{
  "id": "TApiWf20Corpus01",
  "name": "Playlist → Full Text Corpus (CSV/JSON) (TranscriptAPI)",
  "nodes": [
    {
      "parameters": {},
      "id": "20202020-2020-4020-8020-202020202001",
      "name": "Start",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        -260,
        0
      ]
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "20202020-2020-4020-8020-2020202020a1",
              "name": "playlistUrl",
              "value": "REPLACE_WITH_PLAYLIST_URL_OR_ID",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "id": "20202020-2020-4020-8020-202020202002",
      "name": "Set Playlist",
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        -40,
        0
      ]
    },
    {
      "parameters": {
        "url": "https://transcriptapi.com/api/v2/youtube/playlist/videos",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "playlist",
              "value": "={{ $json.playlistUrl }}"
            }
          ]
        },
        "options": {}
      },
      "id": "20202020-2020-4020-8020-202020202003",
      "name": "Get Playlist Videos",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        180,
        0
      ],
      "credentials": {
        "httpHeaderAuth": {
          "id": "REPLACE_TRANSCRIPTAPI_CRED_ID",
          "name": "TranscriptAPI - Authorization Bearer"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "// One item per playlist video (watch URL + title).\nconst data = $input.first().json;\nreturn (data.results || []).map((v) => ({\n  json: { videoId: v.videoId, videoTitle: v.title || null, videoUrl: 'https://www.youtube.com/watch?v=' + v.videoId },\n}));"
      },
      "id": "20202020-2020-4020-8020-202020202004",
      "name": "Extract Video List",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        400,
        0
      ]
    },
    {
      "parameters": {
        "maxItems": 10
      },
      "id": "20202020-2020-4020-8020-202020202005",
      "name": "Keep First 10",
      "type": "n8n-nodes-base.limit",
      "typeVersion": 1,
      "position": [
        620,
        0
      ]
    },
    {
      "parameters": {
        "url": "https://transcriptapi.com/api/v2/youtube/transcript",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "video_url",
              "value": "={{ $json.videoUrl }}"
            },
            {
              "name": "format",
              "value": "json"
            },
            {
              "name": "send_metadata",
              "value": "true"
            }
          ]
        },
        "options": {}
      },
      "id": "20202020-2020-4020-8020-202020202006",
      "name": "Get Transcript (TranscriptAPI)",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        840,
        0
      ],
      "credentials": {
        "httpHeaderAuth": {
          "id": "REPLACE_TRANSCRIPTAPI_CRED_ID",
          "name": "TranscriptAPI - Authorization Bearer"
        }
      },
      "onError": "continueRegularOutput"
    },
    {
      "parameters": {
        "jsCode": "// One CSV/JSON-ready row per video: metadata + full transcript text.\nconst out = [];\nfor (const item of $input.all()) {\n  const d = item.json;\n  const seg = Array.isArray(d.transcript) ? d.transcript : [];\n  if (seg.length === 0) continue; // skip videos without captions\n  const meta = d.metadata || {};\n  const vid = d.video_id;\n  const transcriptText = seg.map((s) => s.text).join(' ');\n  out.push({\n    json: {\n      videoId: vid,\n      title: meta.title || null,\n      author: meta.author_name || null,\n      videoUrl: 'https://www.youtube.com/watch?v=' + vid,\n      language: d.language || null,\n      segmentCount: seg.length,\n      wordCount: transcriptText.split(' ').filter((w) => w.length > 0).length,\n      transcriptText,\n    },\n  });\n}\nreturn out;"
      },
      "id": "20202020-2020-4020-8020-202020202007",
      "name": "Format Corpus Rows",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1060,
        0
      ]
    }
  ],
  "connections": {
    "Start": {
      "main": [
        [
          {
            "node": "Set Playlist",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set Playlist": {
      "main": [
        [
          {
            "node": "Get Playlist Videos",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Playlist Videos": {
      "main": [
        [
          {
            "node": "Extract Video List",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Video List": {
      "main": [
        [
          {
            "node": "Keep First 10",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Keep First 10": {
      "main": [
        [
          {
            "node": "Get Transcript (TranscriptAPI)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Transcript (TranscriptAPI)": {
      "main": [
        [
          {
            "node": "Format Corpus Rows",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "pinData": {}
}