n8n-nodes-extract-pdf
Version:
n8n node to extract text, images and tables from PDF with multilingual support, language detection and comprehensive test suite
79 lines (78 loc) • 1.9 kB
JSON
{
"name": "n8n-nodes-extract-pdf",
"version": "1.0.26",
"description": "n8n node to extract text, images and tables from PDF with multilingual support, language detection and comprehensive test suite",
"keywords": [
"n8n",
"pdf",
"extract",
"ocr",
"tesseract",
"text-extraction",
"pdf-parser",
"tables",
"images",
"pdf-processing",
"document-processing",
"multilingual",
"language-detection",
"testing",
"test-suite"
],
"license": "MIT",
"homepage": "https://n8n.io",
"author": "Created by AI",
"repository": {
"type": "git",
"url": "https://github.com/n8n-io/n8n-nodes-extract-pdf.git"
},
"main": "index.js",
"type": "commonjs",
"scripts": {
"build": "tsc",
"start": "node nodes/ExtractPdfNode/ExtractPdfNode.js",
"test": "jest",
"test:watch": "jest --watch",
"test:coverage": "jest --coverage",
"prepublishOnly": "npm run build"
},
"files": [
"dist",
"index.js"
],
"n8n": {
"credentials": [],
"nodes": [
"dist/nodes/ExtractPdfNode/ExtractPdfNode.node.js"
]
},
"dependencies": {
"franc": "^6.2.0",
"iso-639-3": "^3.0.1",
"n8n-nodes-extract-pdf": "file:",
"natural": "^6.5.0",
"pdf-img-convert": "^1.2.1",
"pdf-parse": "^1.1.1",
"pdf-table-extractor": "^1.0.3",
"semver": "^7.5.4",
"sharp": "^0.32.6",
"tesseract.js": "^4.1.1"
},
"optionalDependencies": {
"canvas": "^2.11.2"
},
"devDependencies": {
"@types/jest": "^29.5.14",
"@types/node": "^18.16.0",
"@types/pdf-parse": "^1.1.1",
"@types/sharp": "^0.32.0",
"jest": "^29.7.0",
"n8n-workflow": "*",
"pdfkit": "^0.16.0",
"ts-jest": "^29.2.6",
"typescript": "~4.6.0"
},
"peerDependencies": {
"n8n-workflow": "*"
}
}