Extracto OCR — Folder Watcher

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 →

{
  "name": "Extracto OCR \u2014 folder watcher",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "value": 1
            }
          ]
        }
      },
      "id": "trigger",
      "name": "Every minute",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "command": "ls -1 /data/incoming/*.{pdf,png,jpg,jpeg} 2>/dev/null"
      },
      "id": "list-files",
      "name": "List new files",
      "type": "n8n-nodes-base.executeCommand",
      "typeVersion": 1,
      "position": [
        460,
        300
      ]
    },
    {
      "parameters": {
        "fileSelector": "={{$json.stdout}}",
        "options": {
          "encoding": "base64"
        }
      },
      "id": "read-file",
      "name": "Read file as base64",
      "type": "n8n-nodes-base.readBinaryFiles",
      "typeVersion": 1,
      "position": [
        680,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "={{$env.EXTRACTO_URL}}/api/v1/ocr/batch",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer {{$env.EXTRACTO_TOKEN}}"
            },
            {
              "name": "Origin",
              "value": "={{$env.EXTRACTO_URL}}"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyContentType": "json",
        "jsonBody": "={ \"files\": [ { \"fileName\": $json.fileName, \"model\": \"anthropic/claude-haiku-4.5\", \"preview\": \"data:application/pdf;base64,\" + $binary.data.data } ] }"
      },
      "id": "submit",
      "name": "Submit to Extracto",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        900,
        300
      ]
    }
  ],
  "connections": {
    "Every minute": {
      "main": [
        [
          {
            "node": "List new files",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "List new files": {
      "main": [
        [
          {
            "node": "Read file as base64",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Read file as base64": {
      "main": [
        [
          {
            "node": "Submit to Extracto",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "saveDataSuccessExecution": "all",
    "saveExecutionProgress": true
  }
}

About this workflow

Extracto OCR — folder watcher. Uses executeCommand, readBinaryFiles, httpRequest. Scheduled trigger; 4 nodes.

Source: https://github.com/codelined-ag/Extracto/blob/e48c332fe01cb8a41b83c775b3db2ddad02e4816/examples/n8n_workflow.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.