About this recipe
Recipe Template
{
"meta": {
"instanceId": "6b6a2db47bdf8371d21090c511052883cc9a3f6af5d0d9d567c702d74a18820e"
},
"nodes": [
{
"id": "f4570aad-db25-4dcd-8589-b1c8335935de",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-180,
3800
],
"parameters": [],
"typeVersion": 1
},
{
"id": "bd481559-85f2-4865-8d85-e50e72369f26",
"name": "Wait",
"type": "n8n-nodes-base.wait",
"position": [
940,
3620
],
"webhookId": "f10708f0-38c6-4c75-b635-37222d5b183a",
"parameters": {
"amount": 45
},
"typeVersion": 1.1
},
{
"id": "cc9e9947-19e4-47c5-95b0-a631d688a8b6",
"name": "Sticky Note36",
"type": "n8n-nodes-base.stickyNote",
"position": [
549.7858793743054,
3709.534654112671
],
"parameters": {
"color": 7,
"width": 327.8244990224782,
"height": 268.48353140372035,
"content": "**40 at a time seems to be the memory limit on my server - run until complete with batches of 40 or increase based on your server memory**\n"
},
"typeVersion": 1
},
{
"id": "9ebbd993-9194-40b1-a98e-352eb3a3f9eb",
"name": "Sticky Note28",
"type": "n8n-nodes-base.stickyNote",
"position": [
-50.797941767307435,
3729.028866440868
],
"parameters": {
"color": 7,
"width": 574.7594700148138,
"height": 248.90718753310907,
"content": "**Firecrawl.dev retrieves markdown inc. title, description, links & content. First define the URLs you'd like to scrape**\n"
},
"typeVersion": 1
},
{
"id": "71c0f975-c0f9-47ae-a245-f852387ad461",
"name": "Connect to your own data source",
"type": "n8n-nodes-base.noOp",
"position": [
1380,
3820
],
"parameters": [],
"typeVersion": 1
},
{
"id": "fba918e7-2c88-4de3-a789-cadbf4f2584e",
"name": "Get urls from own data source",
"type": "n8n-nodes-base.noOp",
"position": [
0,
3800
],
"parameters": [],
"typeVersion": 1
},
{
"id": "221a75eb-0bc8-4747-9ec1-1879c46d9163",
"name": "Example fields from data source",
"type": "n8n-nodes-base.set",
"notes": "Define URLs in array",
"position": [
200,
3800
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "cc2c6af0-68d3-49eb-85fe-3288d2ed0f6b",
"name": "Page",
"type": "array",
"value": "[\"https:\/\/www.automake.io\/\", \"https:\/\/www.n8n.io\/\"]"
}
]
},
"includeOtherFields": true
},
"notesInFlow": true,
"typeVersion": 3.4
},
{
"id": "5a914964-e8ef-4064-8ecb-f1866de0d8c6",
"name": "Sticky Note33",
"type": "n8n-nodes-base.stickyNote",
"position": [
-40,
4000
],
"parameters": {
"color": 3,
"width": 510.3561134140244,
"height": 94.13486342358942,
"content": "**REQUIRED**\nConnect to your database of urls to input. Name the column `Page` like in the `Example fields from data source` node and make sure it has one link per row like `split out page urls`"
},
"typeVersion": 1
},
{
"id": "5c004d5c-afeb-47c9-b30b-eb88880f87b9",
"name": "Sticky Note34",
"type": "n8n-nodes-base.stickyNote",
"position": [
900,
4000
],
"parameters": {
"color": 3,
"width": 284.87764467541297,
"height": 168.68864948728321,
"content": "**REQUIRED**\nUpdate the Auth parameter to your own [Firecrawl](https:\/\/firecrawl.dev) dev token\n\n**Header Auth parameter**\nname - Authorization\nvalue - your-own-api-key"
},
"typeVersion": 1
},
{
"id": "53d97054-a5e4-4819-bdd9-f8632c33eba2",
"name": "Sticky Note35",
"type": "n8n-nodes-base.stickyNote",
"position": [
1360,
4000
],
"parameters": {
"color": 3,
"width": 284.87764467541297,
"height": 91.91340067739628,
"content": "**REQUIRED** \nOutput the data to your own data source e.g. Airtable"
},
"typeVersion": 1
},
{
"id": "357a463f-7581-43ba-8930-af27e4762905",
"name": "Sticky Note37",
"type": "n8n-nodes-base.stickyNote",
"position": [
900,
3570.2075673933587
],
"parameters": {
"color": 7,
"width": 181.96744211154697,
"height": 189.23753199986137,
"content": "**Respect API limits (10 requests per min)**\n"
},
"typeVersion": 1
},
{
"id": "77311c67-f50f-427a-87fd-b29b1f542bbc",
"name": "40 items at a time",
"type": "n8n-nodes-base.limit",
"position": [
580,
3800
],
"parameters": {
"maxItems": 40
},
"typeVersion": 1
},
{
"id": "43557ab1-4e52-4598-83a9-e39d5afc6de7",
"name": "10 at a time",
"type": "n8n-nodes-base.splitInBatches",
"position": [
740,
3800
],
"parameters": {
"options": [],
"batchSize": 10
},
"typeVersion": 3
},
{
"id": "555d52e7-010b-462b-9382-26804493de1c",
"name": "Markdown data and Links",
"type": "n8n-nodes-base.set",
"position": [
1160,
3820
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "3a959c64-4c3c-4072-8427-67f6f6ecba1b",
"name": "title",
"type": "string",
"value": "={{ $json.data.metadata.title }}"
},
{
"id": "d2da0859-a7a0-4c39-913a-150ecb95d075",
"name": "description",
"type": "string",
"value": "={{ $json.data.metadata.description }}"
},
{
"id": "62bd2d76-b78d-4501-a59b-a25ed7b345b0",
"name": "content",
"type": "string",
"value": "={{ $json.data.markdown }}"
},
{
"id": "d4c712fa-b52a-498f-8abc-26dc72be61f7",
"name": "links",
"type": "string",
"value": "={{ $json.data.links }} "
}
]
}
},
"notesInFlow": true,
"typeVersion": 3.4
},
{
"id": "aac948e6-ac86-4cea-be84-f27919d6d936",
"name": "Split out page URLs",
"type": "n8n-nodes-base.splitOut",
"position": [
380,
3800
],
"parameters": {
"options": [],
"fieldToSplitOut": "Page"
},
"typeVersion": 1
},
{
"id": "71c5a0d4-540e-4766-ae99-bdc427019dac",
"name": "Retrieve Page Markdown and Links",
"type": "n8n-nodes-base.httpRequest",
"notes": "curl -X POST https:\/\/api.firecrawl.dev\/v1\/scrape \\\n -H 'Content-Type: application\/json' \\\n -H 'Authorization: Bearer YOUR_API_KEY' \\\n -d '{\n \"url\": \"https:\/\/docs.firecrawl.dev\",\n \"formats\" : [\"markdown\", \"html\"]\n }'\n",
"position": [
960,
3820
],
"parameters": {
"url": "https:\/\/api.firecrawl.dev\/v1\/scrape",
"method": "POST",
"options": [],
"jsonBody": "={\n \"url\": \"{{ $json.Page }}\",\n \"formats\" : [\"markdown\", \"links\"]\n} ",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application\/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"id": "nbamiF1MDku2NNz7",
"name": "Firecrawl Bearer"
}
},
"retryOnFail": true,
"typeVersion": 4.2,
"waitBetweenTries": 5000
},
{
"id": "a2f12929-262e-4354-baa3-f9e3c05ec2eb",
"name": "Sticky Note38",
"type": "n8n-nodes-base.stickyNote",
"position": [
-840,
3340
],
"parameters": {
"color": 4,
"width": 581.9949654101088,
"height": 818.5240734585421,
"content": "## Convert URL HTML to Markdown and Get Page Links\n\n## Use Case\nTransform web pages into AI-friendly markdown format:\n- You need to process webpage content for LLM analysis\n- You want to extract both content and links from web pages\n- You need clean, formatted text without HTML markup\n- You want to respect API rate limits while crawling pages\n\n## What this Workflow Does\nThe workflow uses Firecrawl.dev API to process webpages:\n- Converts HTML content to markdown format\n- Extracts all links from each webpage\n- Handles API rate limiting automatically\n- Processes URLs in batches from your database\n\n## Setup\n1. Create a [Firecrawl.dev](https:\/\/www.firecrawl.dev\/) account and get your API key\n2. Add your Firecrawl API key to the HTTP Request node's Authorization header\n3. Connect your URL database to the input node (column name must be \"Page\") or edit the array in `Example fields from data source`\n4. Configure your preferred output database connection\n\n## How to Adjust it to Your Needs\n- Modify input source to pull URLs from different databases\n- Adjust rate limiting parameters if needed\n- Customize output format for your specific use case\n\n\nMade by Simon @ [automake.io](https:\/\/automake.io)\n"
},
"typeVersion": 1
}
],
"pinData": [],
"connections": {
"Wait": {
"main": [
[
{
"node": "10 at a time",
"type": "main",
"index": 0
}
]
]
},
"10 at a time": {
"main": [
null,
[
{
"node": "Retrieve Page Markdown and Links",
"type": "main",
"index": 0
}
]
]
},
"40 items at a time": {
"main": [
[
{
"node": "10 at a time",
"type": "main",
"index": 0
}
]
]
},
"Split out page URLs": {
"main": [
[
{
"node": "40 items at a time",
"type": "main",
"index": 0
}
]
]
},
"Markdown data and Links": {
"main": [
[
{
"node": "Connect to your own data source",
"type": "main",
"index": 0
}
]
]
},
"Get urls from own data source": {
"main": [
[
{
"node": "Example fields from data source",
"type": "main",
"index": 0
}
]
]
},
"Connect to your own data source": {
"main": [
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Example fields from data source": {
"main": [
[
{
"node": "Split out page URLs",
"type": "main",
"index": 0
}
]
]
},
"Retrieve Page Markdown and Links": {
"main": [
[
{
"node": "Markdown data and Links",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Get urls from own data source",
"type": "main",
"index": 0
}
]
]
}
}
}
How to Use an n8n Template
Create a New Workflow
Click "New Workflow" in your n8n dashboard to get started.
Copy & Paste Template
First, copy this template:
Click here to copy the JSON
.
Then, in n8n, click the three dots (···) → "Import from file" and paste the JSON code.
Customize the Nodes
Go through each node in the workflow to update inputs like spreadsheet IDs, email addresses, or message content. Adjust field mappings to match your data.
Grant Access
For nodes that connect to external apps (like Google Sheets or Slack), you'll need to grant access. Connect your accounts using OAuth or an API key and save the credentials in the node.
Test It
Run the workflow by clicking "Execute Node" for each step or "Run Once" for the whole thing. Check the right sidebar to inspect data and debug any errors (they'll show up in red).
Activate Workflow
Once everything works as expected, click the "Activate" toggle to turn your workflow on. You're all set!