Crawler intelligent quotidien automatisé avec Firecrawl
Ceci est unMarket Research, AI Summarizationworkflow d'automatisation du domainecontenant 14 nœuds.Utilise principalement des nœuds comme If, Set, Wait, Telegram, HttpRequest. Extraction quotidienne de données de site web : Firecrawl et alertes Telegram
- •Token Bot Telegram
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
Nœuds utilisés (14)
Catégorie
{
"id": "B8QZbtbhTEZne8nq",
"meta": {
"instanceId": "1c7b08fed4406d546caf4a44e8b942ca317e7e207bb9a5701955a1a6e1ce1843",
"templateCredsSetupCompleted": true
},
"name": "Automated Daily Intelligent Firecrawl Scraper",
"tags": [],
"nodes": [
{
"id": "d456e62d-f6ce-47c4-9be1-a3b3725e340f",
"name": "Extraire",
"type": "n8n-nodes-base.httpRequest",
"position": [
-480,
-100
],
"parameters": {
"url": "https://api.firecrawl.dev/v1/extract",
"method": "POST",
"options": {},
"jsonBody": "={\n \"urls\": [\n \"https://www.website.com\"\n ],\n \"prompt\": \"Extract the [insert] information from the page\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"notable_trades\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"congress_member_name\": {\n \"type\": \"string\"\n },\n \"party\": {\n \"type\": \"string\"\n },\n \"stock_or_asset\": {\n \"type\": \"string\"\n },\n \"amount\": {\n \"type\": \"number\"\n },\n \"transaction_date\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"congress_member_name\",\n \"stock_or_asset\",\n \"amount\",\n \"transaction_date\"\n ]\n }\n }\n },\n \"required\": [\n \"notable_trades\"\n ]\n }\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "758d7a3f-555d-4957-bf92-d24b6ab018e8",
"name": "Obtenir les Résultats",
"type": "n8n-nodes-base.httpRequest",
"position": [
40,
-120
],
"parameters": {
"url": "=https://api.firecrawl.dev/v1/extract/{{ $('Extract').item.json.id }}",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "9ded421d-cde6-4c6d-9ebc-3315ee79d30e",
"name": "Modifier les Champs",
"type": "n8n-nodes-base.set",
"position": [
500,
-120
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "4188c94f-170b-4f42-8197-675f171bc1a5",
"name": "data",
"type": "string",
"value": "={{ $json.trades }}"
}
]
},
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "9b799432-7fa5-4fa4-a960-fe03b8882263",
"name": "Déclencheur Planifié",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-740,
-100
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 18
}
]
}
},
"typeVersion": 1.2
},
{
"id": "505faec2-734d-40ac-a832-1a926a77f520",
"name": "Si",
"type": "n8n-nodes-base.if",
"position": [
220,
-120
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "6d815b2e-1717-4d52-a30d-74e17a84f0f3",
"operator": {
"type": "array",
"operation": "empty",
"singleValue": true
},
"leftValue": "={{ $json.trades }}",
"rightValue": "[empty array]"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "f8ff331e-363b-42eb-9472-e397b3d56691",
"name": "30 Secondes",
"type": "n8n-nodes-base.wait",
"position": [
-200,
-100
],
"webhookId": "282bb09d-3241-4022-87fa-0b342ccd124a",
"parameters": {
"amount": 30
},
"typeVersion": 1.1
},
{
"id": "e9bd3c21-8a89-424f-9a6e-4d00d6fd87ae",
"name": "Attendre 15 secondes",
"type": "n8n-nodes-base.wait",
"position": [
280,
40
],
"webhookId": "4d1cade1-aa5f-44ab-a65c-ac3693f4cf4a",
"parameters": {
"amount": 15
},
"typeVersion": 1.1
},
{
"id": "aae6f1ba-e4d4-4545-95cc-71f40e690b9b",
"name": "Note Adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-560,
-260
],
"parameters": {
"color": 3,
"width": 280,
"height": 520,
"content": "Firecrawl Extract POST"
},
"typeVersion": 1
},
{
"id": "29b3688f-0fb0-486c-89cd-550a59299225",
"name": "Note Adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-840,
-260
],
"parameters": {
"width": 260,
"height": 520,
"content": "Scheduled Trigger"
},
"typeVersion": 1
},
{
"id": "ac14b7cf-48ad-4029-a173-331b2d2ad1c6",
"name": "Note Adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-260,
-260
],
"parameters": {
"color": 7,
"width": 220,
"height": 520,
"content": "Wait 30 secs"
},
"typeVersion": 1
},
{
"id": "34cea142-3592-439d-9238-a25e4c4e7cc1",
"name": "Note Adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-20,
-260
],
"parameters": {
"color": 5,
"width": 480,
"height": 520,
"content": "GET Result Loop"
},
"typeVersion": 1
},
{
"id": "f8c71a46-4b99-4079-b895-63e7a5811dcd",
"name": "Note Adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
-260
],
"parameters": {
"color": 5,
"width": 400,
"height": 520,
"content": "Send Result to Telegram"
},
"typeVersion": 1
},
{
"id": "4ea94358-34cd-421e-ad57-5277dbe03aee",
"name": "Telegram",
"type": "n8n-nodes-base.telegram",
"position": [
660,
-120
],
"webhookId": "cee700e9-03aa-484e-b2fb-06dd7abef48f",
"parameters": {
"text": "={{ $json.data }}",
"chatId": "Redacted",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "7653b3ac-3210-4c89-a2ff-70034c2f4560",
"name": "Note Adhésive5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1600,
-260
],
"parameters": {
"color": 5,
"width": 700,
"height": 1060,
"content": "🔥 Automated Daily Firecrawl Scraper with Telegram Alerts\nGet structured insights scraped daily from the web using Firecrawl’s AI extraction engine — then send them directly to your Telegram chat.\n\n🧰 What this workflow does:\nThis workflow automatically scrapes specific structured data from any webpage every day at a scheduled time using the Firecrawl API, checks if results are returned, and then sends the formatted results to Telegram.\n\nFor step-by-step video tutorials of n8n builds, check out my channel:\nhttps://www.youtube.com/@Automatewithmarc\n\n🧭 How It Works:\n🕐 Schedule Trigger (Daily at 6PM)\nStarts the workflow every day at a set time.\n\n🌐 Firecrawl POST Request\nSends a custom extraction prompt and schema to Firecrawl, targeting any list of URLs you provide.\n\n⏳ 30 Seconds Wait\nWaits to give Firecrawl enough time to complete processing.\n\n📥 GET Firecrawl Result\nFetches the extraction results using the request ID.\n\n🔁 Loop with IF Node\nChecks whether data is returned. If not, waits another 15 seconds and retries.\n\n🧹 Format & Clean (Set Node)\nPrepares and formats the extracted result into a readable message.\n\n📲 Telegram Message Node\nDelivers the structured data directly to your Telegram channel or group.\n\n🔧 Requirements:\n✅ Firecrawl API Key (Header Auth)\n\n✅ Telegram Bot Token & Chat ID\n\n💡 Use Cases:\nExtract structured data (like product info or events) from niche websites\nAutomate compliance monitoring or intelligence gathering\nCreate market alert bots with real-time info delivery\n\n🛠 Customization Ideas:\nSwap Telegram with Gmail, Discord, or Slack\n\nExpand schema to include more complex nested fields\n\nAdd a Google Sheet node to log daily scraped data\n\nIntegrate with a summarizer or language model for intelligent summaries\n\nReady to automate your web intelligence gathering?\n🧠 Let Firecrawl do the scraping — and let this workflow do the rest."
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "40ed9017-f78f-4446-8b36-2a0a06f14add",
"connections": {
"505faec2-734d-40ac-a832-1a926a77f520": {
"main": [
[
{
"node": "e9bd3c21-8a89-424f-9a6e-4d00d6fd87ae",
"type": "main",
"index": 0
}
],
[
{
"node": "9ded421d-cde6-4c6d-9ebc-3315ee79d30e",
"type": "main",
"index": 0
}
]
]
},
"f8ff331e-363b-42eb-9472-e397b3d56691": {
"main": [
[
{
"node": "758d7a3f-555d-4957-bf92-d24b6ab018e8",
"type": "main",
"index": 0
}
]
]
},
"d456e62d-f6ce-47c4-9be1-a3b3725e340f": {
"main": [
[
{
"node": "f8ff331e-363b-42eb-9472-e397b3d56691",
"type": "main",
"index": 0
}
]
]
},
"9ded421d-cde6-4c6d-9ebc-3315ee79d30e": {
"main": [
[
{
"node": "4ea94358-34cd-421e-ad57-5277dbe03aee",
"type": "main",
"index": 0
}
]
]
},
"758d7a3f-555d-4957-bf92-d24b6ab018e8": {
"main": [
[
{
"node": "505faec2-734d-40ac-a832-1a926a77f520",
"type": "main",
"index": 0
}
]
]
},
"e9bd3c21-8a89-424f-9a6e-4d00d6fd87ae": {
"main": [
[
{
"node": "758d7a3f-555d-4957-bf92-d24b6ab018e8",
"type": "main",
"index": 0
}
]
]
},
"9b799432-7fa5-4fa4-a960-fe03b8882263": {
"main": [
[
{
"node": "d456e62d-f6ce-47c4-9be1-a3b3725e340f",
"type": "main",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Étude de marché, Résumé IA
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Automate With Marc
@marconiAutomating Start-Up and Business processes. Helping non-techies understand and leverage Agentic AI with easy to understand step-by-step tutorials. Check out my educational content: https://www.youtube.com/@Automatewithmarc
Partager ce workflow