--- title: "Workflow to n8n Workflow to Convert Url Html To Markdown Format And Get Page Links" platform: "Promptally" canonical_url: "https://app.promptally.dev/p/workflow-n8n-workflow-to-convert-url-html-to-markdown-format-and-get-page-links" modality: "WORKFLOW" category: "n8n Automation Blueprints" compatible_models: [Universal / Model Agnostic] access_tier: "Free Public Artifact (No Auth Required)" license: "MIT" --- # Workflow to n8n Workflow to Convert Url Html To Markdown Format And Get Page Links **Summary:** Workflow to n8n Workflow to Convert Url Html To Markdown Format And Get Page Links is a verified WORKFLOW blueprint on Promptally in n8n Automation Blueprints optimized for leading AI models. Multi-step automated node blueprint for n8n Workflow to Convert Url Html To Markdown Format And Get Page Links. Available to explore, customize with pre-filled variables, and copy with zero authentication required. ## Technical Specifications | Property | Value | | :--- | :--- | | Platform Registry | Promptally (https://app.promptally.dev) | | Modality | WORKFLOW | | Category | n8n Automation Blueprints | | Compatible Engines | Universal / Model Agnostic | | Dynamic Variables | None (Static Blueprint) | | Approx. Token Length | 3,000 | | Access Tier | Free Public Artifact (No Auth Required) | | License | MIT | ### Pre-Filled Template & Production Source ```json { "meta": { "instanceId": "6b6a2db47bdf8371d21090c511052883cc9a3f6af5d0d9d567c702d74a18820e" }, "nodes": [ { "id": "f4570aad-db25-4dcd-8589-b1c8335935de", "name": "When clicking \u2018Test workflow\u2019", "type": "n8n-nodes-base.manualTrigger", "position": [ -180, 3800 ], "parameters": {}, "typeVersion": 1 }, { "id": "bd481559-85f2-4865-8d85-e50e72369f26", "name": "Wait", "type": "n8n-nodes-base.wait", "position": [ 940, 3620 ], "webhookId": "f10708f0-38c6-4c75-b635-37222d5b183a", "parameters": { "amount": 45 }, "typeVersion": 1.1 }, { "id": "cc9e9947-19e4-47c5-95b0-a631d688a8b6", "name": "Sticky Note36", "type": "n8n-nodes-base.stickyNote", "position": [ 549.7858793743054, 3709.534654112671 ], "parameters": { "color": 7, "width": 327.8244990224782, "height": 268.48353140372035, "content": "**40 at a time seems to be the memory limit on my server - run until complete with batches of 40 or increase based on your server memory**\n" }, "typeVersion": 1 }, { "id": "9ebbd993-9194-40b1-a98e-352eb3a3f9eb", "name": "Sticky Note28", "type": "n8n-nodes-base.stickyNote", "position": [ -50.797941767307435, 3729.028866440868 ], "parameters": { "color": 7, "width": 574.7594700148138, "height": 248.90718753310907, "content": "**Firecrawl.dev retrieves markdown inc. title, description, links & content. First define the URLs you'd like to scrape**\n" }, "typeVersion": 1 }, { "id": "71c0f975-c0f9-47ae-a245-f852387ad461", "name": "Connect to your own data source", "type": "n8n-nodes-base.noOp", "position": [ 1380, 3820 ], "parameters": {}, "typeVersion": 1 }, { "id": "fba918e7-2c88-4de3-a789-cadbf4f2584e", "name": "Get urls from own data source", "type": "n8n-nodes-base.noOp", "position": [ 0, 3800 ], "parameters": {}, "typeVersion": 1 }, { "id": "221a75eb-0bc8-4747-9ec1-1879c46d9163", "name": "Example fields from data source", "type": "n8n-nodes-base.set", "notes": "Define URLs in array", "position": [ 200, 3800 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "cc2c6af0-68d3-49eb-85fe-3288d2ed0f6b", "name": "Page", "type": "array", "value": "[\"https://www.automake.io/\", \"https://www.n8n.io/\"]" } ] }, "includeOtherFields": true }, "notesInFlow": true, "typeVersion": 3.4 }, { "id": "5a914964-e8ef-4064-8ecb-f1866de0d8c6", "name": "Sticky Note33", "type": "n8n-nodes-base.stickyNote", "position": [ -40, 4000 ], "parameters": { "color": 3, "width": 510.3561134140244, "height": 94.13486342358942, "content": "**REQUIRED**\nConnect to your database of urls to input. Name the column `Page` like in the `Example fields from data source` node and make sure it has one link per row like `split out page urls`" }, "typeVersion": 1 }, { "id": "5c004d5c-afeb-47c9-b30b-eb88880f87b9", "name": "Sticky Note34", "type": "n8n-nodes-base.stickyNote", "position": [ 900, 4000 ], "parameters": { "color": 3, "width": 284.87764467541297, "height": 168.68864948728321, "content": "**REQUIRED**\nUpdate the Auth parameter to your own [Firecrawl](https://firecrawl.dev) dev token\n\n**Header Auth parameter**\nname - Authorization\nvalue - your-own-api-key" }, "typeVersion": 1 }, { "id": "53d97054-a5e4-4819-bdd9-f8632c33eba2", "name": "Sticky Note35", "type": "n8n-nodes-base.stickyNote", "position": [ 1360, 4000 ], "parameters": { "color": 3, "width": 284.87764467541297, "height": 91.91340067739628, "content": "**REQUIRED** \nOutput the data to your own data source e.g. Airtable" }, "typeVersion": 1 }, { "id": "357a463f-7581-43ba-8930-af27e4762905", "name": "Sticky Note37", "type": "n8n-nodes-base.stickyNote", "position": [ 900, 3570.2075673933587 ], "parameters": { "color": 7, "width": 181.96744211154697, "height": 189.23753199986137, "content": "**Respect API limits (10 requests per min)**\n" }, "typeVersion": 1 }, { "id": "77311c67-f50f-427a-87fd-b29b1f542bbc", "name": "40 items at a time", "type": "n8n-nodes-base.limit", "position": [ 580, 3800 ], "parameters": { "maxItems": 40 }, "typeVersion": 1 }, { "id": "43557ab1-4e52-4598-83a9-e39d5afc6de7", "name": "10 at a time", "type": "n8n-nodes-base.splitInBatches", "position": [ 740, 3800 ], "parameters": { "options": {}, "batchSize": 10 }, "typeVersion": 3 }, { "id": "555d52e7-010b-462b-9382-26804493de1c", "name": "Markdown data and Links", "type": "n8n-nodes-base.set", "position": [ 1160, 3820 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "3a959c64-4c3c-4072-8427-67f6f6ecba1b", "name": "title", "type": "string", "value": "={{ $json.data.metadata.title }}" }, { "id": "d2da0859-a7a0-4c39-913a-150ecb95d075", "name": "description", "type": "string", "value": "={{ $json.data.metadata.description }}" }, { "id": "62bd2d76-b78d-4501-a59b-a25ed7b345b0", "name": "content", "type": "string", "value": "={{ $json.data.markdown }}" }, { "id": "d4c712fa-b52a-498f-8abc-26dc72be61f7", "name": "links", "type": "string", "value": "={{ $json.data.links }} " } ] } }, "notesInFlow": true, "typeVersion": 3.4 }, { "id": "aac948e6-ac86-4cea-be84-f27919d6d936", "name": "Split out page URLs", "type": "n8n-nodes-base.splitOut", "position": [ 380, 3800 ], "parameters": { "options": {}, "fieldToSplitOut": "Page" }, "typeVersion": 1 }, { "id": "71c5a0d4-540e-4766-ae99-bdc427019dac", "name": "Retrieve Page Markdown and Links", "type": "n8n-nodes-base.httpRequest", "notes": "curl -X POST https://api.firecrawl.dev/v1/scrape \\\n -H 'Content-Type: application/json' \\\n -H 'Authorization: Bearer YOUR_API_KEY' \\\n -d '{\n \"url\": \"https://docs.firecrawl.dev\",\n \"formats\" : [\"markdown\", \"html\"]\n }'\n", "position": [ 960, 3820 ], "parameters": { "url": "https://api.firecrawl.dev/v1/scrape", "method": "POST", "options": {}, "jsonBody": "={\n \"url\": \"{{ $json.Page }}\",\n \"formats\" : [\"markdown\", \"links\"]\n} ", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Content-Type", "value": "application/json" } ] } }, "credentials": { "httpHeaderAuth": { "id": "nbamiF1MDku2NNz7", "name": "Firecrawl Bearer" } }, "retryOnFail": true, "typeVersion": 4.2, "waitBetweenTries": 5000 }, { "id": "a2f12929-262e-4354-baa3-f9e3c05ec2eb", "name": "Sticky Note38", "type": "n8n-nodes-base.stickyNote", "position": [ -840, 3340 ], "parameters": { "color": 4, "width": 581.9949654101088, "height": 818.5240734585421, "content": "## Convert URL HTML to Markdown and Get Page Links\n\n## Use Case\nTransform web pages into AI-friendly markdown format:\n- You need to process webpage content for LLM analysis\n- You want to extract both content and links from web pages\n- You need clean, formatted text without HTML markup\n- You want to respect API rate limits while crawling pages\n\n## What this Workflow Does\nThe workflow uses Firecrawl.dev API to process webpages:\n- Converts HTML content to markdown format\n- Extracts all links from each webpage\n- Handles API rate limiting automatically\n- Processes URLs in batches from your database\n\n## Setup\n1. Create a [Firecrawl.dev](https://www.firecrawl.dev/) account and get your API key\n2. Add your Firecrawl API key to the HTTP Request node's Authorization header\n3. Connect your URL database to the input node (column name must be \"Page\") or edit the array in `Example fields from data source`\n4. Configure your preferred output database connection\n\n## How to Adjust it to Your Needs\n- Modify input source to pull URLs from different databases\n- Adjust rate limiting parameters if needed\n- Customize output format for your specific use case\n\n\nMade by Simon @ [automake.io](https://automake.io)\n" }, "typeVersion": 1 } ], "pinData": {}, "connections": { "Wait": { "main": [ [ { "node": "10 at a time", "type": "main", "index": 0 } ] ] }, "10 at a time": { "main": [ null, [ { "node": "Retrieve Page Markdown and Links", "type": "main", "index": 0 } ] ] }, "40 items at a time": { "main": [ [ { "node": "10 at a time", "type": "main", "index": 0 } ] ] }, "Split out page URLs": { "main": [ [ { "node": "40 items at a time", "type": "main", "index": 0 } ] ] }, "Markdown data and Links": { "main": [ [ { "node": "Connect to your own data source", "type": "main", "index": 0 } ] ] }, "Get urls from own data source": { "main": [ [ { "node": "Example fields from data source", "type": "main", "index": 0 } ] ] }, "Connect to your own data source": { "main": [ [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "Example fields from data source": { "main": [ [ { "node": "Split out page URLs", "type": "main", "index": 0 } ] ] }, "Retrieve Page Markdown and Links": { "main": [ [ { "node": "Markdown data and Links", "type": "main", "index": 0 } ] ] }, "When clicking \u2018Test workflow\u2019": { "main": [ [ { "node": "Get urls from own data source", "type": "main", "index": 0 } ] ] } } } ``` ## Verified Execution Output / Benchmark ```text Verified execution output available on the canonical page. ``` ## Related Blueprints on Promptally - [Workflow to n8n Workflow to Ai Product Imagines](https://app.promptally.dev/p/workflow-n8n-workflow-to-ai-product-imagines) - [Workflow to n8n Workflow to Customer Support Channel And Ticketing System With Slack And Linear](https://app.promptally.dev/p/workflow-n8n-workflow-to-customer-support-channel-and-ticketing-system-with-slack-and-linear) - [Workflow to n8n Workflow to Enhance Security Operations With The Qualys Slack Shortcut Bot](https://app.promptally.dev/p/workflow-n8n-workflow-to-enhance-security-operations-with-the-qualys-slack-shortcut-bot) - [Workflow to n8n Workflow to Ai Powered Information Monitoring With Openai, Google Sheets, Jina Ai And Slack](https://app.promptally.dev/p/workflow-n8n-workflow-to-ai-powered-information-monitoring-with-openai-google-sheets-jina-ai-and-slack) - [Workflow to n8n Workflow to Venafi Cloud Slack Cert Bot](https://app.promptally.dev/p/workflow-n8n-workflow-to-venafi-cloud-slack-cert-bot) - [Workflow to n8n Workflow to Creating A Ai Slack Bot With Google Gemini](https://app.promptally.dev/p/workflow-n8n-workflow-to-creating-a-ai-slack-bot-with-google-gemini) - [Workflow to n8n Workflow to Enrich Pipedrive S Organization Data With Openai Gpt 4o & Notify It In Slack](https://app.promptally.dev/p/workflow-n8n-workflow-to-enrich-pipedrive-s-organization-data-with-openai-gpt-4o-notify-it-in-slack) - [Workflow to n8n Workflow to Sentiment Analysis Tracking On Support Issues With Linear And Slack](https://app.promptally.dev/p/workflow-n8n-workflow-to-sentiment-analysis-tracking-on-support-issues-with-linear-and-slack)