AI駆動のウェブスクレイピング:Jina、Google Sheets、OpenAIを使ったシンプルなソリューション

中級

これはAI分野の自動化ワークフローで、7個のノードを含みます。主にSplitOut, HttpRequest, GoogleSheets, ManualTrigger, LmChatOpenAi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。 AI駆動のウェブスクレイピング:Jina、Google Sheets、OpenAIを使ったシンプルなソリューション

前提条件
  • ターゲットAPIの認証情報が必要な場合あり
  • Google Sheets API認証情報
  • OpenAI API Key

カテゴリー

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
{
  "nodes": [
    {
      "id": "c3ef40df-084e-435c-9a11-3aa0a2f94f36",
      "name": "\"Test workflow\"クリック時",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        740,
        520
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "e0583472-a450-4582-83bc-84a014bea543",
      "name": "分割出力",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        1640,
        520
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "output.results"
      },
      "typeVersion": 1
    },
    {
      "id": "b8aa573d-5b63-4669-900f-bcc915b6ad41",
      "name": "Google Sheetsに保存",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        1900,
        520
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "name",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "name",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "price",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "price",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "availability",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "availability",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "image",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "image",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "link",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "link",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": [
            "Book prices"
          ]
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "list",
          "value": 258629074,
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1VDbfi2PpeheD2ZlO6feX3RdMeSsm0XukQlNVW8uVcuo/edit#gid=258629074",
          "cachedResultName": "Sheet2"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1VDbfi2PpeheD2ZlO6feX3RdMeSsm0XukQlNVW8uVcuo",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1VDbfi2PpeheD2ZlO6feX3RdMeSsm0XukQlNVW8uVcuo/edit?usp=drivesdk",
          "cachedResultName": "Book Prices"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "GHRceL2SKjXxz0Dx",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "a63c3ab3-6aab-43b2-8af6-8b00e24e0ee6",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1300,
        700
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "5oYe8Cxj7liOPAKk",
          "name": "Derek T"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "40326966-0c46-4df2-8d80-fa014e05b693",
      "name": "情報抽出",
      "type": "@n8n/n8n-nodes-langchain.informationExtractor",
      "position": [
        1260,
        520
      ],
      "parameters": {
        "text": "={{ $json.data }}",
        "options": {
          "systemPromptTemplate": "You are an expert extraction algorithm.\nOnly extract relevant information from the text.\nIf you do not know the value of an attribute asked to extract, you may omit the attribute's value.\nAlways output the data in a json array called results.  Each book should have a title, price, availability and product_url, image_url"
        },
        "schemaType": "manual",
        "inputSchema": "{\n  \"results\": {\n      \"type\": \"array\",\n      \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"price\": {\n              \"type\": \"string\"\n              },\n            \"title\": {\n              \"type\": \"string\"\n            },\n            \"image_url\": {\n              \"type\": \"string\"\n            },\n            \"product_url\": {\n              \"type\": \"string\"\n            },\n            \"availability\": {\n              \"type\": \"string\"\n            }            \n           }\n      }\n  }\n}"
      },
      "typeVersion": 1
    },
    {
      "id": "8ddca560-8da7-4090-b865-0523f95ca463",
      "name": "Jina Fetch",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1020,
        520
      ],
      "parameters": {
        "url": "https://r.jina.ai/http://books.toscrape.com/catalogue/category/books/historical-fiction_4/index.html",
        "options": {
          "allowUnauthorizedCerts": true
        },
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "ALBmOXmADcPmyHr1",
          "name": "jina"
        }
      },
      "typeVersion": 4.1
    },
    {
      "id": "b1745cea-fdbe-4f14-b09c-884549beac7e",
      "name": "付箋5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        80,
        320
      ],
      "parameters": {
        "color": 5,
        "width": 587,
        "height": 570,
        "content": "## Start here: Step-by Step Youtube Tutorial :star:\n\n[![AI Powered Web Scraping : the EASY way with n8n and Jina.ai (no-code!)](https://img.youtube.com/vi/f3AJYXHirr8/sddefault.jpg)](https://youtu.be/f3AJYXHirr8)\n\n[Google Sheet Example](https://docs.google.com/spreadsheets/d/1VDbfi2PpeheD2ZlO6feX3RdMeSsm0XukQlNVW8uVcuo/edit?usp=sharing)\n\n\n"
      },
      "typeVersion": 1
    }
  ],
  "pinData": {},
  "connections": {
    "e0583472-a450-4582-83bc-84a014bea543": {
      "main": [
        [
          {
            "node": "b8aa573d-5b63-4669-900f-bcc915b6ad41",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "8ddca560-8da7-4090-b865-0523f95ca463": {
      "main": [
        [
          {
            "node": "40326966-0c46-4df2-8d80-fa014e05b693",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "a63c3ab3-6aab-43b2-8af6-8b00e24e0ee6": {
      "ai_languageModel": [
        [
          {
            "node": "40326966-0c46-4df2-8d80-fa014e05b693",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "40326966-0c46-4df2-8d80-fa014e05b693": {
      "main": [
        [
          {
            "node": "e0583472-a450-4582-83bc-84a014bea543",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "c3ef40df-084e-435c-9a11-3aa0a2f94f36": {
      "main": [
        [
          {
            "node": "8ddca560-8da7-4090-b865-0523f95ca463",
            "type": "main",
            "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?

中級 - 人工知能

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。

ワークフロー情報
難易度
中級
ノード数7
カテゴリー1
ノードタイプ7
難易度説明

経験者向け、6-15ノードの中程度の複雑さのワークフロー

作成者
Derek Cheung

Derek Cheung

@derekcheungsa

Derek is an engineer, instructor, and investor based in Canada. He is publicly building AI applications to solve real-world problems, leveraging his technical expertise to develop practical solutions.

外部リンク
n8n.ioで表示

このワークフローを共有

カテゴリー

カテゴリー: 34