4611-aeb0-021a654c92b8",
"name": "ループ内法律ケース研究用Bright Data MCPクライアント",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
1860,
160
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $('Set the Legal Case Research URL').item.json.base_url }}/{{ $json.Link }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "beb67c30-dd39-4c7d-94f8-853410dec09b",
"name": "ループ内HTMLテキストデータ抽出",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
2080,
160
],
"parameters": {
"text": "=Extract html to textual content {{ $json.result.content[0].text }}",
"promptType": "define"
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "b7fc74e5-4165-4b1a-9c0a-27565302c0e1",
"name": "ループ内HTMLテキストデータ抽出用Webhook通知",
"type": "n8n-nodes-base.httpRequest",
"position": [
2440,
260
],
"parameters": {
"url": "={{ $('Set the Legal Case Research URL').item.json.webhook_url }}",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"name": "case_content",
"value": "={{ $json.text }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "07b78de1-fdc8-4233-a231-37258fa5d1f0",
"name": "ケース内容をディスクに書き込み",
"type": "n8n-nodes-base.readWriteFile",
"position": [
2700,
60
],
"parameters": {
"options": {},
"fileName": "=d:\\Case-{{ $('Loop Over Items').item.json['Id'] }}.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "ff687082-9e3d-4043-9aa6-29e3029499d4",
"name": "ケースデータ抽出用GoogleGeminiチャットモデル",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
580,
360
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "0057d772-732e-4e47-8ab8-eebe140df692",
"name": "ケースコレクション出力コード",
"type": "n8n-nodes-base.code",
"position": [
980,
140
],
"parameters": {
"jsCode": "\nreturn $input.first().json.output"
},
"typeVersion": 2
},
{
"id": "c843170b-e360-4eea-853c-ef38c9f3affe",
"name": "ループ内HTMLテキストデータ抽出用GoogleGeminiチャットモデル",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
2100,
360
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.0-flash-exp"
},
"credentials": {
"googlePalmApi": {
"id": "YeO7dHZnuGBVQKVZ",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "90f4670a-1fca-4826-9017-64a31f29cbc2",
"name": "付箋1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1220,
0
],
"parameters": {
"color": 5,
"width": 1660,
"height": 520,
"content": "## Bright Data Legal Case Research Scraper\n\nLoop through and perform the data extraction using MCP and LLMs"
},
"typeVersion": 1
},
{
"id": "58aac68b-2598-465b-ab3c-f5c0ebcdb595",
"name": "付箋4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-60,
-260
],
"parameters": {
"color": 5,
"width": 440,
"height": 220,
"content": "## LLM Usages\n\nOpenAI 4o mini LLM is being utilized for the structured data extraction handling."
},
"typeVersion": 1
},
{
"id": "14bbbc73-06cd-4513-b9e6-2aebb5009c3d",
"name": "付箋5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-580,
-860
],
"parameters": {
"color": 7,
"width": 400,
"height": 400,
"content": "## Logo\n\n\n\n"
},
"typeVersion": 1
},
{
"id": "96d74c50-074e-4b83-9422-ff2ce56bd55d",
"name": "付箋3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-580,
-360
],
"parameters": {
"width": 400,
"height": 320,
"content": "## Note\n\nDeals with the Legal Case data extraction by utilizing the Bright Data MCP and OpenAI GPT 4o LLM.\n\n**Please make sure to set the input fields node with the Legal case URL\n\nPlease make sure to update the Webhook Notification URL of your interest**"
},
"typeVersion": 1
},
{
"id": "08c6a217-5773-4ebc-ba6e-326de99e90e5",
"name": "待機",
"type": "n8n-nodes-base.wait",
"position": [
1580,
160
],
"webhookId": "65c9fcd3-2c82-4bdd-80b6-271d65b7f61a",
"parameters": {
"amount": 10
},
"typeVersion": 1.1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "03af01f8-7276-4c3c-a610-6532f0d51ef7",
"connections": {
"08c6a217-5773-4ebc-ba6e-326de99e90e5": {
"main": [
[
{
"node": "74a02ac0-859d-4611-aeb0-021a654c92b8",
"type": "main",
"index": 0
}
]
]
},
"f3ea0d19-703b-4f99-955c-122162065363": {
"main": [
[
{
"node": "0057d772-732e-4e47-8ab8-eebe140df692",
"type": "main",
"index": 0
}
]
]
},
"5fd6d0a3-46ca-4184-bc5c-dfc0966f0538": {
"main": [
[],
[
{
"node": "08c6a217-5773-4ebc-ba6e-326de99e90e5",
"type": "main",
"index": 0
}
]
]
},
"a3fe5ce7-3a91-459d-8ef8-17a06fbef12a": {
"ai_outputParser": [
[
{
"node": "f3ea0d19-703b-4f99-955c-122162065363",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"8f1934bf-ccec-4b25-b6cc-7607dcbdf798": {
"main": [
[
{
"node": "048c1093-ea88-441c-98fa-a2d003ab6b8d",
"type": "main",
"index": 0
}
]
]
},
"07b78de1-fdc8-4233-a231-37258fa5d1f0": {
"main": [
[]
]
},
"048c1093-ea88-441c-98fa-a2d003ab6b8d": {
"main": [
[
{
"node": "8dc0a8cd-e4d9-4252-9dd2-94ee95d698e9",
"type": "main",
"index": 0
}
]
]
},
"9e9a27ce-b95c-4ecd-b3c4-97aba420ce45": {
"main": [
[
{
"node": "8f1934bf-ccec-4b25-b6cc-7607dcbdf798",
"type": "main",
"index": 0
}
]
]
},
"0057d772-732e-4e47-8ab8-eebe140df692": {
"main": [
[
{
"node": "5fd6d0a3-46ca-4184-bc5c-dfc0966f0538",
"type": "main",
"index": 0
}
]
]
},
"beb67c30-dd39-4c7d-94f8-853410dec09b": {
"main": [
[
{
"node": "f8c4804a-85ad-462c-913d-e0bc5242bc74",
"type": "main",
"index": 0
},
{
"node": "b7fc74e5-4165-4b1a-9c0a-27565302c0e1",
"type": "main",
"index": 0
}
]
]
},
"8dc0a8cd-e4d9-4252-9dd2-94ee95d698e9": {
"main": [
[
{
"node": "f3ea0d19-703b-4f99-955c-122162065363",
"type": "main",
"index": 0
}
]
]
},
"ff687082-9e3d-4043-9aa6-29e3029499d4": {
"ai_languageModel": [
[
{
"node": "f3ea0d19-703b-4f99-955c-122162065363",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"f8c4804a-85ad-462c-913d-e0bc5242bc74": {
"main": [
[
{
"node": "07b78de1-fdc8-4233-a231-37258fa5d1f0",
"type": "main",
"index": 0
}
]
]
},
"74a02ac0-859d-4611-aeb0-021a654c92b8": {
"main": [
[
{
"node": "beb67c30-dd39-4c7d-94f8-853410dec09b",
"type": "main",
"index": 0
}
]
]
},
"b7fc74e5-4165-4b1a-9c0a-27565302c0e1": {
"main": [
[
{
"node": "5fd6d0a3-46ca-4184-bc5c-dfc0966f0538",
"type": "main",
"index": 0
}
]
]
},
"c843170b-e360-4eea-853c-ef38c9f3affe": {
"ai_languageModel": [
[
{
"node": "beb67c30-dd39-4c7d-94f8-853410dec09b",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}よくある質問
このワークフローの使い方は？
上記のJSON設定コードをコピーし、n8nインスタンスで新しいワークフローを作成して「JSONからインポート」を選択、設定を貼り付けて認証情報を必要に応じて変更してください。
このワークフローはどんな場面に適していますか？
上級 - 人工知能, IT運用
有料ですか？
このワークフローは完全無料です。ただし、ワークフローで使用するサードパーティサービス（OpenAI APIなど）は別途料金が発生する場合があります。
関連ワークフロー
Bright DataとGoogle Geminiを使用したGoogle Mapsビジネス情報スクレイピングとリードリッチ化
Bright DataとGoogle Geminiを利用したGoogle Maps企業情報スクレイピングとリードリッチ化ツール
Set
Code
Wait
+
Set
Code
Wait
29 ノードRanjan Dailata
リード獲得
Bright Data MCPサーバーとGoogle Geminiを使ったLinkedInウェブスクレイピング
Bright Data MCPサーバーとGoogle Geminiを使用したLinkedInデータの抽出・変換
Set
Code
Merge
+
Set
Code
Merge
20 ノードRanjan Dailata
人工知能
Bright Data と OpenAI 4o mini を使用した自動履歴書求人情報マッチングエンジン
Bright Data MCP と OpenAI 4o mini を使った自動履歴書職業マッチングエンジン
Set
Function
Split Out
+
Set
Function
Split Out
22 ノードRanjan Dailata
人事
AIアゲント駆動のProduct Huntデータ抽出と検索（Bright DataとGoogle Geminiを使用）
Bright Data MCPとGoogle Gemini AIを使ってProduct Huntデータをクロールして検索
Set
Function
Mcp Client
+
Set
Function
Mcp Client
21 ノードRanjan Dailata
人工知能
Brave検索による構造化データ抽出（Bright Data MCP + Google Gemini）
Bright Data MCPとGoogle Geminiを使用してBrave検索から構造化されたデータを抽出
Set
Switch
Function
+
Set
Switch
Function
24 ノードRanjan Dailata
人工知能
Amazon製品の価格下落をBright Dataで抽出・要約・分析
Bright DataとGoogle GeminiでAmazonの価格下落情報を抽出・要約・分析
Set
Wait
Merge
+
Set
Wait
Merge
26 ノードRanjan Dailata
人工知能
ワークフロー情報
難易度
上級
ノード数22
カテゴリー2
ノードタイプ13
作成者
Ranjan Dailata
@ranjancseA Professional based out of India specialized in handling AI-powered automations. Contact me at ranjancse@gmail.com
外部リンク
n8n.ioで表示 →
このワークフローを共有