app.py

import io
from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import JSONResponse
from fastapi.middleware.cors import CORSMiddleware
from pypdf import PdfReader
import uvicorn

# --- Initialize the FastAPI app ---
app = FastAPI(
    title="PDF Text Extractor API",
    description="An API that uses PyPDF to extract text from PDF files.",
    version="1.0.0"
)

# --- Configure CORS ---
# Allows your frontend web page to communicate with this API.
origins = [
    "https://clarifyai.pages.dev", # Your production frontend
    "http://127.0.0.1:5500",      # Local development server
    "http://localhost:5500",
    "*" # In development, a wildcard can be useful. For production, be more specific.
]

app.add_middleware(
    CORSMiddleware,
    allow_origins=origins,
    allow_credentials=True,
    allow_methods=["*"], # Allows all methods (GET, POST, etc.)
    allow_headers=["*"], # Allows all headers
)

# --- Define the API Endpoint ---
@app.post("/extract-text")
async def extract_text_from_pdf(file: UploadFile = File(...)):
    """
    Accepts a PDF file, extracts its text content using PyPDF, and returns it.
    """
    # Ensure the uploaded file is a PDF
    if file.content_type != "application/pdf":
        raise HTTPException(status_code=400, detail="Invalid file type. Please upload a PDF.")

    try:
        # Read the uploaded file into an in-memory stream
        pdf_stream = io.BytesIO(await file.read())
        
        # --- PyPDF LOGIC START ---
        reader = PdfReader(pdf_stream)
        full_text = []
        for page in reader.pages:
            text = page.extract_text()
            if text:
                full_text.append(text.strip())
        
        if not full_text:
            final_text = "No text could be extracted. The PDF might be image-based or empty."
        else:
            final_text = "\n\n---\n\n".join(full_text)
        # --- PyPDF LOGIC END ---

        # Return the extracted text in a JSON response
        return JSONResponse(content={"text": final_text})

    except Exception as e:
        # Handle potential errors during PDF processing
        print(f"An error occurred during PDF processing: {e}")
        raise HTTPException(status_code=500, detail=f"Failed to process PDF file: {str(e)}")

# A simple root endpoint to confirm the server is running
@app.get("/")
def read_root():
    return {"status": "PDF PyPDF extraction service is running."}

# This part is for local development, Hugging Face Spaces will use its own server.
if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=8000)