n8n-nodes-ocrbro 0.1.0 → 0.1.2

package/README.md

@@ -0,0 +1,158 @@
+# n8n-nodes-ocrbro
+
+Extract text from images and PDFs in your n8n workflows. This community node provides OCR (Optical Character Recognition) for images using Tesseract.js and text extraction from PDF documents.
+
+![OCR Bro Node](https://img.shields.io/npm/v/n8n-nodes-ocrbro.svg)
+
+## Features
+
+- **OCR from Images** - Extract text from PNG, JPG, TIFF, BMP, and other image formats using Tesseract.js
+- **Extract Text from PDFs** - Pull text content from PDF documents
+- **Multi-language Support** - OCR supports 100+ languages via Tesseract language packs
+- **No External APIs** - All processing happens locally, no data leaves your server
+
+## Installation
+
+### Via n8n Community Nodes (Recommended)
+
+1. Open your n8n instance
+2. Go to **Settings** → **Community Nodes**
+3. Click **Install a community node**
+4. Enter: `n8n-nodes-ocrbro`
+5. Click **Install**
+6. Restart n8n when prompted
+
+## Video Tutorials
+
+### 1. How to install ocrbro n8n node for free?
+[![How to install ocrbro n8n node for free?](https://img.youtube.com/vi/v-SByxejyQ8/0.jpg)](https://youtu.be/v-SByxejyQ8)
+
+### 2. Example PDF Text Extraction
+[![Example PDF Text Extraction](https://img.youtube.com/vi/JpXKcSkO61o/0.jpg)](https://youtu.be/JpXKcSkO61o)
+
+### 3. Example Image Text extraction OCR
+[![Example Image Text extraction OCR](https://img.youtube.com/vi/sZb9GHWbtbo/0.jpg)](https://youtu.be/sZb9GHWbtbo)
+
+### 4. How to create Private n8n PDF text extraction API endpoint on n8n
+[![How to create Private n8n PDF text extraction API endpoint on n8n](https://img.youtube.com/vi/sZb9GHWbtbo/0.jpg)](https://youtu.be/sZb9GHWbtbo)
+
+### 5. How to create Private n8n Image text extraction API endpoint on n8n
+[![How to create Private n8n Image text extraction API endpoint on n8n](https://img.youtube.com/vi/crR1N8z0IHw/0.jpg)](https://youtu.be/crR1N8z0IHw)
+
+### Via npm (Self-hosted)
+
+```bash
+cd ~/.n8n/nodes
+npm install n8n-nodes-ocrbro
+# Restart n8n
+```
+
+### Docker
+
+Mount the node into your n8n container:
+
+```bash
+docker run -it --rm \
+  --name n8n \
+  -p 5678:5678 \
+  -e N8N_CUSTOM_EXTENSIONS="/home/node/.n8n/custom/n8n-nodes-ocrbro" \
+  -v n8n_data:/home/node/.n8n \
+  docker.n8n.io/n8nio/n8n
+```
+
+## Usage
+
+### OCR from Image
+
+Extract text from images using Tesseract OCR.
+
+1. Add **OCR Bro** node to your workflow
+2. Set **Operation** to `OCR from Image`
+3. Configure:
+   - **Input Binary Field**: Name of the binary property containing the image (default: `data`)
+   - **Language**: Tesseract language code (default: `eng`)
+
+**Example workflow:**
+```
+[Read Binary File] → [OCR Bro] → [Set Node]
+```
+
+**Supported image formats:** PNG, JPG/JPEG, TIFF, BMP, GIF, WebP
+
+**Language codes:**
+- `eng` - English
+- `deu` - German
+- `fra` - French
+- `spa` - Spanish
+- `chi_sim` - Chinese (Simplified)
+- `jpn` - Japanese
+- Multiple languages: `eng+deu+fra`
+
+### Extract Text from PDF
+
+Extract text content from PDF documents.
+
+1. Add **OCR Bro** node to your workflow
+2. Set **Operation** to `Extract Text from PDF`
+3. Configure:
+   - **Input Binary Field**: Name of the binary property containing the PDF (default: `data`)
+
+**Example workflow:**
+```
+[HTTP Request (PDF URL)] → [OCR Bro] → [Code Node]
+```
+
+**Output:**
+```json
+{
+  "text": "Extracted text content...",
+  "pages": 5
+}
+```
+
+## Examples
+
+### Basic Image OCR
+
+1. Use **Read Binary File** to load an image
+2. Connect to **OCR Bro** with operation `OCR from Image`
+3. Output contains `text`, `confidence`, and `words` count
+
+### Batch Process Images
+
+1. Use **Read Binary Files** to load multiple images
+2. Connect to **OCR Bro** 
+3. Each item will be processed and return extracted text
+
+### Process PDF and Send via Email
+
+1. **HTTP Request** - Download PDF from URL
+2. **OCR Bro** - Extract text (operation: `Extract Text from PDF`)
+3. **Send Email** - Include extracted text in email body
+
+
+
+## Troubleshooting
+
+### Node not appearing after installation
+- Restart your n8n instance
+- Check the n8n logs for any errors
+
+### Low OCR accuracy
+- Use higher resolution images (300 DPI recommended)
+- Ensure good contrast between text and background
+- Specify the correct language code
+- Pre-process images to remove noise if needed
+
+### PDF extraction returns empty text
+- The PDF may contain scanned images instead of text
+- For scanned PDFs, convert pages to images first, then use the OCR operation
+
+## License
+
+MIT
+
+## Links
+
+- [npm Package](https://www.npmjs.com/package/n8n-nodes-ocrbro)
+- [n8n Community Nodes](https://docs.n8n.io/integrations/community-nodes/)

package/dist/nodes/OcrBro/OcrBro.node.js

@@ -1,4 +1,37 @@
 "use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OcrBro = void 0;
 const tesseract_js_1 = require("tesseract.js");
@@ -10,27 +43,79 @@ class OcrBro {
             icon: 'file:ocrbro.png',
             group: ['transform'],
             version: 1,
-            description: 'OCR Images using Tesseract.js - extracts text from images',
+            description: 'Extract text from images (OCR) or PDFs',
             defaults: {
                 name: 'OCR Bro',
             },
             inputs: ['main'],
             outputs: ['main'],
             properties: [
+                {
+                    displayName: 'Operation',
+                    name: 'operation',
+                    type: 'options',
+                    noDataExpression: true,
+                    options: [
+                        {
+                            name: 'OCR from Image',
+                            value: 'ocrImage',
+                            description: 'Extract text from images using Tesseract OCR',
+                        },
+                        {
+                            name: 'Extract Text from PDF',
+                            value: 'extractPdf',
+                            description: 'Extract text from PDF documents',
+                        },
+                    ],
+                    default: 'ocrImage',
+                },
                 {
                     displayName: 'Input Binary Field',
                     name: 'binaryPropertyName',
                     type: 'string',
                     default: 'data',
                     required: true,
-                    description: 'The name of the binary property containing the image file to OCR',
+                    description: 'The name of the binary property containing the file',
                 },
                 {
                     displayName: 'Language',
                     name: 'language',
                     type: 'string',
                     default: 'eng',
-                    description: 'Tesseract language code (e.g., eng, deu, spa). Multiple languages can be specified separated by "+".',
+                    description: 'Tesseract language code (e.g., eng, deu, spa). Multiple languages can be separated by "+".',
+                    displayOptions: {
+                        show: {
+                            operation: ['ocrImage'],
+                        },
+                    },
+                },
+                {
+                    displayName: 'Password Protected?',
+                    name: 'isPasswordProtected',
+                    type: 'boolean',
+                    default: false,
+                    description: 'Whether the PDF file is encrypted/password protected',
+                    displayOptions: {
+                        show: {
+                            operation: ['extractPdf'],
+                        },
+                    },
+                },
+                {
+                    displayName: 'Password',
+                    name: 'password',
+                    type: 'string',
+                    typeOptions: {
+                        password: true,
+                    },
+                    default: '',
+                    description: 'The password required to unlock the PDF document',
+                    displayOptions: {
+                        show: {
+                            operation: ['extractPdf'],
+                            isPasswordProtected: [true],
+                        },
+                    },
                 },
             ],
         };
@@ -39,51 +124,96 @@ class OcrBro {
         var _a;
         const items = this.getInputData();
         const returnData = [];
+        const operation = this.getNodeParameter('operation', 0);
         const binaryPropertyName = this.getNodeParameter('binaryPropertyName', 0);
-        const language = this.getNodeParameter('language', 0);
-        // @ts-ignore
-        const worker = await (0, tesseract_js_1.createWorker)();
-        // @ts-ignore
-        await worker.loadLanguage(language);
-        // @ts-ignore
-        await worker.initialize(language);
-        for (let i = 0; i < items.length; i++) {
-            try {
-                const item = items[i];
-                // @ts-ignore - n8n types are sometimes weird with binary helpers in dry run
-                const binaryData = await this.helpers.getBinaryDataBuffer(i, binaryPropertyName);
-                const binaryMetadata = item.binary ? item.binary[binaryPropertyName] : undefined;
-                if (!binaryMetadata) {
-                    throw new Error(`Binary property "${binaryPropertyName}" does not exist on item ${i}`);
+        if (operation === 'ocrImage') {
+            const language = this.getNodeParameter('language', 0);
+            // @ts-ignore
+            const worker = await (0, tesseract_js_1.createWorker)();
+            // @ts-ignore
+            await worker.loadLanguage(language);
+            // @ts-ignore
+            await worker.initialize(language);
+            for (let i = 0; i < items.length; i++) {
+                try {
+                    const item = items[i];
+                    // @ts-ignore
+                    const binaryData = await this.helpers.getBinaryDataBuffer(i, binaryPropertyName);
+                    const binaryMetadata = item.binary ? item.binary[binaryPropertyName] : undefined;
+                    if (!binaryMetadata) {
+                        throw new Error(`Binary property "${binaryPropertyName}" does not exist on item ${i}`);
+                    }
+                    const mimeType = binaryMetadata.mimeType;
+                    if (!mimeType.startsWith('image/')) {
+                        throw new Error(`Unsupported file type: ${mimeType}. Use "Extract Text from PDF" for PDF files.`);
+                    }
+                    // @ts-ignore
+                    const { data } = await worker.recognize(binaryData);
+                    returnData.push({
+                        json: {
+                            text: data.text,
+                            confidence: data.confidence,
+                            words: ((_a = data.words) === null || _a === void 0 ? void 0 : _a.length) || 0,
+                        },
+                        binary: item.binary,
+                    });
                 }
-                const mimeType = binaryMetadata.mimeType;
-                if (!mimeType.startsWith('image/')) {
-                    throw new Error(`Unsupported file type: ${mimeType}. OCR Bro only supports image files (PNG, JPG, TIFF, BMP, etc.)`);
+                catch (error) {
+                    if (this.continueOnFail()) {
+                        returnData.push({ json: { error: error.message } });
+                        continue;
+                    }
+                    throw error;
                 }
-                // @ts-ignore
-                const { data } = await worker.recognize(binaryData);
-                returnData.push({
-                    json: {
-                        text: data.text,
-                        confidence: data.confidence,
-                        words: ((_a = data.words) === null || _a === void 0 ? void 0 : _a.length) || 0,
-                    },
-                    binary: item.binary,
-                });
             }
-            catch (error) {
-                if (this.continueOnFail()) {
+            await worker.terminate();
+        }
+        else if (operation === 'extractPdf') {
+            // Dynamic import for ESM module
+            const { extractText, getDocumentProxy } = await Promise.resolve().then(() => __importStar(require('unpdf')));
+            for (let i = 0; i < items.length; i++) {
+                try {
+                    const item = items[i];
+                    // @ts-ignore
+                    const binaryData = await this.helpers.getBinaryDataBuffer(i, binaryPropertyName);
+                    const binaryMetadata = item.binary ? item.binary[binaryPropertyName] : undefined;
+                    if (!binaryMetadata) {
+                        throw new Error(`Binary property "${binaryPropertyName}" does not exist on item ${i}`);
+                    }
+                    const mimeType = binaryMetadata.mimeType;
+                    if (mimeType !== 'application/pdf') {
+                        throw new Error(`Expected PDF file but got: ${mimeType}. Use "OCR from Image" for image files.`);
+                    }
+                    let pdfBufferToProcess = new Uint8Array(binaryData);
+                    const isPasswordProtected = this.getNodeParameter('isPasswordProtected', i, false);
+                    if (isPasswordProtected) {
+                        const password = this.getNodeParameter('password', i);
+                        const { PDFDocument } = await Promise.resolve().then(() => __importStar(require('@yongseok_choi/pdf-lib')));
+                        const pdfDoc = await PDFDocument.load(binaryData, {
+                            password: password,
+                            ignoreEncryption: true,
+                        });
+                        pdfBufferToProcess = (await pdfDoc.save());
+                    }
+                    const pdf = await getDocumentProxy(pdfBufferToProcess);
+                    const { text, totalPages } = await extractText(pdf, { mergePages: true });
                     returnData.push({
                         json: {
-                            error: error.message,
+                            text: text,
+                            pages: totalPages,
                         },
+                        binary: item.binary,
                     });
-                    continue;
                 }
-                throw error;
+                catch (error) {
+                    if (this.continueOnFail()) {
+                        returnData.push({ json: { error: error.message } });
+                        continue;
+                    }
+                    throw error;
+                }
             }
         }
-        await worker.terminate();
         return [returnData];
     }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "n8n-nodes-ocrbro",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Native n8n node for OCR using Tesseract.js",
   "keywords": [
     "n8n-community-node-package"
@@ -42,6 +42,9 @@
     "typescript": "^5.0.0"
   },
   "dependencies": {
-    "tesseract.js": "^4.0.0"
+    "@yongseok_choi/pdf-lib": "^2.2.6",
+    "pdf2json": "^4.0.0",
+    "tesseract.js": "^4.0.0",
+    "unpdf": "^1.4.0"
   }
-}
+}