Getting Started

Transform your document processing workflow with Anyparser’s powerful SDK. In this guide, you’ll learn how to set up the SDK, authenticate your application, and start extracting structured data from documents in minutes. Whether you’re building an enterprise document automation system or integrating document intelligence into your application, we’ll get you up and running quickly with clean, production-ready code examples.

Prerequisites

Before diving in, make sure you have:

Node.js 20.x+ or Python 3.8+ installed
An API key from Anyparser Studio
Basic familiarity with async/await programming

Installation

Choose your SDK
Install the Anyparser SDK for your preferred language:
- Python
- JavaScript
Terminal window
pip install anyparser-core
Terminal window
# Using npm npm install @anyparser/core # Using yarn yarn add @anyparser/core # Using pnpm pnpm add @anyparser/core

Set up authentication
Get your API key from Anyparser Studio and set it up:

Python
JavaScript

from anyparser_core import Anyparser
import asyncio

# Initialize with your API key
parser = Anyparser(api_key="your-api-key")

import { Anyparser } from '@anyparser/core';

// Initialize with your API key
const parser = new Anyparser({
  apiKey: 'your-api-key'
});

Parse your first document
Let’s try parsing a simple PDF document:

Python
JavaScript

async def main():
    # Parse a single document
    result = await parser.parse("path/to/document.pdf")
    print(f"Extracted {result.total_characters} characters")
    print(result.markdown)  # Get markdown formatted content

asyncio.run(main())

async function main() {
  // Parse a single document
  const result = await parser.parse('path/to/document.pdf');
  console.log(`Extracted ${result.totalCharacters} characters`);
  console.log(result.markdown);  // Get markdown formatted content
}

main().catch(console.error);

Features at a Glance

📄 Document Processing: Parse PDFs, Word documents, and more
🔍 OCR Support: Extract text from images and scanned documents
🌐 Web Crawling: Process content from websites and HTML
🤖 AI Integration: Ready-to-use with LangChain, LlamaIndex, and more

What’s Next?

Now that you’re set up, explore these guides to make the most of Anyparser:

Parse Documents Guide - Learn about document parsing options and features
OCR Guide - Extract text from images and scanned documents
Web Crawling Guide - Process web content effectively
API Reference - Explore the complete API documentation
Studio Dashboard - Monitor usage and manage your account