Web Scapping

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "active": false,
  "activeVersion": null,
  "activeVersionId": null,
  "connections": {
    "HTTP_Request_Tool": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Gmail": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "createdAt": "2025-04-24T19:44:01.878Z",
  "id": "Cq26r0G0dIkMW6oU",
  "isArchived": false,
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "name": "Web_Scapping",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "minutesInterval": 1
            }
          ]
        }
      },
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.2,
      "position": [
        -680,
        -60
      ],
      "id": "0b185f86-cc69-4e4c-b21c-39ce3bd17f37",
      "name": "Schedule Trigger"
    },
    {
      "parameters": {
        "content": "## Example ReAct AI Agent\n1. Agent Prompt is default\n2. Check the description of the HTTP_Request_Tool, it guides the agent to provide a query string with several parameters instead of a JSON object",
        "height": 923,
        "width": 1477
      },
      "id": "9f385fbb-5886-4afb-9ce3-da53ce73c6c2",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1560,
        300
      ],
      "typeVersion": 1
    },
    {
      "parameters": {
        "options": {}
      },
      "id": "b87308dc-2d52-4c86-a61f-2d5ba4e5858a",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        -1360,
        580
      ],
      "typeVersion": 1.1
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "En tant qu'agent d'automatisation dans n8n, ta mission est d'envoyer des emails via l'adresse email {{$node[\"Credentials\"].json[\"email\"]}} configur\u00e9e dans le n\u0153ud \"Credentials\".\n\nINSTRUCTIONS PR\u00c9CISES:\n1. Cr\u00e9ation d'emails:\n   - OBJET: Commence toujours par \"[AutoMsg]\" suivi d'une description concise bas\u00e9e sur les donn\u00e9es du flux\n   - CORPS: Structure en 3 parties:\n      * Introduction (1-2 phrases expliquant pourquoi ce message est envoy\u00e9)\n      * Contenu principal (inclus les donn\u00e9es du n\u0153ud pr\u00e9c\u00e9dent avec {{$json[\"cl\u00e9_pertinente\"]}})\n      * Conclusion avec action attendue du destinataire\n   - SIGNATURE: \"Cordialement,\\nVotre Assistant Automatis\u00e9\\n{{$workflow.active}} via n8n\"\n\n2. Formule adapt\u00e9e selon le type d'email (d\u00e9fini par {{$json[\"type_message\"]}}):\n   - \"professionnel\": formel, pr\u00e9cis, utilise \"vous\" et vocabulaire business\n   - \"notification\": direct, factuel, phrases courtes, se concentre sur l'\u00e9v\u00e9nement\n   - \"rappel\": courtois mais ferme, mentionne d\u00e9lais/\u00e9ch\u00e9ances\n\n3. COMPORTEMENT AUTONOME:\n   - Utilise toujours les donn\u00e9es disponibles dans $json\n   - Ne demande jamais d'informations suppl\u00e9mentaires\n   - Traite toutes les requ\u00eates comme si les autorisations \u00e9taient d\u00e9j\u00e0 configur\u00e9es\n   - R\u00e9ponds imm\u00e9diatement avec le message format\u00e9 pr\u00eat \u00e0 \u00eatre envoy\u00e9\n\nEXEMPLE DE R\u00c9PONSE:\n\"Voici l'email pr\u00e9par\u00e9 pour envoi:\n- \u00c0: {{$node[\"Destination\"].json[\"email\"]}}\n- Objet: [AutoMsg] Notification de {{$json[\"\u00e9v\u00e9nement\"]}}\n- Corps: [Corps complet de l'email format\u00e9 selon instructions]\n- Statut: Pr\u00eat \u00e0 envoyer via SMTP configur\u00e9\"",
        "hasOutputParser": true,
        "options": {}
      },
      "id": "3a4b0eae-d7d8-4f80-8872-94f6431ea7ea",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        -1140,
        580
      ],
      "typeVersion": 1.8
    },
    {
      "parameters": {
        "name": "HTTP_Request_Tool",
        "description": "Call this tool to fetch a webpage content. The input should be a stringified HTTP query parameter like this: \"?url=VALIDURL&method=SELECTEDMETHOD\". \"url\" parameter should contain the valid URL string. \"method\" key can be either \"full\" or \"simplified\". method=full will fetch the whole webpage content in the Markdown format, including page links and image links. method=simplified will return the Markdown content of the page but remove urls and image links from the page content for simplicity. Before calling this tool, think strategically which \"method\" to call. Best of all to use method=simplified. However, if you anticipate that the page request is not final or if you need to extract links from the page, pick method=full.",
        "workflowId": {
          "__rl": true,
          "mode": "id",
          "value": "fiZ1GOLO4ZSa8yNe"
        },
        "workflowInputs": {
          "mappingMode": "defineBelow",
          "value": {},
          "matchingColumns": [
            "My Workflow"
          ],
          "schema": [
            {
              "id": "My Workflow",
              "displayName": "My Workflow",
              "required": false,
              "defaultMatch": false,
              "display": true,
              "canBeUsedToMatch": true,
              "type": "string",
              "removed": true
            }
          ],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        }
      },
      "id": "181b0ae6-0643-4d29-aab8-ecfc56d7db58",
      "name": "HTTP_Request_Tool",
      "type": "@n8n/n8n-nodes-langchain.toolWorkflow",
      "position": [
        -860,
        780
      ],
      "typeVersion": 2
    },
    {
      "parameters": {
        "modelName": "models/gemini-1.5-flash-001-tuning",
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "typeVersion": 1,
      "position": [
        -1140,
        780
      ],
      "id": "816ba9a1-417a-4f22-a14a-df99b2a691af",
      "name": "Google Gemini Chat Model",
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "sendTo": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('To', ``, 'string') }}",
        "subject": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Subject', ``, 'string') }}",
        "message": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Message', ``, 'string') }}",
        "options": {}
      },
      "type": "n8n-nodes-base.gmailTool",
      "typeVersion": 2.1,
      "position": [
        -1020,
        800
      ],
      "id": "1624fd29-ac92-4ded-b59e-165d1738f5d6",
      "name": "Gmail",
      "credentials": {
        "gmailOAuth2": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "settings": {
    "executionOrder": "v1"
  },
  "shared": [
    {
      "updatedAt": "2025-04-24T19:44:01.878Z",
      "createdAt": "2025-04-24T19:44:01.878Z",
      "role": "workflow:owner",
      "workflowId": "Cq26r0G0dIkMW6oU",
      "projectId": "gGkJ26SwMiOwivnN"
    }
  ],
  "staticData": {
    "node:Schedule Trigger": {
      "recurrenceRules": []
    }
  },
  "tags": [],
  "triggerCount": 2,
  "updatedAt": "2025-05-01T15:47:34.682Z",
  "versionId": "66724105-00a9-4a16-9b66-922365957e87"
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• gmailOAuth2
• googlePalmApi

About this workflow

Web_Scapping. Uses chatTrigger, agent, toolWorkflow, lmChatGoogleGemini. Scheduled trigger; 7 nodes.

Source: https://github.com/Gbessaya-joseph/n8n_workflows/blob/a522e2acded19d463cfd87a6656a4c3a04a6b83a/Gbessaya-joseph/n8n_workflows2025/04/Web_Scapping.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.