app.py

import streamlit as st
from PIL import Image
import pytesseract
import io

st.set_page_config(page_title="OCR – Image to Text", layout="centered")
st.title("🖼️ OCR – Image to Text")

st.write("Upload an image (PNG, JPG, JPEG) to extract text.")

uploaded_file = st.file_uploader("Upload Image", type=["png", "jpg", "jpeg"])
image = None

if uploaded_file is not None:
    # Display file metadata
    st.write(f"**Filename:** {uploaded_file.name}")
    st.write(f"**Type:** {uploaded_file.type}")
    st.write(f"**Size:** {uploaded_file.size} bytes")

    try:
        # Read bytes and open with PIL
        bytes_data = uploaded_file.getvalue()
        image = Image.open(io.BytesIO(bytes_data))
        st.image(image, caption="Preview", use_column_width=True)
    except Exception as e:
        st.error(f"⚠️ Failed to open image: {e}")

# Only show extract button if image was loaded successfully
if image is not None:
    if st.button("Extract Text"):
        with st.spinner("Running OCR..."):
            try:
                text = pytesseract.image_to_string(image)
                st.success("✅ Text extracted!")
                st.text_area("Extracted Text", value=text, height=300)
            except Exception as e:
                st.error(f"❌ OCR error: {e}")