{ "id": "LWWXKqrEi3hdNOy2", "meta": { "templateCredsSetupCompleted": true }, "name": "Extract tracking numbers from Gmail PDF attachments to Google Sheets with okraPDF OCR", "tags": [], "nodes": [ { "id": "ec424789-3e22-4124-9dd2-2308393103d2", "name": "Overview", "type": "n8n-nodes-base.stickyNote", "position": [ -2480, -352 ], "parameters": { "width": 480, "height": 560, "content": "## Extract tracking numbers from Gmail PDF attachments to Google Sheets with okraPDF OCR\n\nFor operations, ecommerce, logistics, and support teams that get scanned shipping labels or delivery PDFs in Gmail and need the tracking numbers logged in Google Sheets \u2014 without copying from images by hand.\n\n### How it works\n\n1. The Gmail trigger watches for messages with PDF attachments and downloads the first one.\n2. An IF node confirms the attachment is really a PDF.\n3. The PDF is uploaded to okraPDF and an OCR parse job is started.\n4. The workflow waits and polls the job until it reaches a terminal state.\n5. A row is appended to Google Sheets with the sender, subject, job status, tracking-number candidates found in the OCR text, and a short preview.\n\n### Setup\n\n- Add Gmail, Google Sheets, and okraPDF (HTTP Header Auth) credentials.\n- Get an okraPDF API key at okrapdf.com/settings/keys.\n- Pick your destination spreadsheet and sheet in the Google Sheets node.\n- In \"Configure OCR Options\", raise okra_parse_pages if labels span more than one page.\n\n### Customization\n\nEdit the tracking-number expression for carrier-specific formats, or duplicate the PDF branch to handle attachment_1 and beyond." }, "typeVersion": 1 }, { "id": "ce773849-4aac-4568-a005-406476a9a5d1", "name": "Section - Receive", "type": "n8n-nodes-base.stickyNote", "position": [ -1952, -336 ], "parameters": { "color": 7, "width": 420, "height": 360, "content": "## 1. Receive & filter PDF emails\n\nThe Gmail trigger downloads the first attachment; the IF node lets only real PDFs continue." }, "typeVersion": 1 }, { "id": "c50f31f6-3dfa-4f9a-9aa7-1553b7e889a1", "name": "Section - Upload & parse", "type": "n8n-nodes-base.stickyNote", "position": [ -1488, -336 ], "parameters": { "color": 7, "width": 620, "height": 360, "content": "## 2. Upload & start OCR\n\nSet OCR options, upload the PDF to okraPDF, and start an OCR parse job." }, "typeVersion": 1 }, { "id": "4681f65b-2c6f-4d39-916c-fa7ae781507b", "name": "Section - Poll & log", "type": "n8n-nodes-base.stickyNote", "position": [ -816, -336 ], "parameters": { "color": 7, "width": 840, "height": 360, "content": "## 3. Poll, then log to Sheets\n\nWait and re-poll the job until it's terminal, then append a tracking-number row to Google Sheets." }, "typeVersion": 1 }, { "id": "fb3f664e-48a2-48d2-915d-307dc713f4cf", "name": "Gmail Trigger - PDF Attachments", "type": "n8n-nodes-base.gmailTrigger", "position": [ -1904, -128 ], "parameters": { "simple": false, "filters": { "q": "has:attachment filename:pdf", "readStatus": "unread" }, "options": { "downloadAttachments": true, "dataPropertyAttachmentsPrefixName": "attachment_" }, "pollTimes": { "item": [ { "mode": "everyMinute" } ] } }, "credentials": { "gmailOAuth2": { "name": "" } }, "typeVersion": 1.4 }, { "id": "de87d992-c4fe-46c6-817b-5adab6359f9e", "name": "IF attachment_0 is PDF", "type": "n8n-nodes-base.if", "position": [ -1680, -128 ], "parameters": { "options": {}, "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict" }, "combinator": "and", "conditions": [ { "id": "has-attachment-0", "operator": { "type": "string", "operation": "equals" }, "leftValue": "={{ $binary.attachment_0?.mimeType || '' }}", "rightValue": "application/pdf" } ] } }, "typeVersion": 2.2 }, { "id": "980fa6e5-dd29-47f5-9648-9ddc0efb1cdf", "name": "Configure OCR Options", "type": "n8n-nodes-base.set", "position": [ -1456, -128 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "okra-parser", "name": "okra_parser", "type": "string", "value": "gemini-vision" }, { "id": "okra-parse-pages", "name": "okra_parse_pages", "type": "string", "value": "1" }, { "id": "okra-metadata-source", "name": "okra_metadata_source", "type": "string", "value": "n8n-gmail-tracking" } ] }, "includeOtherFields": true }, "typeVersion": 3.4 }, { "id": "6d93d0d4-4914-4fe3-bf32-404fec48f98b", "name": "Upload attachment_0 to okraPDF", "type": "n8n-nodes-base.httpRequest", "position": [ -1232, -128 ], "parameters": { "url": "https://api.okrapdf.com/v1/files", "method": "POST", "options": { "timeout": 300000 }, "sendBody": true, "contentType": "multipart-form-data", "authentication": "genericCredentialType", "bodyParameters": { "parameters": [ { "name": "file", "parameterType": "formBinaryData", "inputDataFieldName": "attachment_0" } ] }, "genericAuthType": "httpHeaderAuth" }, "credentials": { "httpHeaderAuth": { "name": "" } }, "typeVersion": 4.2 }, { "id": "e7068726-2075-479a-911f-df67b1c1305c", "name": "OCR Parse Uploaded PDF", "type": "n8n-nodes-base.httpRequest", "position": [ -1008, -128 ], "parameters": { "url": "https://api.okrapdf.com/v1/parse", "method": "POST", "options": { "timeout": 300000 }, "jsonBody": "={\n \"parser\": \"{{ $('Configure OCR Options').item.json.okra_parser || 'gemini-vision' }}\",\n \"file\": { \"id\": \"{{ $json.id }}\" },\n \"pages\": \"{{ $('Configure OCR Options').item.json.okra_parse_pages || '1' }}\",\n \"metadata\": { \"source\": \"{{ $('Configure OCR Options').item.json.okra_metadata_source || 'n8n-gmail-tracking' }}\" }\n}", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Content-Type", "value": "application/json" } ] } }, "credentials": { "httpHeaderAuth": { "name": "" } }, "typeVersion": 4.2 }, { "id": "824c49c6-5b94-46d3-9695-18f8849b6916", "name": "Wait for Parse Result", "type": "n8n-nodes-base.wait", "position": [ -784, -128 ], "parameters": { "amount": 15 }, "typeVersion": 1.1 }, { "id": "ca06c61e-0fea-4fad-bdac-03f17a351930", "name": "Get Job Result", "type": "n8n-nodes-base.httpRequest", "position": [ -560, -208 ], "parameters": { "url": "={{ ($json.status_url && $json.status_url.startsWith('http')) ? $json.status_url : ('https://api.okrapdf.com/v1/jobs/' + ($json.id || $json.job_id)) }}", "options": { "timeout": 300000, "response": { "response": { "responseFormat": "json" } } }, "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth" }, "credentials": { "httpHeaderAuth": { "name": "" } }, "typeVersion": 4.2 }, { "id": "78fa88fc-cec5-4c27-bacc-7ef036809c77", "name": "If Job Finished?", "type": "n8n-nodes-base.if", "position": [ -336, -128 ], "parameters": { "options": {}, "conditions": { "options": { "version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict" }, "combinator": "and", "conditions": [ { "id": "terminal-status", "operator": { "type": "string", "operation": "equals" }, "leftValue": "={{ ['succeeded','completed','completed_with_errors','failed','canceled','cancelled'].includes(($json.status || $json.internal_status || '').toLowerCase()) ? 'done' : 'pending' }}", "rightValue": "done" } ] } }, "typeVersion": 2.2 }, { "id": "76063812-ff91-4546-bbea-29592e4a7e9a", "name": "Append Tracking Row to Sheets", "type": "n8n-nodes-base.googleSheets", "position": [ -112, -128 ], "parameters": { "columns": { "value": { "result": "={{ $json.result.formats.nodes.pages }}" }, "schema": [ { "id": "object", "type": "string", "display": true, "required": false, "displayName": "object", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "id", "type": "string", "display": true, "removed": false, "required": false, "displayName": "id", "defaultMatch": true, "canBeUsedToMatch": true }, { "id": "type", "type": "string", "display": true, "required": false, "displayName": "type", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "url", "type": "string", "display": true, "required": false, "displayName": "url", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "created", "type": "string", "display": true, "required": false, "displayName": "created", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "livemode", "type": "string", "display": true, "required": false, "displayName": "livemode", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "job_id", "type": "string", "display": true, "required": false, "displayName": "job_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "owner_user_id", "type": "string", "display": true, "required": false, "displayName": "owner_user_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "job_type", "type": "string", "display": true, "required": false, "displayName": "job_type", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "job_label", "type": "string", "display": true, "required": false, "displayName": "job_label", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "status", "type": "string", "display": true, "required": false, "displayName": "status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "internal_status", "type": "string", "display": true, "required": false, "displayName": "internal_status", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "document_id", "type": "string", "display": true, "required": false, "displayName": "document_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "file_name", "type": "string", "display": true, "required": false, "displayName": "file_name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "run_id", "type": "string", "display": true, "required": false, "displayName": "run_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "workflow_name", "type": "string", "display": true, "required": false, "displayName": "workflow_name", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "workflow_id", "type": "string", "display": true, "required": false, "displayName": "workflow_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "engine_id", "type": "string", "display": true, "required": false, "displayName": "engine_id", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "provider", "type": "string", "display": true, "required": false, "displayName": "provider", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "model", "type": "string", "display": true, "required": false, "displayName": "model", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "progress_current", "type": "string", "display": true, "required": false, "displayName": "progress_current", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "progress_total", "type": "string", "display": true, "required": false, "displayName": "progress_total", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "progress", "type": "string", "display": true, "required": false, "displayName": "progress", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "pages_completed", "type": "string", "display": true, "required": false, "displayName": "pages_completed", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "pages_failed", "type": "string", "display": true, "required": false, "displayName": "pages_failed", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "pages_running", "type": "string", "display": true, "required": false, "displayName": "pages_running", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "pages_pending", "type": "string", "display": true, "required": false, "displayName": "pages_pending", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "pages_total", "type": "string", "display": true, "required": false, "displayName": "pages_total", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "chunks_completed", "type": "string", "display": true, "required": false, "displayName": "chunks_completed", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "chunks_total", "type": "string", "display": true, "required": false, "displayName": "chunks_total", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "cost_usd", "type": "string", "display": true, "required": false, "displayName": "cost_usd", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "duration_ms", "type": "string", "display": true, "required": false, "displayName": "duration_ms", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "error", "type": "string", "display": true, "required": false, "displayName": "error", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "latest_error", "type": "string", "display": true, "required": false, "displayName": "latest_error", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "last_error", "type": "string", "display": true, "required": false, "displayName": "last_error", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "request", "type": "string", "display": true, "required": false, "displayName": "request", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "result", "type": "string", "display": true, "required": false, "displayName": "result", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "metadata", "type": "string", "display": true, "required": false, "displayName": "metadata", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "created_at", "type": "string", "display": true, "required": false, "displayName": "created_at", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "updated_at", "type": "string", "display": true, "required": false, "displayName": "updated_at", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "completed_at", "type": "string", "display": true, "required": false, "displayName": "completed_at", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "completed", "type": "string", "display": true, "required": false, "displayName": "completed", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "id" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "append", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1Gg7QzB8Ap6XFBUsqAHKe865V-lt2e6QPm4rNqFud39I/edit#gid=0", "cachedResultName": "Sheet1" }, "documentId": { "__rl": true, "mode": "list", "value": "1Gg7QzB8Ap6XFBUsqAHKe865V-lt2e6QPm4rNqFud39I", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1Gg7QzB8Ap6XFBUsqAHKe865V-lt2e6QPm4rNqFud39I/edit?usp=drivesdk", "cachedResultName": "n8n-okra" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.4 } ], "active": true, "settings": { "binaryMode": "separate", "executionOrder": "v1" }, "versionId": "f41866bd-a4f3-476e-a573-762e57596745", "nodeGroups": [], "connections": { "Get Job Result": { "main": [ [ { "node": "If Job Finished?", "type": "main", "index": 0 } ] ] }, "If Job Finished?": { "main": [ [ { "node": "Append Tracking Row to Sheets", "type": "main", "index": 0 } ], [ { "node": "Wait for Parse Result", "type": "main", "index": 0 } ] ] }, "Configure OCR Options": { "main": [ [ { "node": "Upload attachment_0 to okraPDF", "type": "main", "index": 0 } ] ] }, "Wait for Parse Result": { "main": [ [ { "node": "Get Job Result", "type": "main", "index": 0 } ] ] }, "IF attachment_0 is PDF": { "main": [ [ { "node": "Configure OCR Options", "type": "main", "index": 0 } ] ] }, "OCR Parse Uploaded PDF": { "main": [ [ { "node": "Wait for Parse Result", "type": "main", "index": 0 } ] ] }, "Upload attachment_0 to okraPDF": { "main": [ [ { "node": "OCR Parse Uploaded PDF", "type": "main", "index": 0 } ] ] }, "Gmail Trigger - PDF Attachments": { "main": [ [ { "node": "IF attachment_0 is PDF", "type": "main", "index": 0 } ] ] } } }