Extraction de liens et URL des documents PDF avec PDF.co
Ceci est unDocument Extractionworkflow d'automatisation du domainecontenant 10 nœuds.Utilise principalement des nœuds comme Code, PDFco Api, FormTrigger, HttpRequest. Extraire des liens et URL à partir de documents PDF avec PDF.co
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
Nœuds utilisés (10)
Catégorie
{
"meta": {
"instanceId": "8396a2c42d7edc37401c19b3909f25edcb0e4a6dc3914c824fddd73a329a575c",
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "f6e71b74-1ecb-43e8-baa2-bf05536d01b7",
"name": "Charger PDF",
"type": "n8n-nodes-base.formTrigger",
"position": [
-2224,
-384
],
"webhookId": "a919be0e-e4c8-4b9c-b8e9-b1ffdd6ef9fb",
"parameters": {
"options": {},
"formTitle": "pdf",
"formFields": {
"values": [
{
"fieldType": "file",
"fieldLabel": "data",
"multipleFiles": false,
"acceptFileTypes": ".pdf"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "f24dd98b-b3c4-47f1-8345-10097e53803d",
"name": "Téléverser",
"type": "n8n-nodes-pdfco.PDFco Api",
"position": [
-2016,
-384
],
"parameters": {
"name": "test",
"operation": "Upload File to PDF.co",
"binaryData": true
},
"credentials": {
"pdfcoApi": {
"id": "RgIt0qlGxtcDwXW7",
"name": "PDF.co account"
}
},
"typeVersion": 1
},
{
"id": "b354cde6-5354-4052-9a6c-d66c328a946f",
"name": "PDF vers HTML",
"type": "n8n-nodes-pdfco.PDFco Api",
"position": [
-1776,
-384
],
"parameters": {
"url": "={{ $json.url }}",
"operation": "Convert from PDF",
"advancedOptions": {}
},
"credentials": {
"pdfcoApi": {
"id": "RgIt0qlGxtcDwXW7",
"name": "PDF.co account"
}
},
"typeVersion": 1
},
{
"id": "e15b5c0d-5a46-4faa-828f-25e56cfce322",
"name": "Obtenir HTML",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1568,
-384
],
"parameters": {
"url": "={{ $json.url }}",
"options": {}
},
"typeVersion": 4.2
},
{
"id": "73506c94-6265-4d89-b386-e908285d14e0",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2288,
-448
],
"parameters": {
"width": 208,
"height": 240,
"content": "## Load PDF\n"
},
"typeVersion": 1
},
{
"id": "6d23ab8a-5bae-4317-b73e-fb1b2ba8ff16",
"name": "Note adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2080,
-448
],
"parameters": {
"color": 2,
"height": 240,
"content": "## Upload to PDF.CO \n"
},
"typeVersion": 1
},
{
"id": "72be2279-3028-4c24-8973-00879cff375a",
"name": "Note adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1840,
-448
],
"parameters": {
"color": 4,
"width": 224,
"height": 240,
"content": "## PDF to HTML"
},
"typeVersion": 1
},
{
"id": "cebf4aeb-549c-4c9e-84eb-41d880834fb5",
"name": "Note adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1616,
-448
],
"parameters": {
"width": 192,
"height": 240,
"content": "## Get HTML"
},
"typeVersion": 1
},
{
"id": "8f6d9763-dece-45f6-a78b-1b5f6891f2fa",
"name": "Code1",
"type": "n8n-nodes-base.code",
"position": [
-1360,
-384
],
"parameters": {
"jsCode": "// Recorrer todos los items que entran al nodo\nconst resultados = [];\n\nfor (const item of $input.all()) {\n const texto = item.json.data || '';\n // Regex para URLs (http, https, www)\n const regexUrl = /(https?:\\/\\/[^\\s]+)|(www\\.[^\\s]+)/gi;\n \n // Extraer URLs, si no hay ninguna, el resultado es []\n const urls = texto.match(regexUrl) || [];\n \n // Por cada URL encontrada, crear un nuevo item con la URL\n for (const url of urls) {\n resultados.push({ json: { url } });\n }\n}\n\n// Devolver un array de objetos con las URLs extraídas\nreturn resultados;\n"
},
"typeVersion": 2
},
{
"id": "0c49f98f-0b3c-4c47-ad34-b60b02c5f3a5",
"name": "Note adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1424,
-448
],
"parameters": {
"color": 5,
"width": 208,
"height": 240,
"content": "## Get URL's \n"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"f24dd98b-b3c4-47f1-8345-10097e53803d": {
"main": [
[
{
"node": "b354cde6-5354-4052-9a6c-d66c328a946f",
"type": "main",
"index": 0
}
]
]
},
"e15b5c0d-5a46-4faa-828f-25e56cfce322": {
"main": [
[
{
"node": "8f6d9763-dece-45f6-a78b-1b5f6891f2fa",
"type": "main",
"index": 0
}
]
]
},
"f6e71b74-1ecb-43e8-baa2-bf05536d01b7": {
"main": [
[
{
"node": "f24dd98b-b3c4-47f1-8345-10097e53803d",
"type": "main",
"index": 0
}
]
]
},
"b354cde6-5354-4052-9a6c-d66c328a946f": {
"main": [
[
{
"node": "e15b5c0d-5a46-4faa-828f-25e56cfce322",
"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 - 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
Mauricio Perera
@rckflrAutomation consultant with over 10 years of experience specializing in AI, no-code, and workflow optimization. I’ve delivered tailored AI and NLP solutions across real estate, healthcare, and more, enhancing efficiency and customer experiences. Proficient in tools like Make, Airtable, and Zapier, I also integrate GPT models to create scalable, innovative automations. Contact me to discuss custom n8n workflows or advanced automations to streamline your processes.
Partager ce workflow