app.py

from fastapi import FastAPI, File, UploadFile
import fitz  # PyMuPDF
import pytesseract
from PIL import Image
import io

app = FastAPI()

@app.post("/extract-text")
async def extract_text(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        doc = fitz.open(stream=contents, filetype="pdf")

        extracted_text = ""
        for i, page in enumerate(doc):
            extracted_text += f"\n\n--- Page {i + 1} ---\n\n" + page.get_text()

        return {"filename": file.filename, "text": extracted_text}
    except Exception as e:
        return {"error": str(e)}


@app.post("/extract-text-ocr")
async def extract_text_ocr(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        doc = fitz.open(stream=contents, filetype="pdf")

        full_text = ""

        for i in range(len(doc)):
            page = doc.load_page(i)

            # Normal text
            text = page.get_text()

            # Render page to an image
            pix = page.get_pixmap()
            img = Image.open(io.BytesIO(pix.tobytes()))

            # OCR text
            ocr_text = pytesseract.image_to_string(img)

            full_text += f"\n\n--- Page {i + 1} ---\n\n"
            full_text += text + "\n"
            full_text += "[OCR Text]\n" + ocr_text

        return {"filename": file.filename, "text": full_text}

    except Exception as e:
        return {"error": str(e)}