test_pdf_endpoint.py

import asyncio
import aiohttp
import sys
import base64

async def test_pdf_extraction():
    # Check if filename is provided as argument
    if len(sys.argv) < 2:
        print("Usage: python test_pdf_endpoint.py <pdf_filename> [page_numbers]")
        return
    
    pdf_filename = sys.argv[1]
    page_numbers = sys.argv[2] if len(sys.argv) > 2 else None
    
    # Read the PDF file
    try:
        with open(pdf_filename, 'rb') as f:
            pdf_content = f.read()
    except FileNotFoundError:
        print(f"Error: File '{pdf_filename}' not found.")
        return
    except Exception as e:
        print(f"Error reading file: {e}")
        return
    
    # Test regular file upload endpoint
    print("\n--- Testing file upload endpoint ---")
    url = "http://localhost:8000/extract-text"
    if page_numbers:
        url += f"?page_numbers={page_numbers}"
    
    try:
        async with aiohttp.ClientSession() as session:
            data = aiohttp.FormData()
            data.add_field('file', pdf_content, filename=pdf_filename, content_type='application/pdf')
            
            async with session.post(
                url,
                data=data
            ) as response:
                result = await response.json()
                print(f"Status code: {response.status}")
                if response.status == 200:
                    print(f"Successfully extracted text from {result['filename']}")
                    print(f"Text length: {len(result['text'])} characters")
                    # Print first 500 characters of extracted text
                    print(f"First 500 characters: {result['text'][:500]}")
                else:
                    print(f"Error: {result}")
    except Exception as e:
        print(f"Error connecting to server: {e}")
        print("Make sure the FastAPI server is running on port 8000")
    
    # Test base64 endpoint
    print("\n--- Testing base64 endpoint ---")
    base64_url = "http://localhost:8000/extract-text-base64"
    
    try:
        # Encode the PDF content to base64
        base64_string = base64.b64encode(pdf_content).decode('utf-8')
        
        # Create JSON payload
        payload = {
            "file": base64_string,
            "filename": pdf_filename
        }
        if page_numbers:
            payload["page_numbers"] = page_numbers
        
        async with aiohttp.ClientSession() as session:
            async with session.post(
                base64_url,
                json=payload
            ) as response:
                result = await response.json()
                print(f"Status code: {response.status}")
                if response.status == 200:
                    print(f"Successfully extracted text from {result['filename']}")
                    print(f"Text length: {len(result['text'])} characters")
                    # Print first 500 characters of extracted text
                    print(f"First 500 characters: {result['text'][:500]}")
                else:
                    print(f"Error: {result}")
    except Exception as e:
        print(f"Error connecting to server: {e}")
        print("Make sure the FastAPI server is running on port 8000")

if __name__ == "__main__":
    asyncio.run(test_pdf_extraction())