
Web Scraping & Screenshot Automation with GPT 4.1 mini and Firecrawl
Description
Categories
📢 Marketing🤖 AI & Machine Learning
Nodes Used
n8n-nodes-base.stickyNoten8n-nodes-base.stickyNoten8n-nodes-base.stickyNoten8n-nodes-base.stickyNoten8n-nodes-base.stickyNoten8n-nodes-base.httpRequestn8n-nodes-base.httpRequestn8n-nodes-base.httpRequestn8n-nodes-base.httpRequest@n8n/n8n-nodes-langchain.agent
PriceGratuit
Views0
Last Updated11/28/2025
workflow.json
{
"meta": {
"instanceId": "07969d022f78c86e07b98687c867015ba10dcaf713875d5ef0558ba6f30ac8fc"
},
"nodes": [
{
"id": "d324309d-a8e6-49a7-9aba-6539822ccc09",
"name": "Site",
"type": "n8n-nodes-base.httpRequest",
"position": [
3408,
1472
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/search",
"method": "POST",
"options": {},
"jsonBody": "{\n \"query\": \"nate herk site:www.geeky-gadgets.com\",\n \"limit\": 5\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{}
]
}
},
"typeVersion": 4.2
},
{
"id": "0aea3a14-37ac-46c6-8e8c-a12c3750e801",
"name": "In URL",
"type": "n8n-nodes-base.httpRequest",
"position": [
3408,
1680
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/search",
"method": "POST",
"options": {},
"jsonBody": "{\n \"query\": \"nate herk inurl:skool\",\n \"limit\": 5\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{}
]
}
},
"typeVersion": 4.2
},
{
"id": "f6c6becf-a6de-4523-846b-9ec51d485a2f",
"name": "Exclusion",
"type": "n8n-nodes-base.httpRequest",
"position": [
3760,
1472
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/search",
"method": "POST",
"options": {},
"jsonBody": "{\n \"query\": \"nate herk -inurl:skool\",\n \"limit\": 6\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{}
]
}
},
"typeVersion": 4.2
},
{
"id": "8107f822-b505-4158-8c13-8f1bf7774db0",
"name": "Pro",
"type": "n8n-nodes-base.httpRequest",
"position": [
3760,
1680
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/search",
"method": "POST",
"options": {},
"jsonBody": "{\n \"query\": \"Nate Herk site:youtube.com -shorts intitle:automation\",\n \"limit\": 5\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"headerParameters": {
"parameters": [
{}
]
}
},
"typeVersion": 4.2
},
{
"id": "b3aacfb1-b468-4674-99c0-9bf59147bfac",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
3280,
1408
],
"parameters": {
"color": 5,
"width": 340,
"height": 200,
"content": "## Within a Specific Website"
},
"typeVersion": 1
},
{
"id": "a6a4c52b-6388-4fba-832f-2f77c9c75d62",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
3280,
1632
],
"parameters": {
"color": 5,
"width": 340,
"height": 200,
"content": "## Word Appears in URL"
},
"typeVersion": 1
},
{
"id": "c535f40e-4dae-4fe7-bbd7-c87794e46fcc",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
3648,
1408
],
"parameters": {
"color": 5,
"width": 340,
"height": 200,
"content": "## Exclude Terms\n"
},
"typeVersion": 1
},
{
"id": "5bdedd5c-9068-41aa-8ccc-35ff6acd2360",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
3648,
1632
],
"parameters": {
"color": 5,
"width": 340,
"height": 200,
"content": "## Pro Tip"
},
"typeVersion": 1
},
{
"id": "e287e808-3690-46dc-a85b-aa0ceed922bd",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
3376,
1120
],
"webhookId": "5634d633-9287-41c9-ab57-bea1816b3b0a",
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "d0a5315a-1d4a-41a7-b68c-ab31686370e1",
"name": "GPT 4.1 mini",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
3488,
1264
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "19753a83-34d3-4d61-a1ab-4d7d90f5245d",
"name": "Firecrawl Search",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
3776,
1248
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/search",
"method": "POST",
"options": {},
"jsonBody": "={\n \"query\": \"{{$fromAI(\"searchQuery\")}}\",\n \"limit\": {{$fromAI(\"limit\",\"the number of search results requested\", number)}},\n \"scrapeOptions\": {\n \"formats\": [\"markdown\", \"screenshot@fullPage\"]}\n}",
"sendBody": true,
"specifyBody": "json",
"toolDescription": "Use this tool to search the internet"
},
"typeVersion": 4.2
},
{
"id": "34fa76be-ef2a-4962-9ff1-9d5268525e5f",
"name": "Search Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
3536,
1120
],
"parameters": {
"options": {
"systemMessage": "=# Overview\nYou are a Firecrawl Search Query Generator Agent.\n\nYou have access to a tool called FireCrawl Search.\n\nYour job is to:\n1. Convert natural language instructions into a properly formatted Firecrawl query string using supported operators.\n2. Send that query — along with a `limit` parameter — to the **FireCrawl Search** tool.\n\n## Query Construction Rules:\n\nUse the following rules to transform user input:\n\n- If the user specifies an exact phrase \n → `Nate Herk`\n\n- To exclude terms or domains, prefix them with `-` \n → `-linkedin`, `-site:facebook.com`\n\n- If the user wants to search within a specific site, use `site:` \n → `site:youtube.com`\n\n- If the user wants a word in the URL, use `inurl:` \n → `inurl:nateherk`\n\n- If the user wants multiple words in the URL, use `allinurl:` \n → `allinurl:nate herk agent`\n\n- If the user wants a word in the title of the page, use `intitle:` \n → `intitle:automation`\n\n- If the user wants multiple words in the title, use `allintitle:` \n → `allintitle:ai agent tutorial`\n\n- If the user wants results related to a domain, use `related:` \n → `related:truehorizonai.com`\n\n\n## Tool Usage Instructions:\n\nAlways call the **FireCrawls Search** tool with:\n- `query`: the final constructed query string \n- `limit`: the number of results the user requested\n\nIf the user does **not specify a limit**, default to: \n→ `limit: 5`\n\n## Output\n\nAlways return all of the important information for each item that the tool gives you. The the title, the URL, the results, etc. \n\nFor each 'data' object that is returned in the results, output every field that lives in that object.\n\n## Examples:\n\n**Input:** Search the internet for Nate Herk \n**Action:** Call FireCrawls Search with: \n```json\n{\n \"query\": Nate Herk,\n \"limit\": 5\n}\n```\n\n**Input:** Find pages with AI agent in the title from YouTube, show me 10 \n**Action:** \n```json\n{\n \"query\": intitle:AI agent site:youtube.com,\n \"limit\": 10\n}\n```\n\n**Input:** Show me results that mention Nate Herk but exclude LinkedIn \n**Action:** \n```json\n{\n \"query\": Nate Herk -site:linkedin.com,\n \"limit\": 5\n}\n```\n"
}
},
"typeVersion": 2
},
{
"id": "459d94c8-028d-4bd0-bf7a-406148441c17",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
3280,
1040
],
"parameters": {
"color": 6,
"width": 700,
"height": 340,
"content": "## Firecrawl Agent"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"GPT 4.1 mini": {
"ai_languageModel": [
[
{
"node": "Search Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Firecrawl Search": {
"ai_tool": [
[
{
"node": "Search Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Search Agent",
"type": "main",
"index": 0
}
]
]
}
}
}