Web Reader
Intermédiaire
Ceci est unDocument Extractionworkflow d'automatisation du domainecontenant 15 nœuds.Utilise principalement des nœuds comme If, Set, HttpRequest, StopAndError, ExecuteWorkflowTrigger. Extraire un contenu web propre pour les agents IA et les workflows, avec des solutions de contournement anti-scraping
Prérequis
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
Nœuds utilisés (15)
Catégorie
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
"id": "9UyGvrk6EDY6Hm3W",
"meta": {
"instanceId": "7e84375f1a5a2398bff60c3e83bb370423dae55c261ed7c48ca02f15548655a7",
"templateCredsSetupCompleted": true
},
"name": "WebPage-Reader",
"tags": [],
"nodes": [
{
"id": "f449a425-4ae9-462d-91bb-ff0b85a73202",
"name": "Extracteur de Contenu",
"type": "n8n-nodes-webpage-content-extractor.webpageContentExtractor",
"position": [
940,
100
],
"parameters": {
"html": "={{ $json.data }}"
},
"typeVersion": 1
},
{
"id": "e52eddc5-72a7-4bd8-8679-ecedccad447c",
"name": "Essayer Contournement Antibot",
"type": "n8n-nodes-base.if",
"position": [
280,
180
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "1351d4e8-1c27-43c2-8335-aee7c097422a",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.error.code }}",
"rightValue": "ECONNABORTED"
},
{
"id": "28a4c2eb-0a9b-44ac-87d5-6571be2fb447",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.error.code }}",
"rightValue": "ETIMEDOUT"
},
{
"id": "1287e08b-a342-4651-8e56-1d1ff4677222",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.error.code }}",
"rightValue": "ERR_CANCELED"
},
{
"id": "45256daa-063f-4ed3-8ef0-5ec91cdc0974",
"operator": {
"name": "filter.operator.equals",
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.error.code }}",
"rightValue": "ERR_BAD_REQUEST"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "a90654b8-b83b-41ed-a665-9a0303a84de3",
"name": "Scrape.do",
"type": "n8n-nodes-base.httpRequest",
"position": [
500,
180
],
"parameters": {
"url": "=http://api.scrape.do",
"options": {
"timeout": 120000
},
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "httpQueryAuth",
"queryParameters": {
"parameters": [
{
"name": "url",
"value": "={{ $json.url }}"
}
]
}
},
"credentials": {
"httpQueryAuth": {
"id": "SMKkxhdbOewTAnqe",
"name": "Scrape.do account"
}
},
"retryOnFail": true,
"typeVersion": 4.2,
"waitBetweenTries": 5000
},
{
"id": "62c1fb07-35e0-4942-b38d-b888b559e109",
"name": "Erreur Serveur",
"type": "n8n-nodes-base.stopAndError",
"position": [
500,
380
],
"parameters": {
"errorMessage": "=Error requesting website ({{ $json.error.code }})"
},
"typeVersion": 1
},
{
"id": "7e793496-3ba7-4a30-bb6c-d483c00671c6",
"name": "Pas 404",
"type": "n8n-nodes-base.if",
"position": [
60,
180
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "81558598-6188-4712-962c-3f80fcba1297",
"operator": {
"type": "number",
"operation": "notEquals"
},
"leftValue": "={{ $json.error.status }}",
"rightValue": 404
}
]
}
},
"typeVersion": 2.2
},
{
"id": "9ae25973-ffa0-4b14-943b-d8a9fa0ee3b0",
"name": "Non Trouvé",
"type": "n8n-nodes-base.stopAndError",
"position": [
280,
380
],
"parameters": {
"errorMessage": "=Error requesting website (404)"
},
"typeVersion": 1
},
{
"id": "8af2bbee-ebd0-49e2-aa4a-bc58e1ccaf31",
"name": "Scraper Simple",
"type": "n8n-nodes-base.httpRequest",
"onError": "continueErrorOutput",
"position": [
-160,
120
],
"parameters": {
"url": "={{ $json.url }}",
"options": {
"timeout": 10000,
"redirect": {
"redirect": {}
},
"allowUnauthorizedCerts": true
},
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "User-Agent",
"value": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36"
}
]
}
},
"retryOnFail": true,
"typeVersion": 4.2,
"waitBetweenTries": 5000
},
{
"id": "f0f8106a-9a8c-492e-8082-fc82a3852765",
"name": "Texte Intégral",
"type": "n8n-nodes-base.if",
"position": [
1160,
100
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "b32569d1-ba84-401f-9dc9-99b2c804cba2",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $('Workflow Call').item.json.fulltext }}",
"rightValue": ""
}
]
}
},
"typeVersion": 2.2
},
{
"id": "325b73df-6fe0-4c22-985e-0916a09a8865",
"name": "Sortie Texte Intégral",
"type": "n8n-nodes-base.set",
"position": [
1380,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "91a15268-86a9-4390-9e19-9fba4d21aeed",
"name": "title",
"type": "string",
"value": "={{ $json.title.replace(/\\p{Extended_Pictographic}/gu, '') }}"
},
{
"id": "90d16e3d-49ca-4a65-a4ae-cd689de990db",
"name": "text",
"type": "string",
"value": "={{\n( $json.textContent || '' )\n.replace(/\\p{Extended_Pictographic}/gu, '')\n.replace(/[\\r\\n]+/g, ' ')\n.replace(/\\s+/g, ' ')\n.trim()\n}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "32e88e32-0068-47de-8f72-aee167f15ca2",
"name": "Sortie Résumé",
"type": "n8n-nodes-base.set",
"position": [
1380,
200
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "91a15268-86a9-4390-9e19-9fba4d21aeed",
"name": "title",
"type": "string",
"value": "={{ $json.title.replace(/\\p{Extended_Pictographic}/gu, '') }}"
},
{
"id": "28476e01-485e-4373-a6c3-b3703d4ba1e4",
"name": "url",
"type": "string",
"value": "={{ $('Workflow Call').item.json.url }}"
},
{
"id": "90d16e3d-49ca-4a65-a4ae-cd689de990db",
"name": "content",
"type": "string",
"value": "={{\n( $json.excerpt || '' )\n.replace(/\\p{Extended_Pictographic}/gu, '')\n.replace(/[\\r\\n]+/g, ' ')\n.replace(/\\s+/g, ' ')\n.trim()\n}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "96438bb1-1918-4ae6-9a40-0624968ca7b3",
"name": "Est Binaire",
"type": "n8n-nodes-base.if",
"position": [
720,
0
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8255ef66-f18d-4f38-a283-592cbd617109",
"operator": {
"type": "object",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $binary.data }}",
"rightValue": ".pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "5bb977be-3e50-4240-a05a-4df23e8f7470",
"name": "Erreur TypeContenu",
"type": "n8n-nodes-base.stopAndError",
"position": [
940,
-80
],
"parameters": {
"errorMessage": "=Unsupported content-type"
},
"typeVersion": 1
},
{
"id": "7b68057e-9189-4291-a40f-e9941443a65a",
"name": "Appel Workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
-380,
120
],
"parameters": {
"workflowInputs": {
"values": [
{
"name": "url"
},
{
"name": "fulltext",
"type": "boolean"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "bbe6563d-1131-4f7e-9a19-0dff16d1adb5",
"name": "Note Adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1200,
-100
],
"parameters": {
"width": 760,
"height": 640,
"content": "# WebPage Reader for AI Agents & Workflows\n\nThis sub-workflow enables reliable and clean scraping of any public webpage by simply passing a **url** parameter. It is designed to be embedded into other workflows or used as a tool for AI agents.\n\n🧩 This template requires the [n8n-nodes-webpage-content-extractor](https://www.npmjs.com/package/n8n-nodes-webpage-content-extractor) community node, so it only works in self-hosted n8n environments.\n\n💡 If the site is protected by anti-bot systems (like Cloudflare), it will automatically fallback to [Scrape.do](https://scrape.do/), a scraping API with a generous free plan. You only need to provide your API Token.\n\n## Input Parameters:\n- **url** (string): the webpage URL to scrape\n- **fulltext** (boolean): set true for full page content, false for summarized output\n\n## Output Modes:\n- **fulltext: true** — returns *{ title, text }* with full page content\n- **fulltext: false** — returns *{ title, url, content }* with a short excerpt\n\n## Usage:\nIn your workflows you can invoke this workflow using the **Execute Sub-workflow** or **Call n8n Workflow Tool** nodes.\nRemember to pass the url as a parameter and configure the fulltext option when invoking it.\n\n\n*(See the Setup note for instructions on how to set up this workflow.)*"
},
"typeVersion": 1
},
{
"id": "cf3a4e8f-d63f-482d-81eb-746ed7f66c85",
"name": "Note Adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1600,
-100
],
"parameters": {
"width": 680,
"height": 660,
"content": "# Setup\nTo set up this workflow you will need to install the [n8n-nodes-webpage-content-extractor](https://www.npmjs.com/package/n8n-nodes-webpage-content-extractor) community node and API Token from your [Scrape.do](https://scrape.do/) account. Then you will just need to configure the `Scrape.do` node here with your credentials.\n\n## Community Node Installation\nBefore importing this workflow you first need to install this node on your n8n.\n- Go to your n8n's settings page. By clicking on the three dots next to your username in the bottom left corner of the screen.\n- In the left side menu click on Community Nodes.\n- Now click on the Install button.\n- In the npm Package Name field enter **n8n-nodes-webpage-content-extractor**, check the box that says *I understand the risks of installing unverified code from a public source*, and then click the Install button.\n\n## `Scrape.do` Node Setup\nBefore configuring the node, create your account on [Scrape.do](https://scrape.do/) and save your API Token\n- Open the Node `Scrape.do` configuration window by double-clicking on it.\n- In the **Authentication** field, select the **Generic Credential Type** option.\n- In the **Generic Credential Type** field below select the **Query Auth** option\n- In the **Query Auth** field below select **Create new credential**. To save your token to a new n8n credential.\n- In the window that opens, in the **Name** field, enter the word **token** only. In the **Value** field, paste your **API Token**. Then click the Save button.\n\n\n\n**Your workflow is ready! You can now use it in your workflows and in your AI Agents!**"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {},
"settings": {
"callerPolicy": "workflowsFromSameOwner",
"errorWorkflow": "4HcJPFvOCSd7pZeG",
"executionOrder": "v1",
"saveDataSuccessExecution": "none"
},
"versionId": "8cc14be0-b5b6-41c3-8838-e92591538965",
"connections": {
"7e793496-3ba7-4a30-bb6c-d483c00671c6": {
"main": [
[
{
"node": "e52eddc5-72a7-4bd8-8679-ecedccad447c",
"type": "main",
"index": 0
}
],
[
{
"node": "9ae25973-ffa0-4b14-943b-d8a9fa0ee3b0",
"type": "main",
"index": 0
}
]
]
},
"f0f8106a-9a8c-492e-8082-fc82a3852765": {
"main": [
[
{
"node": "325b73df-6fe0-4c22-985e-0916a09a8865",
"type": "main",
"index": 0
}
],
[
{
"node": "32e88e32-0068-47de-8f72-aee167f15ca2",
"type": "main",
"index": 0
}
]
]
},
"96438bb1-1918-4ae6-9a40-0624968ca7b3": {
"main": [
[
{
"node": "5bb977be-3e50-4240-a05a-4df23e8f7470",
"type": "main",
"index": 0
}
],
[
{
"node": "f449a425-4ae9-462d-91bb-ff0b85a73202",
"type": "main",
"index": 0
}
]
]
},
"a90654b8-b83b-41ed-a665-9a0303a84de3": {
"main": [
[
{
"node": "96438bb1-1918-4ae6-9a40-0624968ca7b3",
"type": "main",
"index": 0
}
]
]
},
"7b68057e-9189-4291-a40f-e9941443a65a": {
"main": [
[
{
"node": "8af2bbee-ebd0-49e2-aa4a-bc58e1ccaf31",
"type": "main",
"index": 0
}
]
]
},
"8af2bbee-ebd0-49e2-aa4a-bc58e1ccaf31": {
"main": [
[
{
"node": "96438bb1-1918-4ae6-9a40-0624968ca7b3",
"type": "main",
"index": 0
}
],
[
{
"node": "7e793496-3ba7-4a30-bb6c-d483c00671c6",
"type": "main",
"index": 0
}
]
]
},
"f449a425-4ae9-462d-91bb-ff0b85a73202": {
"main": [
[
{
"node": "f0f8106a-9a8c-492e-8082-fc82a3852765",
"type": "main",
"index": 0
}
]
]
},
"e52eddc5-72a7-4bd8-8679-ecedccad447c": {
"main": [
[
{
"node": "a90654b8-b83b-41ed-a665-9a0303a84de3",
"type": "main",
"index": 0
}
],
[
{
"node": "62c1fb07-35e0-4942-b38d-b888b559e109",
"type": "main",
"index": 0
}
]
]
}
}
}Foire aux questions
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 - Extraction de documents
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
PDF vers commande
Utiliser l'IA pour automatiser la conversion des commandes d'achat PDF en commandes de vente Adobe Commerce
If
Set
Code
+
If
Set
Code
96 NœudsJKingma
Extraction de documents
Modèle d'agent documentaire
Créer des documents PDF personnalisés à partir de modèles avec Gemini et Google Drive
If
Set
Code
+
If
Set
Code
36 NœudsOzgur Karateke
Extraction de documents
AIe-mail分诊与GPT-4警报系统及Telegramnotification
AIe-mail分诊与GPT-4警报系统及Telegramnotification
If
Set
Gmail
+
If
Set
Gmail
104 NœudsPeter Joslyn
Support
Créer des vidéos IA en utilisant des scripts OpenAI, des images Leonardo et des avatars HeyGen
Créer des vidéos IA avec des scripts OpenAI, des images Leonardo et des avatars HeyGen
If
Set
Code
+
If
Set
Code
68 NœudsAdam Crafts
Design
Créer des vidéos IA en utilisant des scripts, des images et des avatars HeyGen (🔥Offre limitée)
Créer des vidéos IA avec des scripts, des images et des avatars HeyGen (🔥 Offre limitée)
If
Set
Code
+
If
Set
Code
68 NœudsAdam Crafts
Design
1. Configuration du robot pour les détails de la playlist
Créer des playlists de musique YouTube générées par l'IA avec Suno, GPT-4, Runway et Creatomate
If
Set
Code
+
If
Set
Code
203 NœudsJoseph
Création de contenu
Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds15
Catégorie1
Types de nœuds7
Description de la difficulté
Auteur
Liens externes
Voir sur n8n.io →
Partager ce workflow