The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "WkPttMonitor04",
"name": "PTT \u8f3f\u60c5\u76e3\u6e2c (PTT Sentiment Monitor \u00b7 \u672c\u6a5f Ollama)",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 9 * * *"
}
]
}
},
"id": "node-schedule",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
240,
400
]
},
{
"parameters": {
"jsCode": "const board = 'Tech_Job';\nconst keyword = 'AI';\nconst url = 'https://www.ptt.cc/bbs/' + board + '/search?q=' + encodeURIComponent(keyword);\nreturn [{ json: { board, keyword, url } }];"
},
"id": "node-input",
"name": "Input (edit me)",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
460,
400
]
},
{
"parameters": {
"method": "GET",
"url": "={{ $json.url }}",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Cookie",
"value": "over18=1"
},
{
"name": "User-Agent",
"value": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
}
]
},
"options": {}
},
"id": "node-fetch",
"name": "Fetch PTT",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
680,
400
]
},
{
"parameters": {
"jsCode": "const j = $input.first().json;\nconst html = j.data || j.body || '';\nconst re = /<div class=\\x22title\\x22>\\s*<a href=\\x22([^\\x22]+)\\x22>([^<]+)<\\/a>/g;\nconst items = []; let m;\nwhile ((m = re.exec(html)) !== null) {\n const title = m[2].replace(/&/g, '&').replace(/</g, '<').replace(/>/g, '>').trim();\n items.push({ title, link: 'https://www.ptt.cc' + m[1] });\n if (items.length >= 20) break;\n}\nconst meta = $('Input (edit me)').first().json;\nconst list = items.map((n, i) => (i + 1) + '. ' + n.title).join('\\n');\nconst prompt = '\u4ee5\u4e0b\u662f PTT\u300c' + meta.board + '\u300d\u7248\u641c\u5c0b\u300c' + meta.keyword + '\u300d\u7684\u6700\u65b0\u8a0e\u8ad6\u6a19\u984c\u3002\u8acb\u7528\u7e41\u9ad4\u4e2d\u6587\u6574\u7406\u6210\u8f3f\u60c5\u5831\u544a\uff1a\\n1) \u4e3b\u8981\u8a0e\u8ad6\u4ec0\u9ebc\uff082-4 \u500b\u91cd\u9ede\uff09\\n2) \u6574\u9ad4\u98a8\u5411\u8207\u60c5\u7dd2\uff08\u6b63\u9762/\u8ca0\u9762/\u4e2d\u7acb\uff0c\u4e26\u7c21\u8ff0\uff09\\n3) \u503c\u5f97\u54c1\u724c\u6ce8\u610f\u7684\u9ede\\n\\n\u6a19\u984c\u6e05\u55ae\uff1a\\n' + (list || '\uff08\u9019\u6b21\u6c92\u6293\u5230\u6a19\u984c\uff0c\u53ef\u80fd\u662f\u770b\u677f\u6216\u95dc\u9375\u5b57\u9700\u8abf\u6574\uff09');\nreturn [{ json: { count: items.length, prompt } }];"
},
"id": "node-parse",
"name": "Parse PTT",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
400
]
},
{
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:11434/api/chat",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: 'qwen2.5:latest', messages: [ { role: 'system', content: '\u4f60\u662f\u53f0\u7063\u4eba\uff0c\u4e00\u5f8b\u4f7f\u7528\u53f0\u7063\u7e41\u9ad4\u4e2d\u6587\u8207\u53f0\u7063\u6163\u7528\u8a9e\u56de\u8986\uff0c\u7d55\u5c0d\u4e0d\u8981\u51fa\u73fe\u4efb\u4f55\u7c21\u9ad4\u5b57\u6216\u4e2d\u570b\u7528\u8a9e\u3002' }, { role: 'user', content: $json.prompt } ], stream: false }) }}",
"options": {
"timeout": 180000
}
},
"id": "node-ollama",
"name": "Summarize with Ollama",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1120,
400
]
},
{
"parameters": {
"jsCode": "const data = $input.first().json;\nlet summary = '';\ntry { summary = (data.message && data.message.content) || (data.content && data.content[0] && data.content[0].text) || data.response || ''; } catch (e) {}\nif (!summary) summary = JSON.stringify(data);\nreturn [{ json: { summary } }];"
},
"id": "node-extract",
"name": "Extract Result",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1340,
400
]
},
{
"parameters": {
"method": "POST",
"url": "https://discord.com/api/webhooks/REPLACE_WITH_YOUR_WEBHOOK_URL",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ content: ('\ud83d\udde3\ufe0f PTT \u8f3f\u60c5\u5831\u544a\\n\\n' + ($json.summary || '')).slice(0, 1900) }) }}",
"options": {}
},
"id": "node-discord",
"name": "Send to Discord",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1560,
400
]
}
],
"connections": {
"Schedule Trigger": {
"main": [
[
{
"node": "Input (edit me)",
"type": "main",
"index": 0
}
]
]
},
"Input (edit me)": {
"main": [
[
{
"node": "Fetch PTT",
"type": "main",
"index": 0
}
]
]
},
"Fetch PTT": {
"main": [
[
{
"node": "Parse PTT",
"type": "main",
"index": 0
}
]
]
},
"Parse PTT": {
"main": [
[
{
"node": "Summarize with Ollama",
"type": "main",
"index": 0
}
]
]
},
"Summarize with Ollama": {
"main": [
[
{
"node": "Extract Result",
"type": "main",
"index": 0
}
]
]
},
"Extract Result": {
"main": [
[
{
"node": "Send to Discord",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"tags": []
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
PTT 輿情監測 (PTT Sentiment Monitor · 本機 Ollama). Uses httpRequest. Scheduled trigger; 7 nodes.
Source: https://github.com/YuriCrystal/n8n-marketing-flows/blob/main/templates/04-ptt-sentiment-monitor.local-ollama.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
AI-Powered Short-Form Video Generator with OpenAI, Flux, Kling, and ElevenLabs and upload to all .... Uses httpRequest, googleDrive, discord, googleSheets. Scheduled trigger; 51 nodes.
Free Support: Setting up and getting the workflow tailord to your needs. One small free adjustment included.
Continuous quality checks for your production LLM prompts. Keeps a golden test set in n8n Data Tables, runs it on a schedule against any OpenAI-compatible API, compares each run to a blessed baseline,
This workflow aims to help you and your team track your expenses with OpenAI It automatically collects your OpenAI organization’s API usage and cost data every few days and saves it to a ready-to-use
This n8n workflow automates Kubernetes root cause analysis (RCA) and incident alerting by integrating with Loki, Prometheus, and Slack. It streamlines log collection, cluster health monitoring, and AI