This workflow follows the Execute Workflow Trigger → HTTP Request 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": "[FC Sub] Extract Structured Data",
"settings": {
"executionOrder": "v1"
},
"nodes": [
{
"parameters": {
"content": "## [FC Sub] Extract Structured Data\n**Purpose:** LLM-powered structured extraction via Firecrawl `/v1/extract`. Takes an array of URLs plus an optional prompt/schema and returns JSON that conforms to the schema.\n\n**Called by:** main agent's `extract_data` tool.\n\n**Inputs:**\n- `urls[]` (required) \u2014 pages to extract from\n- `prompt?` \u2014 natural-language description of what to extract (required if no schema)\n- `schema?` \u2014 JSON Schema object defining the fields\n- `session_id?`\n\n**Credit cost:** 5 credits per URL extracted (Firecrawl premium op).\n\n**Validation:** If a schema is provided, the response is validated with a lightweight JSON Schema check (type + required fields). `schema_valid` and `validation_errors` are returned so the agent can decide whether to retry.\n\n**Flow:** Trigger \u2192 Prep \u2192 POST `/v1/extract` \u2192 Wait 20s \u2192 Poll \u2192 Shape + Validate \u2192 Ledger \u2192 Return.\n\n**Credentials:** Firecrawl API, Postgres RW.",
"height": 580,
"width": 640,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-40,
-620
],
"id": "sticky-fc-extract",
"name": "README"
},
{
"parameters": {
"inputSource": "passthrough"
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
0,
0
],
"id": "fc-ext-trigger",
"name": "When Executed by Another Workflow"
},
{
"parameters": {
"jsCode": "const input = $input.first().json;\nconst q = (input.query && typeof input.query === 'object') ? input.query : {};\nconst pick = (k, def) => {\n if (input[k] !== undefined) return input[k];\n if (q[k] !== undefined) return q[k];\n return def;\n};\nconst parseIfString = (v, fb) => {\n if (v === undefined || v === null) return fb;\n if (typeof v !== 'string') return v;\n try { return JSON.parse(v); } catch { return fb; }\n};\n\nlet urls = parseIfString(pick('urls'), null);\nif (!Array.isArray(urls)) {\n const single = pick('url');\n if (typeof single === 'string') urls = [single];\n}\nif (!Array.isArray(urls) || urls.length === 0) {\n throw new Error('extract_data requires `urls` (array) or `url` (single string).');\n}\nurls = urls\n .map(u => (typeof u === 'string' ? u.trim() : ''))\n .filter(u => u.length > 0)\n .map(u => /^https?:\\/\\//i.test(u) ? u : 'https://' + u);\nif (urls.length > 10) urls = urls.slice(0, 10); // hard cap \u2014 extract is expensive (5 credits each)\n\nconst prompt = (pick('prompt') || '').toString();\nconst schema = parseIfString(pick('schema'), null);\n\nif (!prompt && !schema) {\n throw new Error('extract_data requires either `prompt` (natural-language goal) or `schema` (JSON Schema).');\n}\n\nconst session_id = (pick('session_id') || $execution.id || 'no-session').toString();\n\nreturn [{ json: {\n urls,\n url_count: urls.length,\n prompt,\n schema,\n session_id,\n execution_id: $execution.id\n} }];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
220,
0
],
"id": "fc-ext-prep",
"name": "Prep Input"
},
{
"parameters": {
"method": "POST",
"url": "https://api.firecrawl.dev/v1/extract",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"urls\": {{ JSON.stringify($json.urls) }}\n {{ $json.prompt ? (', \"prompt\": ' + JSON.stringify($json.prompt)) : '' }}\n {{ $json.schema ? (', \"schema\": ' + JSON.stringify($json.schema)) : '' }}\n}",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 60000
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
440,
0
],
"id": "fc-ext-start",
"name": "Start Extract Job"
},
{
"parameters": {
"amount": 20,
"unit": "seconds"
},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
660,
0
],
"id": "fc-ext-wait1",
"name": "Wait 20s"
},
{
"parameters": {
"method": "GET",
"url": "=https://api.firecrawl.dev/v1/extract/{{ $('Start Extract Job').first().json.id }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 30000
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
880,
0
],
"id": "fc-ext-poll1",
"name": "Poll Status (20s)"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose"
},
"conditions": [
{
"id": "ext-status-1",
"leftValue": "={{ $json.status }}",
"rightValue": "completed",
"operator": {
"type": "string",
"operation": "equals"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1100,
0
],
"id": "fc-ext-if-done",
"name": "IF Completed"
},
{
"parameters": {
"amount": 30,
"unit": "seconds"
},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
1320,
200
],
"id": "fc-ext-wait2",
"name": "Wait 30s"
},
{
"parameters": {
"method": "GET",
"url": "=https://api.firecrawl.dev/v1/extract/{{ $('Start Extract Job').first().json.id }}",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 30000
}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1540,
200
],
"id": "fc-ext-poll2",
"name": "Poll Status (50s)"
},
{
"parameters": {
"jsCode": "const prep = $('Prep Input').first().json;\nconst start = $('Start Extract Job').first().json;\nconst resp = $input.first().json;\n\nconst status = resp.status || 'unknown';\nconst complete = status === 'completed';\nconst data = resp.data || null;\n\n// Lightweight JSON Schema validation (type + required fields only)\nfunction validate(data, schema) {\n const errors = [];\n if (!schema || typeof schema !== 'object') return { valid: true, errors };\n\n const checkType = (val, type) => {\n if (type === 'array') return Array.isArray(val);\n if (type === 'object') return val !== null && typeof val === 'object' && !Array.isArray(val);\n return typeof val === type;\n };\n\n if (schema.type && !checkType(data, schema.type)) {\n errors.push(`Root value expected type ${schema.type}, got ${Array.isArray(data) ? 'array' : typeof data}`);\n }\n if (schema.type === 'object' && Array.isArray(schema.required)) {\n for (const f of schema.required) {\n if (data === null || data === undefined || !(f in data)) {\n errors.push(`Missing required field: ${f}`);\n }\n }\n }\n if (schema.type === 'object' && schema.properties && data && typeof data === 'object') {\n for (const [f, sub] of Object.entries(schema.properties)) {\n if (f in data && sub.type && !checkType(data[f], sub.type)) {\n errors.push(`Field ${f} expected type ${sub.type}, got ${Array.isArray(data[f]) ? 'array' : typeof data[f]}`);\n }\n }\n }\n return { valid: errors.length === 0, errors };\n}\n\nconst validation = validate(data, prep.schema);\nconst credits_used = complete ? (prep.url_count * 5) : 0;\n\nreturn [{ json: {\n status,\n complete,\n job_id: start.id || null,\n data,\n schema_valid: validation.valid,\n validation_errors: validation.errors,\n urls: prep.urls,\n url_count: prep.url_count,\n credits_used,\n note: complete ? undefined : `Extract job still running after ~50s (status: ${status}). Try again or simplify the prompt/schema.`,\n session_id: prep.session_id,\n execution_id: prep.execution_id\n} }];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1760,
100
],
"id": "fc-ext-shape",
"name": "Shape + Validate"
},
{
"parameters": {
"operation": "executeQuery",
"query": "INSERT INTO public.firecrawl_credit_ledger (session_id, execution_id, operation, credits_used, status, metadata)\nVALUES ($1, $2, 'extract', $3, $4, $5::jsonb);",
"options": {
"queryReplacement": "={{ $json.session_id }}, {{ $json.execution_id }}, {{ $json.credits_used }}, {{ $json.complete ? 'ok' : 'partial' }}, {{ JSON.stringify({ status: $json.status, url_count: $json.url_count, schema_valid: $json.schema_valid, validation_errors: $json.validation_errors, job_id: $json.job_id }) }}"
}
},
"type": "n8n-nodes-base.postgres",
"typeVersion": 2.6,
"position": [
1980,
100
],
"id": "fc-ext-ledger",
"name": "Log Credit Ledger"
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "e1",
"name": "status",
"value": "={{ $('Shape + Validate').first().json.status }}",
"type": "string"
},
{
"id": "e2",
"name": "complete",
"value": "={{ $('Shape + Validate').first().json.complete }}",
"type": "boolean"
},
{
"id": "e3",
"name": "data",
"value": "={{ $('Shape + Validate').first().json.data }}",
"type": "object"
},
{
"id": "e4",
"name": "schema_valid",
"value": "={{ $('Shape + Validate').first().json.schema_valid }}",
"type": "boolean"
},
{
"id": "e5",
"name": "validation_errors",
"value": "={{ $('Shape + Validate').first().json.validation_errors }}",
"type": "array"
},
{
"id": "e6",
"name": "credits_used",
"value": "={{ $('Shape + Validate').first().json.credits_used }}",
"type": "number"
},
{
"id": "e7",
"name": "note",
"value": "={{ $('Shape + Validate').first().json.note }}",
"type": "string"
},
{
"id": "e8",
"name": "job_id",
"value": "={{ $('Shape + Validate').first().json.job_id }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
2200,
100
],
"id": "fc-ext-return",
"name": "Return Extract"
}
],
"connections": {
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Prep Input",
"type": "main",
"index": 0
}
]
]
},
"Prep Input": {
"main": [
[
{
"node": "Start Extract Job",
"type": "main",
"index": 0
}
]
]
},
"Start Extract Job": {
"main": [
[
{
"node": "Wait 20s",
"type": "main",
"index": 0
}
]
]
},
"Wait 20s": {
"main": [
[
{
"node": "Poll Status (20s)",
"type": "main",
"index": 0
}
]
]
},
"Poll Status (20s)": {
"main": [
[
{
"node": "IF Completed",
"type": "main",
"index": 0
}
]
]
},
"IF Completed": {
"main": [
[
{
"node": "Shape + Validate",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait 30s",
"type": "main",
"index": 0
}
]
]
},
"Wait 30s": {
"main": [
[
{
"node": "Poll Status (50s)",
"type": "main",
"index": 0
}
]
]
},
"Poll Status (50s)": {
"main": [
[
{
"node": "Shape + Validate",
"type": "main",
"index": 0
}
]
]
},
"Shape + Validate": {
"main": [
[
{
"node": "Log Credit Ledger",
"type": "main",
"index": 0
}
]
]
},
"Log Credit Ledger": {
"main": [
[
{
"node": "Return Extract",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
[FC Sub] Extract Structured Data. Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 12 nodes.
Source: https://github.com/MinaSaad1/n8n-firecrawl-web-crawler-agent/blob/main/workflows/08-sub-extract-structured.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.
[FC Sub] Scrape URL with 24h Cache. Uses executeWorkflowTrigger, postgres, httpRequest. Event-driven trigger; 14 nodes.
Execute Workflow Trigger, Postgres, HTTP Request
[FC Sub] Crawl Site (Bounded). Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 12 nodes.
Execute Workflow Trigger, HTTP Request, Postgres
[FC Sub] Batch Scrape URLs. Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 12 nodes.
Execute Workflow Trigger, HTTP Request, Postgres
[FC Sub] Search the Web. Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 7 nodes.
Execute Workflow Trigger, HTTP Request, Postgres
[FC Sub] Map a Website. Uses executeWorkflowTrigger, httpRequest, postgres. Event-driven trigger; 7 nodes.
Execute Workflow Trigger, HTTP Request, Postgres