This workflow follows the HTTP Request → OpenAI recipe pattern — see all workflows that pair these two integrations.
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 →
{
"name": "DataForge Lite \u2014 Single URL AI Scraper",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "dataforge-lite",
"responseMode": "responseNode",
"options": {}
},
"id": "trigger",
"name": "Scrape URL",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
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); }"
},
"id": "validate",
"name": "Validate",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
400,
400
]
},
{
"parameters": {
"method": "GET",
"url": "={{ $json.url }}",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "User-Agent",
"value": "Mozilla/5.0 (compatible; DataForge/1.0)"
}
]
},
"options": {
"timeout": 20000
}
},
"id": "fetch",
"name": "Fetch Page",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
600,
400
],
"retryOnFail": true,
"maxTries": 2,
"continueOnFail": true
},
{
"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); }"
},
"id": "extract",
"name": "Extract Text",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
800,
400
]
},
{
"parameters": {
"model": "gpt-4o-mini",
"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}}"
}
]
},
"options": {
"temperature": 0.2,
"maxTokens": 800,
"responseFormat": "json_object"
}
},
"id": "ai",
"name": "AI: Extract Data",
"type": "n8n-nodes-base.openAi",
"typeVersion": 1.8,
"position": [
1020,
400
],
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 2000
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ $input.first().json.message?.content || $input.first().json.content || '{}' }}"
},
"id": "respond",
"name": "Respond",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1240,
400
]
},
{
"parameters": {
"content": "## DataForge Lite\nPOST a URL, get structured data.\nNo Sheets, no schedule.",
"width": 260,
"height": 100,
"color": 6
},
"id": "note",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
120,
220
]
}
],
"connections": {
"Scrape URL": {
"main": [
[
{
"node": "Validate",
"type": "main",
"index": 0
}
]
]
},
"Validate": {
"main": [
[
{
"node": "Fetch Page",
"type": "main",
"index": 0
}
]
]
},
"Fetch Page": {
"main": [
[
{
"node": "Extract Text",
"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
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true
},
"tags": [
{
"name": "DataForge",
"id": "dataforge"
},
{
"name": "AutoFlow",
"id": "autoflow"
},
{
"name": "Lite",
"id": "lite"
}
]
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
DataForge Lite — Single URL AI Scraper. Uses httpRequest, openAi. Webhook trigger; 7 nodes.
Source: https://github.com/enzoemir1/autoflow-n8n-workflows/blob/main/workflows/dataforge-lite.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This workflow captures new leads via webhook, enriches and scores them with Apollo and Google Gemini, logs everything in Google Sheets, and automates outreach, reply handling, follow-ups, meeting prep
This powerful n8n automation workflow is designed to execute advanced B2B lead enrichment and hyper-personalization for cold email outreach. By orchestrating a complex chain of data scraping, AI analy
Propulsar — Content Engine v3. Uses openAi, httpRequest, googleSheets. Webhook trigger; 73 nodes.
Eu Clara – Funil Kiwify Completo. Uses postgres, openAi, httpRequest, gmail. Webhook trigger; 70 nodes.
Postagem Redes — Portal: Ações. Uses openAi, googleGemini, ollama, httpRequest. Webhook trigger; 58 nodes.