commit e6d9b2945784c3b3dd24f28844008a08ac477d1c Author: EidanThen Date: Sat May 9 17:46:38 2026 +0000 Subir archivos a "/" diff --git a/Website Craw CSS.json b/Website Craw CSS.json new file mode 100644 index 0000000..b575637 --- /dev/null +++ b/Website Craw CSS.json @@ -0,0 +1,360 @@ +{ + "name": "Website Craw CSS", + "nodes": [ + { + "parameters": {}, + "type": "n8n-nodes-base.manualTrigger", + "typeVersion": 1, + "position": [ + 496, + 0 + ], + "id": "276425c9-312d-41db-8abe-0d126c5e63bc", + "name": "When clicking ‘Execute workflow’" + }, + { + "parameters": { + "amount": 15 + }, + "type": "n8n-nodes-base.wait", + "typeVersion": 1.1, + "position": [ + 880, + 0 + ], + "id": "201b3b1b-cebe-4c9e-abc6-ddf6bf289704", + "name": "Wait", + "webhookId": "bd46a11c-b55b-4967-878b-9e77cf7ae8ac" + }, + { + "parameters": { + "mode": "raw", + "jsonOutput": "={\n\"products\": {{\n$('Get LLM Crawl').last().json.results.flatMap(item => {\nconst parsed = JSON.parse(item.extracted_content);\nreturn parsed.map(({ rating, ...rest }) => ({\n...rest,\nstar_count: Array.isArray(rating) ? rating.length : 0\n}));\n})\n}}\n}\n\n", + "options": {} + }, + "type": "n8n-nodes-base.set", + "typeVersion": 3.4, + "position": [ + 1632, + -16 + ], + "id": "0c9c0b61-4f26-498a-af48-39d311009a36", + "name": "LLM Result" + }, + { + "parameters": { + "url": "=https://pruebadetemplate-crwal4ai.k11ytw.easypanel.host/task/{{ $json.task_id }}", + "authentication": "genericCredentialType", + "genericAuthType": "httpHeaderAuth", + "options": {} + }, + "type": "n8n-nodes-base.httpRequest", + "typeVersion": 4.2, + "position": [ + 1056, + 0 + ], + "id": "a78332b7-7b8c-4d88-ab86-c20a07557e43", + "name": "Get LLM Crawl", + "credentials": { + "httpBasicAuth": { + "id": "kSyyvvNaOBuA00C4", + "name": "crawl4aiserver" + }, + "httpHeaderAuth": { + "id": "VLM9roYC9zcTGJsa", + "name": "panel" + } + } + }, + { + "parameters": { + "mode": "raw", + "jsonOutput": "={\n \"task_id\": \"{{ $('Markdown Crawl Request').item.json.task_id }}\", \"status\": \"{{ $json.status }}\"\n}", + "options": {} + }, + "type": "n8n-nodes-base.set", + "typeVersion": 3.4, + "position": [ + 1264, + 0 + ], + "id": "0e2549d5-b06c-4bd8-93ca-6f7e81f81d53", + "name": "LLM TID Field" + }, + { + "parameters": { + "conditions": { + "options": { + "caseSensitive": true, + "leftValue": "", + "typeValidation": "strict", + "version": 2 + }, + "conditions": [ + { + "id": "aad7f793-d74c-4f00-8d29-11b4782b43c8", + "leftValue": "={{ $json.status }}", + "rightValue": "pending", + "operator": { + "type": "string", + "operation": "notEquals" + } + }, + { + "id": "c1ca239e-8ba0-447f-bc6e-bdbc83273c9f", + "leftValue": "={{ $json.status }}", + "rightValue": "processing", + "operator": { + "type": "string", + "operation": "notEquals" + } + } + ], + "combinator": "and" + }, + "options": {} + }, + "type": "n8n-nodes-base.if", + "typeVersion": 2.2, + "position": [ + 1472, + 0 + ], + "id": "e83c31da-0d64-4fb0-b9ab-8b7ebd941ce5", + "name": "LLM if In Process" + }, + { + "parameters": { + "method": "POST", + "url": "https://pruebadetemplate-crwal4ai.k11ytw.easypanel.host/crawl", + "authentication": "genericCredentialType", + "genericAuthType": "httpHeaderAuth", + "sendBody": true, + "specifyBody": "json", + "jsonBody": "={\n \"urls\": {{ JSON.stringify(Array.from({ length: 2 }, (_, i) =>\n'https://sandbox.oxylabs.io/products?page=${i + 1}')) }},\n \"crawler_params\": {\n \"headless\": true\n },\n \"extraction_config\": {\n \"type\": \"json_css\",\n \"params\": {\n \"schema\": {\n \"name\": \"Oxylabs Products\",\n \"baseSelector\": \"div.product-card\",\n \"fields\": [\n {\n \"name\": \"product_link\",\n \"selector\": \".card-header\",\n \"type\": \"attribute\",\n \"attribute\": \"href\"\n },\n {\n \"name\": \"title\",\n \"selector\": \".title\",\n \"type\": \"text\"\n },\n {\n \"name\": \"rating\",\n \"type\": \"list\",\n \"selector\": \".rating svg\",\n \"fields\": [\n {\n \"name\": \"star_svg\",\n \"type\": \"html\"\n }\n ]\n },\n {\n \"name\": \"description\",\n \"selector\": \".description\",\n \"type\": \"text\"\n },\n {\n \"name\": \"price\",\n \"selector\": \".price-wrapper\",\n \"type\": \"text\"\n },\n {\n \"name\": \"stock_status\",\n \"selector\": \".in-stock\",\n \"type\": \"text\"\n }\n ]\n }\n }\n },\n \"verbose\": true,\n \"cache_mode\": \"bypass\",\n \"semaphore_count\": 2\n}\n", + "options": {} + }, + "type": "n8n-nodes-base.httpRequest", + "typeVersion": 4.2, + "position": [ + 672, + 0 + ], + "id": "05fbc6b5-989e-4cfa-bc6b-f12d1c43255e", + "name": "Markdown Crawl Request", + "credentials": { + "httpBasicAuth": { + "id": "kSyyvvNaOBuA00C4", + "name": "crawl4aiserver" + }, + "httpHeaderAuth": { + "id": "VLM9roYC9zcTGJsa", + "name": "panel" + } + } + }, + { + "parameters": { + "documentId": { + "__rl": true, + "value": "1LatvxzjsFgWUcDgqIFubGbsy6yNeeSwZ7w9yg_tb8xY", + "mode": "list", + "cachedResultName": "UrlsTest", + "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1LatvxzjsFgWUcDgqIFubGbsy6yNeeSwZ7w9yg_tb8xY/edit?usp=drivesdk" + }, + "sheetName": { + "__rl": true, + "value": "gid=0", + "mode": "list", + "cachedResultName": "Hoja 1", + "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1LatvxzjsFgWUcDgqIFubGbsy6yNeeSwZ7w9yg_tb8xY/edit#gid=0" + }, + "options": {} + }, + "type": "n8n-nodes-base.googleSheets", + "typeVersion": 4.7, + "position": [ + 1072, + 272 + ], + "id": "74ee3af8-6237-43c7-909c-1c72f52a5a0c", + "name": "Get row(s) in sheet", + "credentials": { + "googleSheetsOAuth2Api": { + "id": "SE121yXzuB6zr94l", + "name": "Google Sheets account" + } + }, + "disabled": true + }, + { + "parameters": { + "options": {} + }, + "type": "n8n-nodes-base.splitInBatches", + "typeVersion": 3, + "position": [ + 1280, + 272 + ], + "id": "e5199e00-0338-4f3d-88c6-8ec96835975f", + "name": "Loop Over Items", + "disabled": true + }, + { + "parameters": { + "fieldToSplitOut": "products", + "options": {} + }, + "type": "n8n-nodes-base.splitOut", + "typeVersion": 1, + "position": [ + 1808, + -16 + ], + "id": "748d3237-e40b-4f4c-800a-625c24ab6cd2", + "name": "Split Out" + }, + { + "parameters": { + "binaryPropertyName": "products", + "options": {} + }, + "type": "n8n-nodes-base.convertToFile", + "typeVersion": 1.1, + "position": [ + 1968, + -16 + ], + "id": "99c19185-50e6-4b49-9f7e-15c434c03f14", + "name": "Convert to File" + } + ], + "pinData": {}, + "connections": { + "When clicking ‘Execute workflow’": { + "main": [ + [ + { + "node": "Markdown Crawl Request", + "type": "main", + "index": 0 + } + ] + ] + }, + "Wait": { + "main": [ + [ + { + "node": "Get LLM Crawl", + "type": "main", + "index": 0 + } + ] + ] + }, + "Get LLM Crawl": { + "main": [ + [ + { + "node": "LLM TID Field", + "type": "main", + "index": 0 + } + ] + ] + }, + "LLM TID Field": { + "main": [ + [ + { + "node": "LLM if In Process", + "type": "main", + "index": 0 + } + ] + ] + }, + "LLM if In Process": { + "main": [ + [ + { + "node": "LLM Result", + "type": "main", + "index": 0 + } + ], + [ + { + "node": "Wait", + "type": "main", + "index": 0 + } + ] + ] + }, + "Markdown Crawl Request": { + "main": [ + [ + { + "node": "Wait", + "type": "main", + "index": 0 + } + ] + ] + }, + "Get row(s) in sheet": { + "main": [ + [ + { + "node": "Loop Over Items", + "type": "main", + "index": 0 + } + ] + ] + }, + "Loop Over Items": { + "main": [ + [], + [] + ] + }, + "LLM Result": { + "main": [ + [ + { + "node": "Split Out", + "type": "main", + "index": 0 + } + ] + ] + }, + "Split Out": { + "main": [ + [ + { + "node": "Convert to File", + "type": "main", + "index": 0 + } + ] + ] + } + }, + "active": false, + "settings": { + "executionOrder": "v1" + }, + "versionId": "fcdd8ae2-6c72-4cf6-a3b9-d87b93e0d0d2", + "meta": { + "templateCredsSetupCompleted": true, + "instanceId": "57b253ac4a90f3c1149cb4540b0ccf8677c4c106dc133e4a240f1f14ec79a39c" + }, + "id": "1qFQ6FmyYMqrrV8n", + "tags": [] +} \ No newline at end of file diff --git a/Website Craw IA.json b/Website Craw IA.json new file mode 100644 index 0000000..cc90d31 --- /dev/null +++ b/Website Craw IA.json @@ -0,0 +1,323 @@ +{ + "name": "Website Craw IA v4", + "nodes": [ + { + "parameters": {}, + "type": "n8n-nodes-base.manualTrigger", + "typeVersion": 1, + "position": [ + 64, + 0 + ], + "id": "e4051790-d93e-4048-9d8e-64de8b644f57", + "name": "When clicking ‘Execute workflow’" + }, + { + "parameters": {}, + "type": "n8n-nodes-base.wait", + "typeVersion": 1.1, + "position": [ + 880, + 0 + ], + "id": "3ec97de7-159c-46e6-af26-267d52f14d57", + "name": "Wait", + "webhookId": "1ef26c6f-55e3-4f51-bab5-6bb1e4b85fb8" + }, + { + "parameters": { + "mode": "raw", + "jsonOutput": "={\n\"result\": {{ $('Get LLM Crawl').item.json.result.extracted_content }}\n}", + "options": {} + }, + "type": "n8n-nodes-base.set", + "typeVersion": 3.4, + "position": [ + 1632, + -16 + ], + "id": "5d269e95-2e32-456b-8d07-54b279a0f543", + "name": "LLM Result" + }, + { + "parameters": { + "url": "=https://evo-crwal4ai.5lbnb4.easypanel.host/task/{{ $json.task_id }}", + "authentication": "genericCredentialType", + "genericAuthType": "httpHeaderAuth", + "options": {} + }, + "type": "n8n-nodes-base.httpRequest", + "typeVersion": 4.2, + "position": [ + 1056, + 0 + ], + "id": "e1d5e1dc-27ca-4617-bc2d-eafa3292db17", + "name": "Get LLM Crawl", + "credentials": { + "httpBasicAuth": { + "id": "kSyyvvNaOBuA00C4", + "name": "crawl4aiserver" + }, + "httpHeaderAuth": { + "id": "VLM9roYC9zcTGJsa", + "name": "panel" + } + } + }, + { + "parameters": { + "mode": "raw", + "jsonOutput": "={\n \"task_id\": \"{{ $('Markdown Crawl Request').item.json.task_id }}\", \"status\": \"{{ $json.status }}\"\n}", + "options": {} + }, + "type": "n8n-nodes-base.set", + "typeVersion": 3.4, + "position": [ + 1264, + 0 + ], + "id": "7b604366-9af1-417a-b724-f039e574cc19", + "name": "LLM TID Field" + }, + { + "parameters": { + "conditions": { + "options": { + "caseSensitive": true, + "leftValue": "", + "typeValidation": "strict", + "version": 2 + }, + "conditions": [ + { + "id": "aad7f793-d74c-4f00-8d29-11b4782b43c8", + "leftValue": "={{ $json.status }}", + "rightValue": "pending", + "operator": { + "type": "string", + "operation": "notEquals" + } + }, + { + "id": "c1ca239e-8ba0-447f-bc6e-bdbc83273c9f", + "leftValue": "={{ $json.status }}", + "rightValue": "processing", + "operator": { + "type": "string", + "operation": "notEquals" + } + } + ], + "combinator": "and" + }, + "options": {} + }, + "type": "n8n-nodes-base.if", + "typeVersion": 2.2, + "position": [ + 1472, + 0 + ], + "id": "4fef42a2-3682-4ca4-b2c9-4205471aa1ce", + "name": "LLM if In Process" + }, + { + "parameters": { + "method": "POST", + "url": "https://evo-crwal4ai.5lbnb4.easypanel.host/crawl", + "authentication": "genericCredentialType", + "genericAuthType": "httpHeaderAuth", + "sendBody": true, + "specifyBody": "json", + "jsonBody": "={\n \"urls\": \"{{ $json.loc }}\",\n \"crawler_params\": {\n \"headless\": true\n },\n \"extraction_config\": {\n \"type\": \"llm\",\n \"params\": {\n \"llm_config\": {\n \"provider\": \"openai/gpt4o-mini\"\n },\n \"schema\": {\n \"title\": \"ProductData\",\n \"type\": \"object\",\n \"properties\": {\n \"title\": { \"type\": \"string\", \"description\": \"Product name (page title).\" },\n \"sku\": { \"type\": \"string\", \"description\": \"SKU/Referencia: use Product.sku/mpn or 'Referencia:' text on page.\" },\n \"price\": { \"type\": \"string\", \"description\": \"Numeric price only, e.g. 12.29\" },\n \"currency\": { \"type\": \"string\", \"description\": \"Price currency code/symbol if available (e.g. USD, B/., $).\" },\n \"category\": { \"type\": \"string\", \"description\": \"Breadcrumb category; prefer the node 'leches' if present, else the most specific category.\" },\n \"description\": { \"type\": \"string\", \"description\": \"Long textual description.\" },\n \"image\": { \"type\": \"string\", \"description\": \"Main image URL.\" },\n \"url\": { \"type\": \"string\", \"description\": \"Canonical product URL.\" }\n },\n \"required\": [\"title\", \"price\", \"url\"]\n },\n \"extraction_type\": \"schema\",\n \"instruction\": \"Extract data primarily from