Usa Dumpling AI para extraer contenido de blogs de sitios web y guardarlo en Google Sheets
Intermedio
Este es unMarket Research, Multimodal AIflujo de automatización del dominio deautomatización que contiene 11 nodos.Utiliza principalmente nodos como Set, Code, FormTrigger, HttpRequest, GoogleSheets. Usa Dumpling AI para extraer contenido de blogs de sitios web y guardarlo en Google Sheets
Requisitos previos
- •Pueden requerirse credenciales de autenticación para la API de destino
- •Credenciales de API de Google Sheets
Nodos utilizados (11)
Vista previa del flujo de trabajo
Visualización de las conexiones entre nodos, con soporte para zoom y panorámica
Exportar flujo de trabajo
Copie la siguiente configuración JSON en n8n para importar y usar este flujo de trabajo
{
"id": "VPtrkEUaljkq5VtD",
"meta": {
"instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
"templateCredsSetupCompleted": true
},
"name": "Crawl Website Blog Content and Save to Google Sheets with Dumpling AI",
"tags": [],
"nodes": [
{
"id": "b9be7abb-d02c-4383-b18d-e40f77f833bf",
"name": "Envío de Formulario",
"type": "n8n-nodes-base.formTrigger",
"position": [
-112,
0
],
"webhookId": "75c29ccf-8a5d-4d8c-95ca-74a838257011",
"parameters": {
"options": {},
"formTitle": "blog content strategy",
"formFields": {
"values": [
{
"fieldLabel": "Client URL",
"requiredField": true
}
]
}
},
"typeVersion": 2.2
},
{
"id": "e4c0b49d-ec38-4357-ad7c-bb47145b0cd5",
"name": "Crear Hoja de Auditoría de Blog",
"type": "n8n-nodes-base.googleSheets",
"position": [
112,
0
],
"parameters": {
"title": "={{ $json[\"Client URL\"].trim().split(/›|>|»/)[0].trim().split(\".\")[0] }}",
"options": {},
"resource": "spreadsheet",
"sheetsUi": {
"sheetValues": [
{
"title": "Blog content audit"
}
]
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GaJqJHuS5mQxap7q",
"name": "Google Sheets account"
}
},
"typeVersion": 4.6
},
{
"id": "1138d43b-14bb-4f9c-a6dc-f82cc965e5c4",
"name": "Establecer Encabezados de Hoja",
"type": "n8n-nodes-base.set",
"position": [
336,
0
],
"parameters": {
"values": {
"string": [
{
"name": "rows",
"value": "Url,Crawled_pages,website_content"
}
]
},
"options": {}
},
"typeVersion": 1
},
{
"id": "3630f64c-a9df-4c18-a668-822b5d0aed00",
"name": "Formatear Fila de Encabezado",
"type": "n8n-nodes-base.code",
"position": [
560,
0
],
"parameters": {
"jsCode": "return [\n {\n json: {\n data: [ $json.rows.split(',') ]\n }\n }\n];\n\n"
},
"typeVersion": 2
},
{
"id": "171ecc40-447d-4a64-adc8-f0d38d1d9cdf",
"name": "Insertar Encabezados en Hoja",
"type": "n8n-nodes-base.httpRequest",
"position": [
784,
0
],
"parameters": {
"url": "=https://sheets.googleapis.com/v4/spreadsheets/{{ $('Create Blog Audit Sheet').first().json.spreadsheetId }}/values/{{ $('Create Blog Audit Sheet').first().json.sheets[0].properties.title }}!A:Z",
"method": "PUT",
"options": {},
"sendBody": true,
"sendQuery": true,
"authentication": "predefinedCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "range",
"value": "={{ $('Create Blog Audit Sheet').first().json.sheets[0].properties.title }}!A:Z"
},
{
"name": "values",
"value": "={{ $json.data }}"
}
]
},
"queryParameters": {
"parameters": [
{
"name": "valueInputOption",
"value": "RAW"
}
]
},
"nodeCredentialType": "googleSheetsOAuth2Api"
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GaJqJHuS5mQxap7q",
"name": "Google Sheets account"
}
},
"typeVersion": 4.1
},
{
"id": "a1b24d76-a502-409a-b310-d4d3cc5e7c9a",
"name": "Dumpling AI: Rastrear Sitio Web",
"type": "n8n-nodes-base.httpRequest",
"position": [
1008,
0
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/crawl",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "url",
"value": "={{ $('Form Submission ').item.json[\"Client URL\"] }}"
},
{
"name": "limit",
"value": "=10"
}
]
},
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "bf50d679-1f16-4811-9e20-99eaccd9fc44",
"name": "Extraer URLs de Blogs",
"type": "n8n-nodes-base.code",
"position": [
1232,
0
],
"parameters": {
"jsCode": "// Get all input items\nconst items = $input.all();\n\n// Convert everything to a string for searching\nconst fullDataString = JSON.stringify(items);\n\n// Find ALL URLs in the content\nconst urlPattern = /https?:\\/\\/[^\\s\\\"\\'<>\\(\\)\\[\\]]+/gi;\nconst allUrls = fullDataString.match(urlPattern) || [];\n\n// Clean and deduplicate URLs\nlet uniqueUrls = [...new Set(allUrls.map(url => \n url.replace(/[\\(\\)\\[\\]\\\"\\'<>\\\\]/g, '').trim()\n))];\n\n// Function to determine if a URL might be a blog post\nfunction isPotentialBlogPost(url) {\n // Common blog URL patterns\n const blogPatterns = [\n /\\/blog\\//i,\n /\\/post\\//i,\n /\\/posts\\//i,\n /\\/article\\//i,\n /\\/articles\\//i,\n /\\/news\\//i,\n /\\/insights\\//i,\n /\\/stories\\//i,\n /\\/resources\\/blog/i,\n /\\/\\d{4}\\/\\d{2}\\//,\n /\\/how-to-/i,\n /\\/guide-to-/i,\n /\\/tips/i,\n /\\/free-printable-art/i\n ];\n \n // Exclude patterns\n const excludePatterns = [\n /\\.(jpg|jpeg|png|gif|svg|css|js|pdf|zip)$/i,\n /\\/wp-content\\//i,\n /\\/cart\\//i,\n /\\/checkout/i,\n /\\/product\\//i,\n /\\/shop\\//i,\n /\\?add-to-cart=/i,\n /\\/my-account/i,\n /\\/collections?\\//i\n ];\n \n // Check excludes first\n for (const pattern of excludePatterns) {\n if (pattern.test(url)) {\n return false;\n }\n }\n \n // Check blog patterns\n for (const pattern of blogPatterns) {\n if (pattern.test(url)) {\n return true;\n }\n }\n \n return false;\n}\n\n// Filter URLs\nconst blogUrls = uniqueUrls.filter(url => url.includes('/blog'));\nconst potentialBlogPosts = uniqueUrls.filter(isPotentialBlogPost);\n\n// Combine and deduplicate\nconst allBlogRelatedUrls = [...new Set([...blogUrls, ...potentialBlogPosts])];\n\n// Sort URLs\nallBlogRelatedUrls.sort();\n\n// Return results\nif (allBlogRelatedUrls.length > 0) {\n return allBlogRelatedUrls.map(url => ({\n json: {\n blogUrl: url\n }\n }));\n} else {\n return [{\n json: {\n message: \"No blog URLs found\",\n totalUrlsChecked: uniqueUrls.length\n }\n }];\n}"
},
"typeVersion": 2
},
{
"id": "cf4d1e28-6dd4-46f5-bdde-6882b9bc59d9",
"name": "Dumpling AI: Extraer Páginas de Blog",
"type": "n8n-nodes-base.httpRequest",
"position": [
1456,
0
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/scrape",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "url",
"value": "={{ $json.blogUrl }}"
}
]
},
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "d5135eaa-34f2-4d9e-afa9-5dd4a98b658b",
"name": "Preparar Datos de Fila",
"type": "n8n-nodes-base.set",
"position": [
1680,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "ce53a00e-e3ff-49b8-a867-2b2005655946",
"name": "Url",
"type": "string",
"value": "={{ $('Form Submission ').item.json[\"Client URL\"] }}"
},
{
"id": "8d2cc248-a6da-44a2-a22a-865e13f9d15c",
"name": "Crawled_pages",
"type": "string",
"value": "={{ $('Extract Blog URLs').item.json.blogUrl }}"
},
{
"id": "4a3c75d6-fa9e-4cb5-84b0-3fb33f38bd45",
"name": "website_content",
"type": "string",
"value": "={{ $json.content }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7fb2c810-f438-48af-a075-29e514d6855c",
"name": "Guardar Datos del Blog en Google Sheets",
"type": "n8n-nodes-base.googleSheets",
"position": [
1904,
0
],
"parameters": {
"columns": {
"value": {},
"schema": [
{
"id": "Url",
"type": "string",
"display": true,
"required": false,
"displayName": "Url",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Crawled_pages",
"type": "string",
"display": true,
"required": false,
"displayName": "Crawled_pages",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "website_content",
"type": "string",
"display": true,
"required": false,
"displayName": "website_content",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "autoMapInputData",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "id",
"value": "={{ $('Create Blog Audit Sheet').item.json.sheets[0].properties.sheetId }}"
},
"documentId": {
"__rl": true,
"mode": "url",
"value": "={{ $('Create Blog Audit Sheet').item.json.spreadsheetUrl }}"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "GaJqJHuS5mQxap7q",
"name": "Google Sheets account"
}
},
"typeVersion": 4.7
},
{
"id": "bbd3cb7c-b1a5-4919-8617-9050dabdde20",
"name": "Nota Adhesiva",
"type": "n8n-nodes-base.stickyNote",
"position": [
-128,
-304
],
"parameters": {
"width": 880,
"height": 448,
"content": "## Workflow Overview\n\n1. **Trigger: Form Submission (Client URL)** — Starts the workflow when a client URL is entered. \n2. **Create Blog Audit Sheet** — Creates a new Google Sheet for the audit. \n3. **Set Sheet Headers** — Defines the columns (URL, Crawled Pages, Website Content). \n4. **Format Header Row** — Prepares the headers into the right format for Google Sheets. \n5. **Insert Headers into Sheet** — Updates the sheet with the headers. \n6. **Dumpling AI: Crawl Website** — Crawls the submitted URL to discover pages. \n7. **Extract Blog URLs** — Filters the crawl results to keep only blog-related links. \n8. **Dumpling AI: Scrape Blog Pages** — Scrapes the content from each blog page. \n9. **Prepare Row Data** — Maps the URL, crawled page, and content into structured fields. \n10. **Save Blog Data to Google Sheets** — Appends the results into the audit sheet for review.\n\n"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {
"Form Submission ": [
{
"json": {
"formMode": "test",
"Client URL": "https://crane-baby.com/",
"submittedAt": "2025-08-23T19:14:17.927+10:00"
}
}
],
"Extract Blog URLs": [
{
"json": {
"blogUrl": "https://crane-baby.com/blog"
}
},
{
"json": {
"blogUrl": "https://crane-baby.com/blog/"
}
},
{
"json": {
"blogUrl": "https://crane-baby.com/free-printable-art/"
}
}
],
"Set Sheet Headers": [
{
"json": {
"rows": "Url,Crawled_pages,website_content",
"sheets": [
{
"properties": {
"index": 0,
"title": "Blog content audit",
"sheetId": 618343398,
"sheetType": "GRID",
"gridProperties": {
"rowCount": 1000,
"columnCount": 26
}
}
}
],
"properties": {
"title": "https://crane-baby",
"locale": "en_US",
"timeZone": "Etc/GMT",
"autoRecalc": "ON_CHANGE",
"defaultFormat": {
"padding": {
"top": 2,
"left": 3,
"right": 3,
"bottom": 2
},
"textFormat": {
"bold": false,
"italic": false,
"fontSize": 10,
"underline": false,
"fontFamily": "arial,sans,sans-serif",
"strikethrough": false,
"foregroundColor": {},
"foregroundColorStyle": {
"rgbColor": {}
}
},
"wrapStrategy": "OVERFLOW_CELL",
"backgroundColor": {
"red": 1,
"blue": 1,
"green": 1
},
"verticalAlignment": "BOTTOM",
"backgroundColorStyle": {
"rgbColor": {
"red": 1,
"blue": 1,
"green": 1
}
}
},
"spreadsheetTheme": {
"themeColors": [
{
"color": {
"rgbColor": {}
},
"colorType": "TEXT"
},
{
"color": {
"rgbColor": {
"red": 1,
"blue": 1,
"green": 1
}
},
"colorType": "BACKGROUND"
},
{
"color": {
"rgbColor": {
"red": 0.25882354,
"blue": 0.95686275,
"green": 0.52156866
}
},
"colorType": "ACCENT1"
},
{
"color": {
"rgbColor": {
"red": 0.91764706,
"blue": 0.20784314,
"green": 0.2627451
}
},
"colorType": "ACCENT2"
},
{
"color": {
"rgbColor": {
"red": 0.9843137,
"blue": 0.015686275,
"green": 0.7372549
}
},
"colorType": "ACCENT3"
},
{
"color": {
"rgbColor": {
"red": 0.20392157,
"blue": 0.3254902,
"green": 0.65882355
}
},
"colorType": "ACCENT4"
},
{
"color": {
"rgbColor": {
"red": 1,
"blue": 0.003921569,
"green": 0.42745098
}
},
"colorType": "ACCENT5"
},
{
"color": {
"rgbColor": {
"red": 0.27450982,
"blue": 0.7764706,
"green": 0.7411765
}
},
"colorType": "ACCENT6"
},
{
"color": {
"rgbColor": {
"red": 0.06666667,
"blue": 0.8,
"green": 0.33333334
}
},
"colorType": "LINK"
}
],
"primaryFontFamily": "Arial"
}
},
"spreadsheetId": "1f3TscxV2YsGuUIfi-VfF4otWOjZZaO6SXH5ToHvDdjQ",
"spreadsheetUrl": "https://docs.google.com/spreadsheets/d/1f3TscxV2YsGuUIfi-VfF4otWOjZZaO6SXH5ToHvDdjQ/edit"
}
}
],
"Create Blog Audit Sheet": [
{
"json": {
"sheets": [
{
"properties": {
"index": 0,
"title": "Blog content audit",
"sheetId": 618343398,
"sheetType": "GRID",
"gridProperties": {
"rowCount": 1000,
"columnCount": 26
}
}
}
],
"properties": {
"title": "https://crane-baby",
"locale": "en_US",
"timeZone": "Etc/GMT",
"autoRecalc": "ON_CHANGE",
"defaultFormat": {
"padding": {
"top": 2,
"left": 3,
"right": 3,
"bottom": 2
},
"textFormat": {
"bold": false,
"italic": false,
"fontSize": 10,
"underline": false,
"fontFamily": "arial,sans,sans-serif",
"strikethrough": false,
"foregroundColor": {},
"foregroundColorStyle": {
"rgbColor": {}
}
},
"wrapStrategy": "OVERFLOW_CELL",
"backgroundColor": {
"red": 1,
"blue": 1,
"green": 1
},
"verticalAlignment": "BOTTOM",
"backgroundColorStyle": {
"rgbColor": {
"red": 1,
"blue": 1,
"green": 1
}
}
},
"spreadsheetTheme": {
"themeColors": [
{
"color": {
"rgbColor": {}
},
"colorType": "TEXT"
},
{
"color": {
"rgbColor": {
"red": 1,
"blue": 1,
"green": 1
}
},
"colorType": "BACKGROUND"
},
{
"color": {
"rgbColor": {
"red": 0.25882354,
"blue": 0.95686275,
"green": 0.52156866
}
},
"colorType": "ACCENT1"
},
{
"color": {
"rgbColor": {
"red": 0.91764706,
"blue": 0.20784314,
"green": 0.2627451
}
},
"colorType": "ACCENT2"
},
{
"color": {
"rgbColor": {
"red": 0.9843137,
"blue": 0.015686275,
"green": 0.7372549
}
},
"colorType": "ACCENT3"
},
{
"color": {
"rgbColor": {
"red": 0.20392157,
"blue": 0.3254902,
"green": 0.65882355
}
},
"colorType": "ACCENT4"
},
{
"color": {
"rgbColor": {
"red": 1,
"blue": 0.003921569,
"green": 0.42745098
}
},
"colorType": "ACCENT5"
},
{
"color": {
"rgbColor": {
"red": 0.27450982,
"blue": 0.7764706,
"green": 0.7411765
}
},
"colorType": "ACCENT6"
},
{
"color": {
"rgbColor": {
"red": 0.06666667,
"blue": 0.8,
"green": 0.33333334
}
},
"colorType": "LINK"
}
],
"primaryFontFamily": "Arial"
}
},
"spreadsheetId": "1f3TscxV2YsGuUIfi-VfF4otWOjZZaO6SXH5ToHvDdjQ",
"spreadsheetUrl": "https://docs.google.com/spreadsheets/d/1f3TscxV2YsGuUIfi-VfF4otWOjZZaO6SXH5ToHvDdjQ/edit"
}
}
],
"Insert Headers into Sheet": [
{
"json": {
"updatedRows": 1,
"updatedCells": 3,
"updatedRange": "'Blog content audit'!A1:C1",
"spreadsheetId": "1f3TscxV2YsGuUIfi-VfF4otWOjZZaO6SXH5ToHvDdjQ",
"updatedColumns": 3
}
}
]
},
"settings": {
"executionOrder": "v1"
},
"versionId": "319cd2cf-cb58-48ba-80dd-88c67a42fa8f",
"connections": {
"b9be7abb-d02c-4383-b18d-e40f77f833bf": {
"main": [
[
{
"node": "e4c0b49d-ec38-4357-ad7c-bb47145b0cd5",
"type": "main",
"index": 0
}
]
]
},
"d5135eaa-34f2-4d9e-afa9-5dd4a98b658b": {
"main": [
[
{
"node": "7fb2c810-f438-48af-a075-29e514d6855c",
"type": "main",
"index": 0
}
]
]
},
"bf50d679-1f16-4811-9e20-99eaccd9fc44": {
"main": [
[
{
"node": "cf4d1e28-6dd4-46f5-bdde-6882b9bc59d9",
"type": "main",
"index": 0
}
]
]
},
"3630f64c-a9df-4c18-a668-822b5d0aed00": {
"main": [
[
{
"node": "171ecc40-447d-4a64-adc8-f0d38d1d9cdf",
"type": "main",
"index": 0
}
]
]
},
"1138d43b-14bb-4f9c-a6dc-f82cc965e5c4": {
"main": [
[
{
"node": "3630f64c-a9df-4c18-a668-822b5d0aed00",
"type": "main",
"index": 0
}
]
]
},
"e4c0b49d-ec38-4357-ad7c-bb47145b0cd5": {
"main": [
[
{
"node": "1138d43b-14bb-4f9c-a6dc-f82cc965e5c4",
"type": "main",
"index": 0
}
]
]
},
"171ecc40-447d-4a64-adc8-f0d38d1d9cdf": {
"main": [
[
{
"node": "a1b24d76-a502-409a-b310-d4d3cc5e7c9a",
"type": "main",
"index": 0
}
]
]
},
"a1b24d76-a502-409a-b310-d4d3cc5e7c9a": {
"main": [
[
{
"node": "bf50d679-1f16-4811-9e20-99eaccd9fc44",
"type": "main",
"index": 0
}
]
]
},
"cf4d1e28-6dd4-46f5-bdde-6882b9bc59d9": {
"main": [
[
{
"node": "d5135eaa-34f2-4d9e-afa9-5dd4a98b658b",
"type": "main",
"index": 0
}
]
]
}
}
}Preguntas frecuentes
¿Cómo usar este flujo de trabajo?
Copie el código de configuración JSON de arriba, cree un nuevo flujo de trabajo en su instancia de n8n y seleccione "Importar desde JSON", pegue la configuración y luego modifique la configuración de credenciales según sea necesario.
¿En qué escenarios es adecuado este flujo de trabajo?
Intermedio - Investigación de mercado, IA Multimodal
¿Es de pago?
Este flujo de trabajo es completamente gratuito, puede importarlo y usarlo directamente. Sin embargo, tenga en cuenta que los servicios de terceros utilizados en el flujo de trabajo (como la API de OpenAI) pueden requerir un pago por su cuenta.
Flujos de trabajo relacionados recomendados
Extraer perspicacias de marketing de videos de TikTok con Dumpling AI y GPT-4
Extraer insights de marketing de videos de TikTok usando Dumpling AI y GPT-4 y generar contenido
Code
Ai Transform
Form Trigger
+
Code
Ai Transform
Form Trigger
12 NodosYang
Investigación de mercado
Extraer opciones de productos de cualquier sitio web usando Dumpling AI y GPT-4o
Usar Dumpling AI y GPT-4o para extraer productos populares de cualquier sitio web
Code
Gmail
Split Out
+
Code
Gmail
Split Out
9 NodosYang
Investigación de mercado
Genera automáticamente videos y sonido de nivel cinematográfico de animales desde formularos usando Dumpling AI
Convertir entradas de formularios en videos de calidad cinematográfica con GPT-4, Dumpling AI y audio de ElevenLabs
Set
Code
Wait
+
Set
Code
Wait
23 NodosYang
Creación de contenido
Generar automáticamente publicaciones específicas para la plataforma desde videos de YouTube con Dumpling AI
Usar GPT-4o y Dumpling AI para generar automáticamente publicaciones para Instagram, Facebook y LinkedIn a partir de videos de YouTube
Set
Code
Merge
+
Set
Code
Merge
20 NodosYang
Creación de contenido
Análisis automatizado y registro de SEO de páginas, usando RapidAPI y Hojas de Cálculo de Google
Análisis y registro automatizado de SEO de páginas usando RapidAPI y Google Sheets
Set
Code
Form Trigger
+
Set
Code
Form Trigger
33 NodosEvoort Solutions
Investigación de mercado
Investigador de creatividad de MetaAds v1.4
Usar Google Vision y Video Intelligence API para analizar las creatividades de anuncios de Meta
If
Set
Code
+
If
Set
Code
32 NodosKirill Khatkevich
Investigación de mercado
Información del flujo de trabajo
Nivel de dificultad
Intermedio
Número de nodos11
Categoría2
Tipos de nodos6
Descripción de la dificultad
Autor
Yang
@yangEnlaces externos
Ver en n8n.io →
Compartir este flujo de trabajo