import gradio as gr
import numpy as np
from pypdf import PdfReader
import os

def extract_text(file):

    
    reader = PdfReader(file)

    text = []
    for p in np.arange(0, len(reader.pages), 1):
        page = reader.pages[int(p)]

        # extracting text from page
        text.append(page.extract_text())

    text = ' '.join(text)

    return text

with gr.Blocks() as demo:
    file_input = gr.File(label="Upload a PDF file")
    text_output = gr.Textbox(label="Extracted Text")
    file_input.upload(extract_text, inputs=file_input, outputs=text_output)

demo.launch()