352 lines
9.6 KiB
JSON
352 lines
9.6 KiB
JSON
{
|
||
"meta": {
|
||
"instanceId": "4a11afdb3c52fd098e3eae9fad4b39fdf1bbcde142f596adda46c795e366b326"
|
||
},
|
||
"nodes": [
|
||
{
|
||
"id": "f1b36f4b-6558-4e83-a999-e6f2d24e196c",
|
||
"name": "OpenRouter Chat Model",
|
||
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
|
||
"position": [
|
||
620,
|
||
240
|
||
],
|
||
"parameters": {
|
||
"model": "openai/gpt-4.1",
|
||
"options": {}
|
||
},
|
||
"typeVersion": 1
|
||
},
|
||
{
|
||
"id": "89ca0a07-286f-4e68-9e85-0327a4859cc0",
|
||
"name": "Structured Output Parser",
|
||
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
|
||
"position": [
|
||
900,
|
||
240
|
||
],
|
||
"parameters": {
|
||
"schemaType": "manual",
|
||
"inputSchema": "{\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"description\": { \"type\": \"string\" },\n \"rating\": { \"type\": \"number\" },\n \"reviews\": { \"type\": \"integer\" },\n \"price\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"description\", \"rating\", \"reviews\", \"price\"]\n }\n}"
|
||
},
|
||
"typeVersion": 1.2
|
||
},
|
||
{
|
||
"id": "e4800c1d-c0d8-4093-81ec-fc19ad0034cd",
|
||
"name": "scrap url",
|
||
"type": "n8n-nodes-base.httpRequest",
|
||
"position": [
|
||
240,
|
||
60
|
||
],
|
||
"parameters": {
|
||
"url": "https://api.brightdata.com/request",
|
||
"method": "POST",
|
||
"options": {},
|
||
"sendBody": true,
|
||
"sendHeaders": true,
|
||
"bodyParameters": {
|
||
"parameters": [
|
||
{
|
||
"name": "zone",
|
||
"value": "web_unlocker1"
|
||
},
|
||
{
|
||
"name": "url",
|
||
"value": "={{ $json.url }}"
|
||
},
|
||
{
|
||
"name": "format",
|
||
"value": "raw"
|
||
}
|
||
]
|
||
},
|
||
"headerParameters": {
|
||
"parameters": [
|
||
{
|
||
"name": "Authorization",
|
||
"value": "{{BRIGHTDATA_TOKEN}}"
|
||
}
|
||
]
|
||
}
|
||
},
|
||
"typeVersion": 4.2
|
||
},
|
||
{
|
||
"id": "1a1f768f-615d-4035-81b0-63b860f8e6ac",
|
||
"name": "Sticky Note1",
|
||
"type": "n8n-nodes-base.stickyNote",
|
||
"position": [
|
||
160,
|
||
-140
|
||
],
|
||
"parameters": {
|
||
"content": "## Web Scraper API\n\n[Inscription - Free Trial](https://get.brightdata.com/website-scraper)"
|
||
},
|
||
"typeVersion": 1
|
||
},
|
||
{
|
||
"id": "2f260d96-4fff-4a4f-af29-1e43f465d54c",
|
||
"name": "When clicking ‘Test workflow’",
|
||
"type": "n8n-nodes-base.manualTrigger",
|
||
"position": [
|
||
-440,
|
||
200
|
||
],
|
||
"parameters": {},
|
||
"typeVersion": 1
|
||
},
|
||
{
|
||
"id": "4be9033f-0b9f-466d-916e-88fbb2a80417",
|
||
"name": "url",
|
||
"type": "n8n-nodes-base.splitInBatches",
|
||
"position": [
|
||
20,
|
||
200
|
||
],
|
||
"parameters": {
|
||
"options": {}
|
||
},
|
||
"typeVersion": 3
|
||
},
|
||
{
|
||
"id": "21b6d21c-b977-4175-9068-e0e2e19fa472",
|
||
"name": "get urls to scrape",
|
||
"type": "n8n-nodes-base.googleSheets",
|
||
"position": [
|
||
-200,
|
||
200
|
||
],
|
||
"parameters": {
|
||
"options": {},
|
||
"sheetName": "{{TRACK_SHEET_GID}}",
|
||
"documentId": "{{WEB_SHEET_ID}}"
|
||
},
|
||
"credentials": {
|
||
"googleSheetsOAuth2Api": {
|
||
"id": "KsXWRZTrfCUFrrHD",
|
||
"name": "Google Sheets"
|
||
}
|
||
},
|
||
"typeVersion": 4.5
|
||
},
|
||
{
|
||
"id": "25ef76ec-cf0d-422e-b060-68c49192a008",
|
||
"name": "clean html",
|
||
"type": "n8n-nodes-base.code",
|
||
"position": [
|
||
460,
|
||
60
|
||
],
|
||
"parameters": {
|
||
"jsCode": "// CleanHtmlFunction.js\n// Purpose: n8n Function node to clean HTML: remove doctype, scripts, styles, head, comments, classes, extra blank lines, and non-whitelisted tags\n\nreturn items.map(item => {\n const rawHtml = item.json.data;\n\n // 1) remove doctype, scripts, styles, comments and head section, and strip class attributes\n let cleaned = rawHtml\n .replace(/<!doctype html>/gi, '')\n .replace(/<script[\\s\\S]*?<\\/script>/gi, '')\n .replace(/<style[\\s\\S]*?<\\/style>/gi, '')\n .replace(/<!--[\\s\\S]*?-->/g, '')\n .replace(/<head[\\s\\S]*?<\\/head>/gi, '')\n .replace(/\\sclass=\"[^\"]*\"/gi, '');\n\n // 2) define whitelist of tags to keep\n const allowedTags = [\n 'h1','h2','h3','h4','h5','h6',\n 'p','ul','ol','li',\n 'strong','em','a','blockquote',\n 'code','pre'\n ];\n\n // 3) strip out all tags not in the whitelist, reconstruct allowed tags cleanly\n cleaned = cleaned.replace(\n /<\\/?([a-z][a-z0-9]*)\\b[^>]*>/gi,\n (match, tagName) => {\n const name = tagName.toLowerCase();\n if (allowedTags.includes(name)) {\n return match.startsWith('</') ? `</${name}>` : `<${name}>`;\n }\n return '';\n }\n );\n\n // 4) collapse multiple blank or whitespace-only lines into a single newline\n cleaned = cleaned.replace(/(\\s*\\r?\\n\\s*){2,}/g, '\\n');\n\n // 5) trim leading/trailing whitespace\n cleaned = cleaned.trim();\n\n return {\n json: { cleanedHtml: cleaned }\n };\n});"
|
||
},
|
||
"typeVersion": 2
|
||
},
|
||
{
|
||
"id": "f72660d5-8427-4655-acbe-10365273c27b",
|
||
"name": "extract data",
|
||
"type": "@n8n/n8n-nodes-langchain.chainLlm",
|
||
"position": [
|
||
680,
|
||
60
|
||
],
|
||
"parameters": {
|
||
"text": "={{ $json.cleanedHtml }}",
|
||
"messages": {
|
||
"messageValues": [
|
||
{
|
||
"message": "=You are an expert in web page scraping. Provide a structured response in JSON format. Only the response, without commentary.\n\nExtract the product information for {{ $(‘url’).item.json.url.split(’/s?k=’)[1].split(’&’)[0] }} present on the page.\n\nname\ndescription\nrating\nreviews\nprice"
|
||
}
|
||
]
|
||
},
|
||
"promptType": "define",
|
||
"hasOutputParser": true
|
||
},
|
||
"typeVersion": 1.6
|
||
},
|
||
{
|
||
"id": "8b4af1bb-d7f8-456e-b630-ecd9b6e4bcdc",
|
||
"name": "add results",
|
||
"type": "n8n-nodes-base.googleSheets",
|
||
"position": [
|
||
1280,
|
||
200
|
||
],
|
||
"parameters": {
|
||
"columns": {
|
||
"value": {
|
||
"name": "={{ $json.output.name }}",
|
||
"price": "={{ $json.output.price }}",
|
||
"rating": "={{ $json.output.rating }}",
|
||
"reviews": "={{ $json.output.reviews }}",
|
||
"description": "={{ $json.output.description }}"
|
||
},
|
||
"schema": [
|
||
{
|
||
"id": "name",
|
||
"type": "string"
|
||
},
|
||
{
|
||
"id": "description",
|
||
"type": "string"
|
||
},
|
||
{
|
||
"id": "rating",
|
||
"type": "string"
|
||
},
|
||
{
|
||
"id": "reviews",
|
||
"type": "string"
|
||
},
|
||
{
|
||
"id": "price",
|
||
"type": "string"
|
||
}
|
||
],
|
||
"mappingMode": "defineBelow"
|
||
},
|
||
"options": {},
|
||
"operation": "append",
|
||
"sheetName": "{{RESULTS_SHEET_GID}}",
|
||
"documentId": "{{WEB_SHEET_ID}}"
|
||
},
|
||
"credentials": {
|
||
"googleSheetsOAuth2Api": {
|
||
"id": "KsXWRZTrfCUFrrHD",
|
||
"name": "Google Sheets"
|
||
}
|
||
},
|
||
"typeVersion": 4.5
|
||
},
|
||
{
|
||
"id": "7a5ba438-2ede-4d6c-b8fa-9a958ba1ef3e",
|
||
"name": "Split items",
|
||
"type": "n8n-nodes-base.splitOut",
|
||
"position": [
|
||
1060,
|
||
60
|
||
],
|
||
"parameters": {
|
||
"include": "allOtherFields",
|
||
"options": {},
|
||
"fieldToSplitOut": "output"
|
||
},
|
||
"typeVersion": 1
|
||
}
|
||
],
|
||
"pinData": {},
|
||
"connections": {
|
||
"url": {
|
||
"main": [
|
||
[],
|
||
[
|
||
{
|
||
"node": "scrap url",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"scrap url": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "clean html",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"clean html": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "extract data",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"Split items": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "add results",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"add results": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "url",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"extract data": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "Split items",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"get urls to scrape": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "url",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"OpenRouter Chat Model": {
|
||
"ai_languageModel": [
|
||
[
|
||
{
|
||
"node": "extract data",
|
||
"type": "ai_languageModel",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"Structured Output Parser": {
|
||
"ai_outputParser": [
|
||
[
|
||
{
|
||
"node": "extract data",
|
||
"type": "ai_outputParser",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
},
|
||
"When clicking ‘Test workflow’": {
|
||
"main": [
|
||
[
|
||
{
|
||
"node": "get urls to scrape",
|
||
"type": "main",
|
||
"index": 0
|
||
}
|
||
]
|
||
]
|
||
}
|
||
}
|
||
} |