{ "id": "rgpHmMpjYVZFi020", "meta": { "templateCredsSetupCompleted": true }, "name": "Price Monitor (Template)", "tags": [], "nodes": [ { "id": "f9298f65-d6ca-49b5-8aa9-8949e3d300e6", "name": "Main Sticky", "type": "n8n-nodes-base.stickyNote", "position": [ -2608, 1088 ], "parameters": { "width": 450, "height": 612, "content": "### \ud83d\udecd\ufe0f AI Price Monitor & Aggregator\n\n#### How it works\nThis workflow takes a product name from Telegram, searches Google for purchase links (Amazon EG & Jumia), scrapes the prices, and uses AI to summarize the best deal.\n1. **Trigger:** Receive product name via Telegram.\n2. **Search:** Google Search finds relevant URLs.\n3. **Scrape:** Parallel processing scrapes Amazon and Jumia/Other sites separately.\n4. **AI Analysis:** GPT-4o extracts the product details and prices from the raw HTML.\n5. **Response:** Sends a clean summary back to Telegram.\n\n#### Setup steps\n1. **Credentials:** configure your `Telegram API`, `OpenAI`, and `Decodo` credentials.\n2. **Decodo:** Ensure your Decodo account allows Google Search operations.\n3. **Webhook:** Verify the Telegram webhook is active.\n\n#### Customization tips\n- **Sites:** Edit the `Build Queries` node to add more stores (e.g., noon.com).\n- **Filters:** Adjust the `Router` node if you want to add specific scraping logic for other domains." }, "typeVersion": 1 }, { "id": "51a537b5-3a24-4055-a3b4-4ad53ef52a42", "name": "Section 1", "type": "n8n-nodes-base.stickyNote", "position": [ -2144, 1232 ], "parameters": { "color": 7, "width": 900, "height": 260, "content": "## 1. Get Links & Route\nReceives the user request, searches Google, and separates Amazon links from others for specialized handling." }, "typeVersion": 1 }, { "id": "4b054f9d-c25c-4166-bb02-ac3257c1a0d3", "name": "Section 2", "type": "n8n-nodes-base.stickyNote", "position": [ -1296, 896 ], "parameters": { "color": 7, "width": 750, "height": 300, "content": "## 2. Amazon Scraping\nSpecialized HTML cleaning and scoring logic optimized for Amazon product pages." }, "typeVersion": 1 }, { "id": "4feef981-8b47-4b59-8066-028c6d6c5589", "name": "Section 3", "type": "n8n-nodes-base.stickyNote", "position": [ -1328, 1632 ], "parameters": { "color": 7, "width": 750, "height": 300, "content": "## 3. General Scraping\nGeneric scraping logic for Jumia and other supported e-commerce sites." }, "typeVersion": 1 }, { "id": "be4e928a-c8a9-45cf-9a32-7d95d27b6d03", "name": "Section 4", "type": "n8n-nodes-base.stickyNote", "position": [ -800, 1232 ], "parameters": { "color": 7, "width": 600, "height": 380, "content": "## 4. AI Extraction & Reply\nMerges results and uses an AI Agent to extract structured price data and reply to the user." }, "typeVersion": 1 }, { "id": "6d1b1c0b-fdc6-4d34-b364-4bffca5ec4c3", "name": "Telegram Trigger", "type": "n8n-nodes-base.telegramTrigger", "position": [ -2112, 1344 ], "parameters": { "updates": [ "message" ], "additionalFields": {} }, "typeVersion": 1.2 }, { "id": "b345f524-39b0-494d-aab3-cda1f8a886b4", "name": "Build Queries", "type": "n8n-nodes-base.code", "position": [ -1904, 1344 ], "parameters": { "jsCode": "const product = $json.message.text?.trim();\nif (!product) return [];\n\nconst stores = [\n { store: \"amazon\", site: \"amazon.eg\" },\n { store: \"jumia\", site: \"jumia.com.eg\" },\n];\n\nreturn stores.map(s => ({\n json: {\n store: s.store,\n product,\n query: `${product} site:${s.site}`\n }\n}));\n" }, "typeVersion": 2 }, { "id": "e899ff7e-84cf-43e8-93dc-03f035134f1c", "name": "AI Extraction Agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ -640, 1344 ], "parameters": { "text": "=User search intent:\n{{ $('Telegram Trigger').first().json.message.text }}\n\nScraped data (multiple sources):\n{{ $json.text }}\n", "options": { "systemMessage": "You are a product comparison extraction agent.\n\nYou will receive scraped and cleaned HTML text from multiple e-commerce pages\n(Amazon, Jumia, or others), along with their URLs and relevance scores.\n\nYour job is to:\n\n1. Identify the SAME product across different platforms.\n2. For EACH platform extract:\n - Product name (clean, human readable)\n - Price (number + currency if present)\n - Platform name (Amazon, Jumia, etc.)\n - URL\n3. Compare the platforms.\n4. Prepare a final user-friendly message suitable for Telegram.\n\nSTRICT RULES:\n- Do NOT invent prices or product names.\n- If price is missing, write \"Price not found\".\n- If multiple prices exist on the same page, choose the most prominent product price.\n- Ignore ads, bundles, delivery fees, unrelated products.\n- Use ONLY the provided text.\n- Be concise and clear.\n- Use emojis moderately (Telegram friendly).\n\nOUTPUT FORMAT:\nReturn ONLY a single formatted message string.\nNo JSON.\nNo explanations.\nNo markdown blocks.\n" }, "promptType": "define" }, "typeVersion": 3 }, { "id": "91e84561-d41a-464c-90eb-13174e459871", "name": "Google Search", "type": "@decodo/n8n-nodes-decodo.decodo", "position": [ -1728, 1344 ], "parameters": { "query": "={{ $json.query }}", "headless": false, "operation": "google_search", "results_limit": 1 }, "typeVersion": 1 }, { "id": "57f34ec5-1b04-4c7d-aa33-9d3c398f2bec", "name": "Extract & Filter URLs", "type": "n8n-nodes-base.code", "position": [ -1520, 1344 ], "parameters": { "jsCode": "// Collect URLs from Decodo Google Search output\nconst allItems = $input.all();\n\nconst urls = [];\n\nfunction collectUrls(obj) {\n if (!obj || typeof obj !== 'object') return;\n\n // Collect URL fields\n if (typeof obj.url === 'string' && obj.url.startsWith('http')) {\n urls.push(obj.url);\n }\n\n // Recurse into arrays\n if (Array.isArray(obj)) {\n for (const item of obj) {\n collectUrls(item);\n }\n }\n // Recurse into objects\n else {\n for (const key of Object.keys(obj)) {\n collectUrls(obj[key]);\n }\n }\n}\n\n// Walk through every Decodo item\nfor (const item of allItems) {\n collectUrls(item.json);\n}\n\n// Deduplicate + remove Google search URLs\nconst uniqueUrls = [...new Set(urls)]\n .filter(url => !url.includes('google.com/search'))\n .slice(0, 20); // \u2705 LIMIT TO 20 ONLY\n\n// Return one item per URL\nreturn uniqueUrls.map(url => ({\n json: { url }\n}));\n" }, "typeVersion": 2 }, { "id": "98f99c7f-c4a1-4599-8d55-43ff58dff4f0", "name": "Router (Amazon vs. Other)", "type": "n8n-nodes-base.if", "position": [ -1344, 1344 ], "parameters": { "options": {}, "conditions": { "options": { "version": 3, "leftValue": "", "caseSensitive": true, "typeValidation": "strict" }, "combinator": "and", "conditions": [ { "id": "c783147f-8282-43f6-9b12-8e2526f35be9", "operator": { "type": "string", "operation": "contains" }, "leftValue": "={{ $json.url }}", "rightValue": "amazon" } ] } }, "typeVersion": 2.3 }, { "id": "b88b3738-780f-4d91-8071-06739ede596f", "name": "Scrape Amazon", "type": "@decodo/n8n-nodes-decodo.decodo", "position": [ -1072, 1008 ], "parameters": { "url": "={{ $('Extract & Filter URLs').item.json.url }}", "parse": false, "operation": "amazon" }, "typeVersion": 1 }, { "id": "719695c2-8b79-49bb-9637-43abece23440", "name": "Loop (Amazon)", "type": "n8n-nodes-base.splitInBatches", "position": [ -1232, 992 ], "parameters": { "options": {} }, "typeVersion": 3 }, { "id": "886ec5de-c344-490f-a8aa-70909b6b60d4", "name": "Clean HTML (Amazon)", "type": "n8n-nodes-base.code", "position": [ -912, 1008 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "const item = $input.item.json;\n\nlet html = \"\";\n\ntry {\n html = item.results[0].content || \"\";\n} catch (e) {\n html = \"\";\n}\n\nlet cleaned = html\n .replace(/]*>[\\s\\S]*?<\\/script>/gi, \"\")\n .replace(/]*>[\\s\\S]*?<\\/style>/gi, \"\")\n .replace(/]*>[\\s\\S]*?<\\/noscript>/gi, \"\")\n .replace(/<\\/?[^>]+>/g, \" \")\n .replace(/ /gi, \" \")\n .replace(/&/gi, \"&\")\n .replace(/"/gi, '\"')\n .replace(/'/gi, \"'\")\n .replace(/</gi, \"<\")\n .replace(/>/gi, \">\")\n .replace(/\\s+/g, \" \")\n .trim();\n\nreturn {\n json: {\n text_clean: cleaned,\n url: $('Loop (Amazon)').first().json.url\n }\n};\n" }, "typeVersion": 2 }, { "id": "28e8d953-d8f5-4946-b2d5-a09a156cc63e", "name": "Scrape Other", "type": "@decodo/n8n-nodes-decodo.decodo", "position": [ -1072, 1728 ], "parameters": { "url": "={{ $json.url }}" }, "typeVersion": 1 }, { "id": "ca82c8e1-bd5e-4432-84d9-8bf30b45b098", "name": "Loop (Other)", "type": "n8n-nodes-base.splitInBatches", "position": [ -1232, 1712 ], "parameters": { "options": {} }, "typeVersion": 3 }, { "id": "08182aff-c250-4133-8dea-45dba46d1c68", "name": "Clean HTML (Other)", "type": "n8n-nodes-base.code", "position": [ -896, 1728 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "const item = $input.item.json;\n\nlet html = \"\";\n\ntry {\n html = item.results[0].content || \"\";\n} catch (e) {\n html = \"\";\n}\n\nlet cleaned = html\n .replace(/]*>[\\s\\S]*?<\\/script>/gi, \"\")\n .replace(/]*>[\\s\\S]*?<\\/style>/gi, \"\")\n .replace(/]*>[\\s\\S]*?<\\/noscript>/gi, \"\")\n .replace(/<\\/?[^>]+>/g, \" \")\n .replace(/ /gi, \" \")\n .replace(/&/gi, \"&\")\n .replace(/"/gi, '\"')\n .replace(/'/gi, \"'\")\n .replace(/</gi, \"<\")\n .replace(/>/gi, \">\")\n .replace(/\\s+/g, \" \")\n .trim();\n\nreturn {\n json: {\n text_clean: cleaned,\n url: $('Loop (Other)').first().json.url\n }\n};\n" }, "typeVersion": 2 }, { "id": "95becc17-a85a-42b3-8c7f-41707045543d", "name": "Score Match (Other)", "type": "n8n-nodes-base.code", "position": [ -736, 1728 ], "parameters": { "jsCode": "// 1\ufe0f\u20e3 User message (dynamic, from Telegram)\nconst userMessage =\n $('Telegram Trigger').first().json.message.text\n .toLowerCase()\n .replace(/[^\\w\\s\\u0600-\\u06FF]/g, ' ');\n\n// 2\ufe0f\u20e3 Tokenize user message dynamically\nconst userTokens = userMessage\n .split(/\\s+/)\n .filter(w => w.length >= 3);\n\n// 3\ufe0f\u20e3 Cleaned page text\nconst pageText = ($json.text_clean || '')\n .toLowerCase()\n .replace(/[^\\w\\s\\u0600-\\u06FF]/g, ' ');\n\n// 4\ufe0f\u20e3 URL (pass-through from earlier nodes)\nconst url = $json.url || null;\n\n// Guards\nif (!pageText || userTokens.length === 0) {\n return [{\n json: {\n match: false,\n score: 0,\n url\n }\n }];\n}\n\n// 5\ufe0f\u20e3 Dynamic scoring\nlet score = 0;\nlet matchedTokens = [];\n\nfor (const token of userTokens) {\n const occurrences = pageText.split(token).length - 1;\n if (occurrences > 0) {\n score += Math.min(occurrences * 3, 15); // density-aware\n matchedTokens.push(token);\n }\n}\n\n// 6\ufe0f\u20e3 Structural bonuses (language-agnostic)\nif (pageText.length > 1500) score += 5; // real product page\nif (pageText.length < 400) score -= 10; // weak page\nif (\n pageText.includes('add to cart') ||\n pageText.includes('\u0627\u0636\u0641') ||\n pageText.includes('\u0623\u0636\u0641')\n) score += 5;\n\n// 7\ufe0f\u20e3 Dynamic threshold (based on user input length)\nconst threshold = Math.max(12, userTokens.length * 4);\nconst isMatch = score >= threshold;\n\n// 8\ufe0f\u20e3 Output EVERYTHING needed downstream\nreturn [{\n json: {\n match: isMatch,\n score,\n threshold,\n url,\n matched_tokens: matchedTokens,\n text_clean: pageText\n }\n}];\n" }, "typeVersion": 2 }, { "id": "502a928b-2091-4b63-9716-651337efa735", "name": "Score Match (Amazon)", "type": "n8n-nodes-base.code", "position": [ -736, 1008 ], "parameters": { "jsCode": "// 1\ufe0f\u20e3 User message (dynamic, from Telegram)\nconst userMessage =\n $('Telegram Trigger').first().json.message.text\n .toLowerCase()\n .replace(/[^\\w\\s\\u0600-\\u06FF]/g, ' ');\n\n// 2\ufe0f\u20e3 Tokenize user message dynamically\nconst userTokens = userMessage\n .split(/\\s+/)\n .filter(w => w.length >= 3);\n\n// 3\ufe0f\u20e3 Cleaned page text\nconst pageText = ($json.text_clean || '')\n .toLowerCase()\n .replace(/[^\\w\\s\\u0600-\\u06FF]/g, ' ');\n\n// 4\ufe0f\u20e3 URL (pass-through from earlier nodes)\nconst url = $json.url || null;\n\n// Guards\nif (!pageText || userTokens.length === 0) {\n return [{\n json: {\n match: false,\n score: 0,\n url\n }\n }];\n}\n\n// 5\ufe0f\u20e3 Dynamic scoring\nlet score = 0;\nlet matchedTokens = [];\n\nfor (const token of userTokens) {\n const occurrences = pageText.split(token).length - 1;\n if (occurrences > 0) {\n score += Math.min(occurrences * 3, 15); // density-aware\n matchedTokens.push(token);\n }\n}\n\n// 6\ufe0f\u20e3 Structural bonuses (language-agnostic)\nif (pageText.length > 1500) score += 5; // real product page\nif (pageText.length < 400) score -= 10; // weak page\nif (\n pageText.includes('add to cart') ||\n pageText.includes('\u0627\u0636\u0641') ||\n pageText.includes('\u0623\u0636\u0641')\n) score += 5;\n\n// 7\ufe0f\u20e3 Dynamic threshold (based on user input length)\nconst threshold = Math.max(12, userTokens.length * 4);\nconst isMatch = score >= threshold;\n\n// 8\ufe0f\u20e3 Output EVERYTHING needed downstream\nreturn [{\n json: {\n match: isMatch,\n score,\n threshold,\n url,\n matched_tokens: matchedTokens,\n text_clean: pageText\n }\n}];\n" }, "typeVersion": 2 }, { "id": "d373cd04-5d7b-42fb-bb8e-bff1e13bf9e8", "name": "Pick Best (Amazon)", "type": "n8n-nodes-base.code", "position": [ -1120, 1280 ], "parameters": { "jsCode": "const items = $input.all().map(i => i.json);\n\n// Keep only valid matches\nconst valid = items.filter(i => i.match === true);\n\n// If none matched, return nothing\nif (!valid.length) return [];\n\n// Pick highest score\nvalid.sort((a, b) => b.score - a.score);\n\nreturn [{\n json: valid[0]\n}];\n" }, "typeVersion": 2 }, { "id": "dd39e9a7-5491-487a-a4d2-9bfb636f645b", "name": "Pick Best (Other)", "type": "n8n-nodes-base.code", "position": [ -1120, 1424 ], "parameters": { "jsCode": "const items = $input.all().map(i => i.json);\n\n// Keep only valid matches\nconst valid = items.filter(i => i.match === true);\n\n// If none matched, return nothing\nif (!valid.length) return [];\n\n// Pick highest score\nvalid.sort((a, b) => b.score - a.score);\n\nreturn [{\n json: valid[0]\n}];\n" }, "typeVersion": 2 }, { "id": "d8c9cb70-d67b-401c-8191-474efc31eaac", "name": "Merge Results", "type": "n8n-nodes-base.merge", "position": [ -944, 1344 ], "parameters": {}, "typeVersion": 3.2 }, { "id": "c863240d-717b-4557-9aa9-cdbe7944c45c", "name": "GPT Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ -640, 1504 ], "parameters": { "model": { "__rl": true, "mode": "list", "value": "gpt-4o-mini" }, "options": {} }, "typeVersion": 1.2 }, { "id": "a3b4c774-7d06-4188-9503-8735319cbae8", "name": "Format Context", "type": "n8n-nodes-base.code", "position": [ -800, 1344 ], "parameters": { "jsCode": "const items = $input.all().map(i => i.json);\n\nconst combinedText = items.map(item => `\nSOURCE URL:\n${item.url}\n\nRELEVANCE SCORE:\n${item.score}\n\nCONTENT:\n${item.text_clean.slice(0, 5000)}\n`).join('\\n\\n====================\\n\\n');\n\nreturn [{\n json: {\n text: combinedText // \ud83d\udd34 THIS NAME IS CRITICAL\n }\n}];\n" }, "typeVersion": 2 }, { "id": "fb221ed8-fa1c-4483-b9d2-38289e5a21df", "name": "Send Reply", "type": "n8n-nodes-base.telegram", "position": [ -336, 1344 ], "parameters": { "text": "={{ $json.output }}", "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}", "additionalFields": { "appendAttribution": false } }, "typeVersion": 1.2 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "9d7a4e7f-c857-4178-a66d-490c22015ce6", "connections": { "GPT Model": { "ai_languageModel": [ [ { "node": "AI Extraction Agent", "type": "ai_languageModel", "index": 0 } ] ] }, "Loop (Other)": { "main": [ [ { "node": "Pick Best (Other)", "type": "main", "index": 0 } ], [ { "node": "Scrape Other", "type": "main", "index": 0 } ] ] }, "Scrape Other": { "main": [ [ { "node": "Clean HTML (Other)", "type": "main", "index": 0 } ] ] }, "Build Queries": { "main": [ [ { "node": "Google Search", "type": "main", "index": 0 } ] ] }, "Google Search": { "main": [ [ { "node": "Extract & Filter URLs", "type": "main", "index": 0 } ] ] }, "Loop (Amazon)": { "main": [ [ { "node": "Pick Best (Amazon)", "type": "main", "index": 0 } ], [ { "node": "Scrape Amazon", "type": "main", "index": 0 } ] ] }, "Merge Results": { "main": [ [ { "node": "Format Context", "type": "main", "index": 0 } ] ] }, "Scrape Amazon": { "main": [ [ { "node": "Clean HTML (Amazon)", "type": "main", "index": 0 } ] ] }, "Format Context": { "main": [ [ { "node": "AI Extraction Agent", "type": "main", "index": 0 } ] ] }, "Telegram Trigger": { "main": [ [ { "node": "Build Queries", "type": "main", "index": 0 } ] ] }, "Pick Best (Other)": { "main": [ [ { "node": "Merge Results", "type": "main", "index": 1 } ] ] }, "Clean HTML (Other)": { "main": [ [ { "node": "Score Match (Other)", "type": "main", "index": 0 } ] ] }, "Pick Best (Amazon)": { "main": [ [ { "node": "Merge Results", "type": "main", "index": 0 } ] ] }, "AI Extraction Agent": { "main": [ [ { "node": "Send Reply", "type": "main", "index": 0 } ] ] }, "Clean HTML (Amazon)": { "main": [ [ { "node": "Score Match (Amazon)", "type": "main", "index": 0 } ] ] }, "Score Match (Other)": { "main": [ [ { "node": "Loop (Other)", "type": "main", "index": 0 } ] ] }, "Score Match (Amazon)": { "main": [ [ { "node": "Loop (Amazon)", "type": "main", "index": 0 } ] ] }, "Extract & Filter URLs": { "main": [ [ { "node": "Router (Amazon vs. Other)", "type": "main", "index": 0 } ] ] }, "Router (Amazon vs. Other)": { "main": [ [ { "node": "Loop (Amazon)", "type": "main", "index": 0 } ], [ { "node": "Loop (Other)", "type": "main", "index": 0 } ] ] } } }