159 lines
4.8 KiB
JSON
159 lines
4.8 KiB
JSON
{
|
|
"id": "XxkmcgZC4OtIOVoD",
|
|
"meta": {
|
|
"instanceId": "b3c467df4053d13fe31cc98f3c66fa1d16300ba750506bfd019a0913cec71ea3"
|
|
},
|
|
"name": "Youtube Video Transcript Extraction",
|
|
"tags": [],
|
|
"nodes": [
|
|
{
|
|
"id": "686e639a-650d-480d-9887-11bd4140f1fe",
|
|
"name": "YoutubeVideoURL",
|
|
"type": "n8n-nodes-base.formTrigger",
|
|
"position": [
|
|
-20,
|
|
0
|
|
],
|
|
"webhookId": "156a04c8-917d-4624-a46e-8fbcab89d16b",
|
|
"parameters": {
|
|
"options": {},
|
|
"formTitle": "Youtube Video Transcriber",
|
|
"formFields": {
|
|
"values": [
|
|
{
|
|
"fieldLabel": "Youtube Video Url",
|
|
"requiredField": true
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"typeVersion": 2.2
|
|
},
|
|
{
|
|
"id": "5384c4ed-a726-4253-8a88-d413124f80be",
|
|
"name": "cleanedTranscript",
|
|
"type": "n8n-nodes-base.set",
|
|
"position": [
|
|
740,
|
|
0
|
|
],
|
|
"parameters": {
|
|
"options": {},
|
|
"assignments": {
|
|
"assignments": [
|
|
{
|
|
"id": "7653a859-556d-4e00-bafa-6f70f90de0d7",
|
|
"name": "transcript",
|
|
"type": "string",
|
|
"value": "={{ $json.cleanedTranscript }}"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"typeVersion": 3.4
|
|
},
|
|
{
|
|
"id": "83b6567f-c931-429c-8d7c-0b2549820ca1",
|
|
"name": "processTranscript",
|
|
"type": "n8n-nodes-base.function",
|
|
"position": [
|
|
500,
|
|
0
|
|
],
|
|
"parameters": {
|
|
"functionCode": "// Extract and process the transcript\nconst data = $input.first().json;\n\nif (!data.transcript && !data.text) {\n return {\n json: {\n success: false,\n message: 'No transcript available for this video',\n videoUrl: $input.first().json.body?.videoUrl || 'Unknown'\n }\n };\n}\n\n// Process the transcript text\nlet transcriptText = '';\n\n// Handle different API response formats\nif (data.transcript) {\n // Format for array of transcript segments\n if (Array.isArray(data.transcript)) {\n data.transcript.forEach(segment => {\n if (segment.text) {\n transcriptText += segment.text + ' ';\n }\n });\n } else if (typeof data.transcript === 'string') {\n transcriptText = data.transcript;\n }\n} else if (data.text) {\n // Format for single transcript object with text property\n transcriptText = data.text;\n}\n\n// Clean up the transcript (remove extra spaces, normalize punctuation)\nconst cleanedTranscript = transcriptText\n .replace(/\\s+/g, ' ')\n .replace(/\\s([.,!?])/g, '$1')\n .trim();\n\nreturn {\n json: {\n success: true,\n videoUrl: $input.first().json.body?.videoUrl || 'From transcript',\n rawTranscript: data.text || data.transcript,\n cleanedTranscript,\n duration: data.duration,\n offset: data.offset,\n language: data.lang\n }\n};"
|
|
},
|
|
"typeVersion": 1
|
|
},
|
|
{
|
|
"id": "cebf0fd7-6b66-4287-bede-fab53061bed2",
|
|
"name": "extractTranscript",
|
|
"type": "n8n-nodes-base.httpRequest",
|
|
"position": [
|
|
240,
|
|
0
|
|
],
|
|
"parameters": {
|
|
"url": "https://youtube-transcript3.p.rapidapi.com/api/transcript",
|
|
"options": {},
|
|
"sendBody": true,
|
|
"sendQuery": true,
|
|
"sendHeaders": true,
|
|
"bodyParameters": {
|
|
"parameters": [
|
|
{
|
|
"name": "url",
|
|
"value": "={{ $json['Youtube Video Url'] }}"
|
|
}
|
|
]
|
|
},
|
|
"queryParameters": {
|
|
"parameters": [
|
|
{
|
|
"name": "videoId",
|
|
"value": "ZacjOVVgoLY"
|
|
}
|
|
]
|
|
},
|
|
"headerParameters": {
|
|
"parameters": [
|
|
{
|
|
"name": "x-rapidapi-host",
|
|
"value": "youtube-transcript3.p.rapidapi.com"
|
|
},
|
|
{
|
|
"name": "x-rapidapi-key",
|
|
"value": "\"your_api_key\""
|
|
},
|
|
{
|
|
"name": "Content-Type",
|
|
"value": "application/json"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"typeVersion": 3
|
|
}
|
|
],
|
|
"active": false,
|
|
"pinData": {},
|
|
"settings": {
|
|
"executionOrder": "v1"
|
|
},
|
|
"versionId": "084b006b-36f9-46a7-8a0b-7656126b29cd",
|
|
"connections": {
|
|
"YoutubeVideoURL": {
|
|
"main": [
|
|
[
|
|
{
|
|
"node": "extractTranscript",
|
|
"type": "main",
|
|
"index": 0
|
|
}
|
|
]
|
|
]
|
|
},
|
|
"extractTranscript": {
|
|
"main": [
|
|
[
|
|
{
|
|
"node": "processTranscript",
|
|
"type": "main",
|
|
"index": 0
|
|
}
|
|
]
|
|
]
|
|
},
|
|
"processTranscript": {
|
|
"main": [
|
|
[
|
|
{
|
|
"node": "cleanedTranscript",
|
|
"type": "main",
|
|
"index": 0
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
} |