DataForge Lite — Single URL AI Scraper

{
  "meta": {
    "instanceId": "dataforge-lite-v1"
  },
  "name": "DataForge Lite — Single URL AI Scraper",
  "tags": [
    {
      "id": "dataforge",
      "name": "DataForge"
    },
    {
      "id": "autoflow",
      "name": "AutoFlow"
    },
    {
      "id": "lite",
      "name": "Lite"
    }
  ],
  "nodes": [
    {
      "id": "trigger",
      "name": "Scrape URL",
      "type": "n8n-nodes-base.webhook",
      "position": [
        200,
        400
      ],
      "webhookId": "dataforge-lite",
      "parameters": {
        "path": "dataforge-lite",
        "options": {},
        "httpMethod": "POST",
        "responseMode": "responseNode"
      },
      "typeVersion": 2
    },
    {
      "id": "validate",
      "name": "Validate",
      "type": "n8n-nodes-base.code",
      "position": [
        400,
        400
      ],
      "parameters": {
        "jsCode": "try {\n  const b = $input.first().json.body || $input.first().json;\n  if (!b.url) throw new Error('URL is required.');\n  return [{ json: { url: b.url, extractFields: b.extract_fields || 'price,features,description', name: b.name || '' } }];\n} catch (e) { throw new Error('Invalid input: ' + e.message); }"
      },
      "typeVersion": 2
    },
    {
      "id": "fetch",
      "name": "Fetch Page",
      "type": "n8n-nodes-base.httpRequest",
      "maxTries": 2,
      "position": [
        600,
        400
      ],
      "parameters": {
        "url": "={{ $json.url }}",
        "method": "GET",
        "options": {
          "timeout": 20000
        },
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "User-Agent",
              "value": "Mozilla/5.0 (compatible; DataForge/1.0)"
            }
          ]
        }
      },
      "retryOnFail": true,
      "typeVersion": 4.2,
      "continueOnFail": true
    },
    {
      "id": "extract",
      "name": "Extract Text",
      "type": "n8n-nodes-base.code",
      "position": [
        800,
        400
      ],
      "parameters": {
        "jsCode": "try {\n  const url = $('Validate').first().json;\n  const r = $input.first().json;\n  const html = typeof r === 'string' ? r : (r.data || r.body || JSON.stringify(r));\n  const text = html.replace(/<script[^>]*>[\\s\\S]*?<\\/script>/gi,'').replace(/<style[^>]*>[\\s\\S]*?<\\/style>/gi,'').replace(/<[^>]+>/g,' ').replace(/\\s+/g,' ').trim().substring(0,4000);\n  return [{ json: { ...url, pageText: text } }];\n} catch(e) { throw new Error('Extract failed: ' + e.message); }"
      },
      "typeVersion": 2
    },
    {
      "id": "ai",
      "name": "AI: Extract Data",
      "type": "n8n-nodes-base.openAi",
      "maxTries": 3,
      "position": [
        1020,
        400
      ],
      "parameters": {
        "model": "gpt-4o-mini",
        "options": {
          "maxTokens": 800,
          "temperature": 0.2,
          "responseFormat": "json_object"
        },
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "=Extract from the page: {{ $json.extractFields }}. Also: title, description, stats, sentiment. JSON: { \"title\": \"\", \"description\": \"\", \"extractedData\": {}, \"statistics\": [], \"sentiment\": \"\" }"
            },
            {
              "role": "user",
              "content": "=URL: {{$json.url}}\nExtract: {{$json.extractFields}}\n\nContent:\n{{$json.pageText}}"
            }
          ]
        }
      },
      "retryOnFail": true,
      "typeVersion": 1.8,
      "waitBetweenTries": 2000
    },
    {
      "id": "respond",
      "name": "Respond",
      "type": "n8n-nodes-base.respondToWebhook",
      "position": [
        1240,
        400
      ],
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ $input.first().json.message?.content || $input.first().json.content || '{}' }}"
      },
      "typeVersion": 1.1
    },
    {
      "id": "note",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        120,
        220
      ],
      "parameters": {
        "color": 6,
        "width": 260,
        "height": 100,
        "content": "## DataForge Lite\nPOST a URL, get structured data.\nNo Sheets, no schedule."
      },
      "typeVersion": 1
    }
  ],
  "settings": {
    "executionOrder": "v1",
    "saveManualExecutions": true
  },
  "connections": {
    "Validate": {
      "main": [
        [
          {
            "node": "Fetch Page",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Page": {
      "main": [
        [
          {
            "node": "Extract Text",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Scrape URL": {
      "main": [
        [
          {
            "node": "Validate",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Text": {
      "main": [
        [
          {
            "node": "AI: Extract Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "AI: Extract Data": {
      "main": [
        [
          {
            "node": "Respond",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}