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": "AI Lead Scraper \u2014 ISP Proxy Rotation + OpenAI Scoring",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "lead-intake",
"responseMode": "responseNode",
"options": {
"rawBody": false
}
},
"id": "a1b2c3d4-0001-4e5f-9a0b-111111111101",
"name": "Webhook \u2014 Lead Intake",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
240,
300
]
},
{
"parameters": {
"mode": "runOnceForAllItems",
"language": "python",
"pythonCode": "import random\nimport json\n\n# Static ISP proxy pool \u2014 rotate per request\nPROXY_POOL = [\n {\"host\": \"isp-us-01.proxyfleet.io\", \"port\": 8080, \"user\": \"{{$env.ISP_PROXY_USER}}\", \"pass\": \"{{$env.ISP_PROXY_PASS}}\"},\n {\"host\": \"isp-eu-02.proxyfleet.io\", \"port\": 8080, \"user\": \"{{$env.ISP_PROXY_USER}}\", \"pass\": \"{{$env.ISP_PROXY_PASS}}\"},\n {\"host\": \"isp-ap-03.proxyfleet.io\", \"port\": 8080, \"user\": \"{{$env.ISP_PROXY_USER}}\", \"pass\": \"{{$env.ISP_PROXY_PASS}}\"},\n {\"host\": \"isp-uk-04.proxyfleet.io\", \"port\": 8080, \"user\": \"{{$env.ISP_PROXY_USER}}\", \"pass\": \"{{$env.ISP_PROXY_PASS}}\"}\n]\n\nproxy = random.choice(PROXY_POOL)\nproxy_url = f\"http://{proxy['user']}:{proxy['pass']}@{proxy['host']}:{proxy['port']}\"\n\nitems = _input.all()\nresults = []\nfor item in items:\n body = item.json.get('body', item.json)\n results.append({\n 'json': {\n 'target_url': body.get('url', ''),\n 'company': body.get('company', ''),\n 'contact_email': body.get('email', ''),\n 'proxy_url': proxy_url,\n 'proxy_host': proxy['host'],\n 'rotation_id': f\"rot-{random.randint(100000, 999999)}\"\n }\n })\nreturn results"
},
"id": "a1b2c3d4-0002-4e5f-9a0b-111111111102",
"name": "Python \u2014 Rotate ISP Proxy",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
480,
300
]
},
{
"parameters": {
"method": "GET",
"url": "={{ $json.target_url }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpProxyAuth",
"options": {
"proxy": "={{ $json.proxy_url }}",
"timeout": 30000,
"redirect": {
"redirect": {
"followRedirects": true,
"maxRedirects": 5
}
}
}
},
"id": "a1b2c3d4-0003-4e5f-9a0b-111111111103",
"name": "HTTP \u2014 Scrape Target Page",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
720,
300
],
"onError": "continueErrorOutput"
},
{
"parameters": {
"mode": "runOnceForAllItems",
"language": "python",
"pythonCode": "import re\nimport json\n\nitems = _input.all()\nresults = []\nfor item in items:\n html = str(item.json.get('data', item.json.get('body', '')))\n company = item.json.get('company', '')\n email = item.json.get('contact_email', '')\n \n # Extract structured signals\n title_match = re.search(r'<title[^>]*>([^<]+)</title>', html, re.I)\n emails = list(set(re.findall(r'[\\w.+-]+@[\\w-]+\\.[\\w.-]+', html)))\n phones = list(set(re.findall(r'\\+?[\\d\\s()-]{10,18}', html)))\n \n results.append({\n 'json': {\n 'company': company,\n 'contact_email': email or (emails[0] if emails else ''),\n 'page_title': title_match.group(1).strip() if title_match else '',\n 'emails_found': emails[:5],\n 'phones_found': phones[:3],\n 'proxy_host': item.json.get('proxy_host', ''),\n 'html_length': len(html),\n 'scrape_status': 'success' if len(html) > 500 else 'partial'\n }\n })\nreturn results"
},
"id": "a1b2c3d4-0004-4e5f-9a0b-111111111104",
"name": "Python \u2014 Extract Lead Signals",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
960,
300
]
},
{
"parameters": {
"resource": "chat",
"operation": "complete",
"model": "gpt-4o-mini",
"prompt": {
"messages": [
{
"role": "system",
"content": "You are a B2B lead qualification engine. Score leads 0-100 based on company signals, contact quality, and buying intent. Return ONLY valid JSON with keys: score, tier (hot/warm/cold), reasoning, recommended_action."
},
{
"role": "user",
"content": "=Qualify this lead:\nCompany: {{ $json.company }}\nEmail: {{ $json.contact_email }}\nPage Title: {{ $json.page_title }}\nEmails Found: {{ $json.emails_found }}\nPhones Found: {{ $json.phones_found }}\nScrape Status: {{ $json.scrape_status }}\nProxy Used: {{ $json.proxy_host }}"
}
]
},
"options": {
"temperature": 0.2,
"maxTokens": 512
}
},
"id": "a1b2c3d4-0005-4e5f-9a0b-111111111105",
"name": "OpenAI \u2014 Auto Lead Scoring",
"type": "n8n-nodes-base.openAi",
"typeVersion": 1.4,
"position": [
1200,
300
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "runOnceForAllItems",
"language": "python",
"pythonCode": "import json\n\nitems = _input.all()\nresults = []\nfor item in items:\n ai_response = item.json.get('message', {}).get('content', item.json.get('text', '{}'))\n try:\n score_data = json.loads(ai_response)\n except:\n score_data = {'score': 0, 'tier': 'cold', 'reasoning': 'parse_error', 'recommended_action': 'retry'}\n \n results.append({\n 'json': {\n 'lead_id': f\"LEAD-{item.json.get('rotation_id', '000')}\",\n 'company': item.json.get('company', ''),\n 'contact_email': item.json.get('contact_email', ''),\n 'score': score_data.get('score', 0),\n 'tier': score_data.get('tier', 'cold'),\n 'reasoning': score_data.get('reasoning', ''),\n 'recommended_action': score_data.get('recommended_action', ''),\n 'proxy_host': item.json.get('proxy_host', ''),\n 'qualified_at': '{{ $now.toISO() }}'\n }\n })\nreturn results"
},
"id": "a1b2c3d4-0006-4e5f-9a0b-111111111106",
"name": "Python \u2014 Structure Lead Output",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1440,
300
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify($json) }}",
"options": {
"responseCode": 200,
"responseHeaders": {
"entries": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
}
},
"id": "a1b2c3d4-0007-4e5f-9a0b-111111111107",
"name": "Respond \u2014 Qualified Lead JSON",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1680,
300
]
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "hot-lead-filter",
"leftValue": "={{ $json.tier }}",
"rightValue": "hot",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "a1b2c3d4-0008-4e5f-9a0b-111111111108",
"name": "IF \u2014 Hot Lead?",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1440,
520
]
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.CRM_WEBHOOK_URL }}",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify($json) }}",
"options": {}
},
"id": "a1b2c3d4-0009-4e5f-9a0b-111111111109",
"name": "HTTP \u2014 Push to CRM",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1680,
520
]
}
],
"connections": {
"Webhook \u2014 Lead Intake": {
"main": [
[
{
"node": "Python \u2014 Rotate ISP Proxy",
"type": "main",
"index": 0
}
]
]
},
"Python \u2014 Rotate ISP Proxy": {
"main": [
[
{
"node": "HTTP \u2014 Scrape Target Page",
"type": "main",
"index": 0
}
]
]
},
"HTTP \u2014 Scrape Target Page": {
"main": [
[
{
"node": "Python \u2014 Extract Lead Signals",
"type": "main",
"index": 0
}
]
]
},
"Python \u2014 Extract Lead Signals": {
"main": [
[
{
"node": "OpenAI \u2014 Auto Lead Scoring",
"type": "main",
"index": 0
}
]
]
},
"OpenAI \u2014 Auto Lead Scoring": {
"main": [
[
{
"node": "Python \u2014 Structure Lead Output",
"type": "main",
"index": 0
}
]
]
},
"Python \u2014 Structure Lead Output": {
"main": [
[
{
"node": "Respond \u2014 Qualified Lead JSON",
"type": "main",
"index": 0
},
{
"node": "IF \u2014 Hot Lead?",
"type": "main",
"index": 0
}
]
]
},
"IF \u2014 Hot Lead?": {
"main": [
[
{
"node": "HTTP \u2014 Push to CRM",
"type": "main",
"index": 0
}
],
[]
]
}
},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true,
"callerPolicy": "workflowsFromSameOwner",
"errorWorkflow": ""
},
"staticData": null,
"tags": [
{
"name": "lead-generation",
"createdAt": "2026-06-08T00:00:00.000Z",
"updatedAt": "2026-06-08T00:00:00.000Z",
"id": "tag-lead-gen"
},
{
"name": "proxy-rotation",
"createdAt": "2026-06-08T00:00:00.000Z",
"updatedAt": "2026-06-08T00:00:00.000Z",
"id": "tag-proxy"
}
],
"triggerCount": 1,
"updatedAt": "2026-06-08T12:00:00.000Z",
"versionId": "wf1-v1.0.0",
"meta": {
"templateCredsSetupCompleted": false
}
}
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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Lead Scraper — ISP Proxy Rotation + OpenAI Scoring. Uses httpRequest, openAi. Webhook trigger; 9 nodes.
Source: https://github.com/36412749-collab/n8n-ai-agent-scraping-booster/blob/main/n8n_workflow_1_ai_lead_scraper.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.
CLINICAINTEGRAL_secretary. Uses postgres, mcpClientTool, googleDriveTool, toolWorkflow. Webhook trigger; 89 nodes.
Postgres, Mcp Client Tool, Google Drive Tool +14
Remi 1.1. Uses lmChatOpenAi, memoryPostgresChat, openAi, postgres. Webhook trigger; 89 nodes.
OpenAI Chat, Memory Postgres Chat, OpenAI +7
This n8n workflow orchestrates a powerful suite of AI Agents and automations to manage and optimize various aspects of an e-commerce operation, particularly for platforms like Shopify. It leverages La
Google Sheets, HTTP Request, Slack +10
my-secretary. Uses postgres, mcpClientTool, googleDriveTool, toolWorkflow. Webhook trigger; 86 nodes.
Postgres, Mcp Client Tool, Google Drive Tool +13
Aura-bot. Uses postgres, lmChatOpenAi, memoryBufferWindow, httpRequest. Webhook trigger; 82 nodes.
Postgres, OpenAI Chat, Memory Buffer Window +6