{ "id": "yt-transcript-04", "meta": { "instanceId": "vorlux-hub" }, "name": "Vorlux AI | YouTube Transcript Pull (Daily)", "active": true, "nodes": [ { "id": "d4e5f6a7-0004-4ddd-8004-000000000001", "name": "Daily 6am", "type": "n8n-nodes-base.scheduleTrigger", "typeVersion": 1.2, "position": [220, 300], "parameters": { "rule": { "interval": [ { "field": "hours", "hoursInterval": 24 } ] } } }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000011", "name": "Webhook Trigger", "type": "n8n-nodes-base.webhook", "typeVersion": 2, "position": [220, 500], "parameters": { "path": "youtube-transcript-pull", "httpMethod": "POST", "responseMode": "onReceived", "options": {} } }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000002", "name": "Get Recent Videos", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [460, 300], "parameters": { "method": "GET", "url": "={{$env.VORLUX_HUB_URL}}/api/integrations/youtube?action=search&limit=20&missing_transcript=true", "options": { "timeout": 15000 } }, "notes": "Gets recent videos that don't have transcripts yet" }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000003", "name": "Has Videos?", "type": "n8n-nodes-base.if", "typeVersion": 2, "position": [700, 300], "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict" }, "conditions": [ { "leftValue": "={{ ($json.data || []).length > 0 }}", "rightValue": "true", "operator": { "type": "string", "operation": "equals" } } ], "combinator": "and" } } }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000004", "name": "Pull Transcripts", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [940, 200], "notes": "For each video, attempts to pull transcript using 4 fallback methods", "parameters": { "mode": "runOnceForAllItems", "jsCode": "const videos = $input.first().json.data || [];\nconst hubUrl = $env.VORLUX_HUB_URL || 'http://localhost:3010';\nconst results = [];\n\nfor (const video of videos.slice(0, 10)) {\n const videoId = video.video_id || video.videoId || video.id;\n let transcript = '';\n let method = 'none';\n \n // Method 1: Hub's built-in transcript fetcher\n try {\n const r1 = await fetch(hubUrl + '/api/integrations/youtube/liked-pipeline', {\n method: 'POST',\n headers: { 'Content-Type': 'application/json' },\n body: JSON.stringify({ videoId, action: 'fetch_transcript' }),\n signal: AbortSignal.timeout(30000)\n });\n const d1 = await r1.json();\n if (d1.data?.transcript && d1.data.transcript.length > 100) {\n transcript = d1.data.transcript;\n method = 'hub_api';\n }\n } catch {}\n \n // Method 2: YouTube transcript API (supadata)\n if (!transcript) {\n try {\n const r2 = await fetch(`https://api.supadata.ai/v1/youtube/transcript?videoId=${videoId}&text=true`, {\n signal: AbortSignal.timeout(15000)\n });\n const d2 = await r2.json();\n if (d2.content && d2.content.length > 100) {\n transcript = d2.content;\n method = 'supadata';\n }\n } catch {}\n }\n \n // Method 3: youtube-transcript-api via local proxy\n if (!transcript) {\n try {\n const r3 = await fetch(hubUrl + '/api/integrations/youtube/transcript?videoId=' + videoId, {\n signal: AbortSignal.timeout(20000)\n });\n const d3 = await r3.json();\n if (d3.data?.transcript && d3.data.transcript.length > 100) {\n transcript = d3.data.transcript;\n method = 'local_proxy';\n }\n } catch {}\n }\n \n // Method 4: Auto-generated captions via YouTube innertube\n if (!transcript) {\n try {\n const r4 = await fetch(`https://www.youtube.com/watch?v=${videoId}`, { signal: AbortSignal.timeout(10000) });\n const html = await r4.text();\n const captionMatch = html.match(/\"captionTracks\":\\[\\{\"baseUrl\":\"([^\"]+)\"/);\n if (captionMatch) {\n const captionUrl = captionMatch[1].replace(/\\\\u0026/g, '&');\n const cRes = await fetch(captionUrl, { signal: AbortSignal.timeout(10000) });\n const cXml = await cRes.text();\n transcript = cXml.replace(/<[^>]+>/g, ' ').replace(/\\s+/g, ' ').trim();\n method = 'innertube_captions';\n }\n } catch {}\n }\n \n results.push({\n videoId,\n title: video.title || '',\n transcriptLength: transcript.length,\n method,\n hasTranscript: transcript.length > 100,\n transcript: transcript.substring(0, 10000)\n });\n}\n\nreturn [{ json: { results, pulled: results.filter(r => r.hasTranscript).length, total: results.length } }];" } }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000005", "name": "Store Transcripts", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [1200, 200], "notes": "Stores each pulled transcript back to the Hub content_projects table", "parameters": { "mode": "runOnceForAllItems", "jsCode": "const results = $input.first().json.results || [];\nconst hubUrl = $env.VORLUX_HUB_URL || 'http://localhost:3010';\nlet stored = 0;\n\nfor (const r of results.filter(r => r.hasTranscript)) {\n try {\n await fetch(hubUrl + '/api/content/pipeline', {\n method: 'POST',\n headers: { 'Content-Type': 'application/json' },\n body: JSON.stringify({\n action: 'store_transcript',\n videoId: r.videoId,\n title: r.title,\n transcript: r.transcript,\n method: r.method,\n source: 'youtube_transcript_pull'\n }),\n signal: AbortSignal.timeout(10000)\n });\n stored++;\n } catch {}\n}\n\nreturn [{ json: { stored, total: results.length, pulled: results.filter(r => r.hasTranscript).length, methods: results.reduce((acc, r) => { acc[r.method] = (acc[r.method] || 0) + 1; return acc; }, {}) } }];" } }, { "id": "d4e5f6a7-0004-4ddd-8004-000000000006", "name": "Discord Notify", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [1440, 200], "parameters": { "method": "POST", "url": "={{$env.DISCORD_CONTENT_WEBHOOK}}", "sendBody": true, "specifyBody": "json", "jsonBody": "={\"embeds\":[{\"title\":\"YouTube Transcripts Pulled\",\"description\":\"Pulled: {{ $json.pulled }}/{{ $json.total }} videos\\nStored: {{ $json.stored }}\\nMethods: {{ JSON.stringify($json.methods) }}\",\"color\":16711680,\"footer\":{\"text\":\"YouTube Transcript Pull - Daily\"}}]}", "options": { "timeout": 10000 } } } ], "connections": { "Daily 6am": { "main": [ [ { "node": "Get Recent Videos", "type": "main", "index": 0 } ] ] }, "Webhook Trigger": { "main": [ [ { "node": "Get Recent Videos", "type": "main", "index": 0 } ] ] }, "Get Recent Videos": { "main": [ [ { "node": "Has Videos?", "type": "main", "index": 0 } ] ] }, "Has Videos?": { "main": [ [ { "node": "Pull Transcripts", "type": "main", "index": 0 } ], [] ] }, "Pull Transcripts": { "main": [ [ { "node": "Store Transcripts", "type": "main", "index": 0 } ] ] }, "Store Transcripts": { "main": [ [ { "node": "Discord Notify", "type": "main", "index": 0 } ] ] } }, "settings": { "executionOrder": "v1", "saveManualExecutions": true, "saveExecutionProgress": true }, "tags": [ { "name": "youtube" }, { "name": "transcript" }, { "name": "content" } ], "versionId": "2" }