backend/api/pdf_handler.py

from fastapi import APIRouter, UploadFile, File, HTTPException
import fitz  # PyMuPDF
import io

router = APIRouter()

@router.post("/extract")
async def extract_pdf(file: UploadFile = File(...)):
    """
    Receives a PDF file and extracts its text content using PyMuPDF.
    """
    if file.content_type != "application/pdf":
        raise HTTPException(status_code=400, detail="File must be a PDF")
    
    try:
        contents = await file.read()
        pdf_document = fitz.open(stream=contents, filetype="pdf")
        
        extracted_text = ""
        for page_num in range(len(pdf_document)):
            page = pdf_document.load_page(page_num)
            extracted_text += f"\n--- Seite {page_num + 1} ---\n"
            extracted_text += page.get_text()
            
        pdf_document.close()
        
        return {
            "filename": file.filename,
            "text": extracted_text,
            "pages": len(pdf_document)
        }
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))