This workflow follows the Chainllm → HTTP Request recipe pattern — see all workflows that pair these two integrations.
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 →
{
"nodes": [
{
"id": "6ea4e702-1af8-407b-b653-964a519db1c2",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1560,
-360
],
"parameters": {
"text": "=You are a highly skilled news categorizer, specializing in indentifying interesting stuff from Hacker News front-page headlines.\n\nYou are provided with JSON data containing a list of dates and their corresponding top headlines from the Hacker News front page. Each headline will also include a URL linking to the original article or discussion. Importantly, the dates provided will be the SAME DAY across MULTIPLE YEARS (e.g., January 1st, 2023, January 1st, 2022, January 1st, 2021, etc.). You need to indentify key headlines and also analyze how the tech landscape has evolved over the years, as reflected in the headlines for this specific day.\n\nYour task is to indentify top 10-15 headlines from across the years from the given json data and return in Markdown formatted bullet points categorizing into themes and adding markdown hyperlinks to the source URL with Prefixing Year before the headline. Follow the Output Foramt Mentioned.\n\n**Input Format:**\n\n```json\n[\n {\n \"headlines\": [\n \"Headline 1 Title [URL1]\",\n \"Headline 2 Title [URL2]\",\n \"Headline 3 Title [URL3]\",\n ...\n ]\n \"date\": \"YYYY-MM-DD\",\n },\n {\n \"headlines\": [\n \"Headline 1 Title [URL1]\",\n \"Headline 2 Title [URL2]\",\n ...\n ]\n \"date\": \"YYYY-MM-DD\",\n },\n ...\n]\n```\n\n**Output Format In Markdown**\n\n```\n# HN Lookback <FullMonthName-DD> | <start YYYY> to <end YYYY> \n\n## [Theme 1]\n- YYYY [Headline 1](URL1)\n- YYYY [Headline 2](URL2)\n...\n\n## [Theme 2]\n- YYYY [Headline 1](URL1)\n- YYYY [Headline 2](URL2)\n...\n\n... \n\n## <this is optional>\n<if any interesing ternds emerge mention them in oneline>\n```\n\n**Here is the Json data for Hackernews Headlines across the years**\n\n```\n{{ JSON.stringify($json.data) }}\n```",
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "b5a97c2a-0c3b-4ebe-aec5-7bca6b55ad4c",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1740,
-200
],
"parameters": {
"options": {},
"modelName": "models/gemini-1.5-pro"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "18cba750-aef5-451d-880f-2c12d8540d78",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-380,
-360
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 21
}
]
}
},
"typeVersion": 1.2
},
{
"id": "341da616-8670-4cd9-b47a-ee25e2ae9862",
"name": "CreateYearsList",
"type": "n8n-nodes-base.code",
"position": [
-200,
-360
],
"parameters": {
"jsCode": "for (const item of $input.all()) {\n const currentDateStr = item.json.timestamp.split('T')[0];\n const currentDate = new Date(currentDateStr);\n const currentYear = currentDate.getFullYear();\n const currentMonth = currentDate.getMonth(); // 0 for January, 1 for February, etc.\n const currentDay = currentDate.getDate();\n\n const datesToFetch = [];\n for (let year = currentYear; year >= 2007; year--) {\n let targetDate;\n if (year === 2007) {\n // Special handling for 2007 to start from Feb 19\n if (currentMonth > 1 || (currentMonth === 1 && currentDay >= 19))\n {\n targetDate = new Date(2007, 1, 19); // Feb 19, 2007\n } else {\n continue; // Skip 2007 if currentDate is before Feb 19\n }\n } else {\n targetDate = new Date(year, currentMonth, currentDay);\n }\n \n // Format the date as YYYY-MM-DD\n const formattedDate = targetDate.toISOString().split('T')[0];\n datesToFetch.push(formattedDate);\n }\n item.json.datesToFetch = datesToFetch;\n}\n\nreturn $input.all();"
},
"typeVersion": 2
},
{
"id": "42e24547-be24-4f29-8ce8-c0df7d47a6ff",
"name": "CleanUpYearList",
"type": "n8n-nodes-base.set",
"position": [
0,
-360
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b269dc0d-21e1-4124-8f3a-2c7bfa4add5c",
"name": "datesToFetch",
"type": "array",
"value": "={{ $json.datesToFetch }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "6e51ad05-0f3d-4bfb-8c8d-5b71e7355344",
"name": "SplitOutYearList",
"type": "n8n-nodes-base.splitOut",
"position": [
200,
-360
],
"parameters": {
"options": {},
"fieldToSplitOut": "datesToFetch"
},
"typeVersion": 1
},
{
"id": "6f827071-718f-4e27-9f7a-cc50296f7bc4",
"name": "GetFrontPage",
"type": "n8n-nodes-base.httpRequest",
"position": [
420,
-360
],
"parameters": {
"url": "=https://news.ycombinator.com/front",
"options": {
"batching": {
"batch": {
"batchSize": 1,
"batchInterval": 3000
}
}
},
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "day",
"value": "={{ $json.datesToFetch }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "7287e6b1-337f-4634-ac23-5ceaa87b0db3",
"name": "ExtractDetails",
"type": "n8n-nodes-base.html",
"position": [
640,
-360
],
"parameters": {
"options": {},
"operation": "extractHtmlContent",
"extractionValues": {
"values": [
{
"key": "=headlines",
"cssSelector": ".titleline",
"returnArray": true,
"skipSelectors": "span"
},
{
"key": "date",
"cssSelector": ".pagetop > font"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "fceff31e-4dcd-4199-89c5-8eb75cd479bf",
"name": "GetHeadlines",
"type": "n8n-nodes-base.set",
"position": [
920,
-460
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e1ce33e9-e4f8-4215-bbdb-156a955a0a97",
"name": "headlines",
"type": "array",
"value": "={{ $json.headlines }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "f7683614-7225-4f05-ba12-86b326fdb4a1",
"name": "GetDate",
"type": "n8n-nodes-base.set",
"position": [
920,
-280
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "fc1d15f6-a999-4d6b-a7bc-3ffa9427679e",
"name": "date",
"type": "string",
"value": "={{ $json.date }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "7e09ce85-ece1-46a0-aa59-8e3da66413b2",
"name": "MergeHeadlinesDate",
"type": "n8n-nodes-base.merge",
"position": [
1180,
-360
],
"parameters": {
"mode": "combine",
"options": {},
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "db3bf408-8179-4ca4-a5b4-8a390b68f994",
"name": "SingleJson",
"type": "n8n-nodes-base.aggregate",
"position": [
1380,
-360
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData"
},
"typeVersion": 1
},
{
"id": "2abbc0e9-ed1e-4ba0-9d2f-7c3cd314a0fe",
"name": "Telegram",
"type": "n8n-nodes-base.telegram",
"position": [
2020,
-360
],
"parameters": {
"text": "={{ $json.text }}",
"chatId": "@OnThisDayHN",
"additionalFields": {
"parse_mode": "Markdown",
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
}
],
"connections": {
"GetDate": {
"main": [
[
{
"node": "MergeHeadlinesDate",
"type": "main",
"index": 1
}
]
]
},
"SingleJson": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"GetFrontPage": {
"main": [
[
{
"node": "ExtractDetails",
"type": "main",
"index": 0
}
]
]
},
"GetHeadlines": {
"main": [
[
{
"node": "MergeHeadlinesDate",
"type": "main",
"index": 0
}
]
]
},
"ExtractDetails": {
"main": [
[
{
"node": "GetHeadlines",
"type": "main",
"index": 0
},
{
"node": "GetDate",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Telegram",
"type": "main",
"index": 0
}
]
]
},
"CleanUpYearList": {
"main": [
[
{
"node": "SplitOutYearList",
"type": "main",
"index": 0
}
]
]
},
"CreateYearsList": {
"main": [
[
{
"node": "CleanUpYearList",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "CreateYearsList",
"type": "main",
"index": 0
}
]
]
},
"SplitOutYearList": {
"main": [
[
{
"node": "GetFrontPage",
"type": "main",
"index": 0
}
]
]
},
"MergeHeadlinesDate": {
"main": [
[
{
"node": "SingleJson",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googlePalmApitelegramApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow automates the extraction and analysis of front-page news details from websites, using AI to process scheduled updates and deliver concise summaries via Telegram. It's ideal for journalists, researchers, or content curators who need regular insights into current events without manual browsing, saving hours of daily monitoring. The key step involves splitting a list of years or topics generated by code nodes, then fetching web content with HTTP requests and extracting key details using HTML parsing, before feeding it into a Google Gemini-powered LLM chain for intelligent summarisation.
Use this workflow for daily or weekly news digests focused on specific themes, such as historical events or ongoing stories, where Telegram notifications keep you informed on the go. Avoid it for real-time breaking news, as the cron trigger suits periodic rather than instant updates; opt for webhook triggers instead in those cases. Common variations include customising the year list for seasonal reports or integrating additional sources like RSS feeds for broader coverage.
About this workflow
Telegram Splitout. Uses chainLlm, lmChatGoogleGemini, scheduleTrigger, splitOut. Scheduled trigger; 13 nodes.
Source: https://github.com/Zie619/n8n-workflows — 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.
DailyQuote. Uses scheduleTrigger, httpRequest, telegram, chainLlm. Scheduled trigger; 17 nodes.
Get notified when the International Space Station passes over your location - but only when you can actually see it! This workflow combines real-time ISS tracking with weather condition checks to send
Stop finding out about updates after something breaks. Claude reads every changelog and tells you exactly what changed, what might break, and how urgent the update is — with a ready-to-run Docker upda
Ai Price Tracker. Uses scheduleTrigger, httpRequest, markdown, chainLlm. Scheduled trigger; 42 nodes.
This template is perfect for: AI art enthusiasts who want to stay updated on trending AI-generated artwork Content curators looking to automate art discovery Japanese-speaking users who want translate