app.py

import streamlit as st
import pandas as pd
from transformers import pipeline
import base64

def upload_and_extract_text():
    uploaded_file = st.file_uploader("Upload PDF file", type=["pdf"])

    if uploaded_file is not None:
        ocr_pipeline = pipeline("text2text-generation", model="google/t5-v1_1-large")
        extracted_text = ocr_pipeline(uploaded_file.read(), max_length=1024, do_sample=False)[0]["generated_text"]
        return extracted_text

def text_to_dataframe(text):
    lines = text.split("\n")
    data = []
    for line in lines:
        data.append([line])
    df = pd.DataFrame(data, columns=["Text"])
    return df

def main():
    st.title("PDF to Spreadsheet Converter")
    st.write("Upload a PDF file to extract text and save it as a spreadsheet.")

    extracted_text = upload_and_extract_text()

    if extracted_text is not None:
        st.write("### Extracted Text")
        st.write(extracted_text)

        df = text_to_dataframe(extracted_text)
        st.write("### Spreadsheet Preview")
        st.write(df)

        csv = df.to_csv(index=False)
        b64 = base64.b64encode(csv.encode()).decode()
        href = f'<a href="data:file/csv;base64,{b64}" download="extracted_text.csv">Download Extracted Text as CSV</a>'
        st.markdown(href, unsafe_allow_html=True)

if __name__ == "__main__":
    main()