app.py

import streamlit as st
import pandas as pd
import numpy as np
import os
from grobidmonkey import reader
from grobid_client.grobid_client import GrobidClient

def save_uploaded_file(uploaded_file):
    file_path = os.path.join("./uploads", uploaded_file.name)
    os.makedirs("./uploads", exist_ok=True)  # Create 'uploads' directory if it doesn't exist
    with open(file_path, "wb") as f:
        f.write(uploaded_file.getbuffer())
    return file_path  # Return the file path as a string

st.title('Paper2Slides')

st.subheader('Upload paper in pdf format')

col1, col2 = st.columns([3, 1])
with col1:
    uploaded_file = st.file_uploader("Choose a file")
with col2:
    option = st.selectbox(
        'Select parsing method.',
        ('monkey', 'x2d', 'lxml'))

if uploaded_file is not None:
    
    st.write(uploaded_file.name)
    bytes_data = uploaded_file.getvalue()
    st.write(len(bytes_data), "bytes")
    

    saved_file_path = save_uploaded_file(uploaded_file)
    os.makedirs("./outputs", exist_ok=True)
    exec("grobid_client --input ./uploads/ --output ./outputs/ processFulltextDocument")
    
    # client = GrobidClient(config_path="./grobidconfig.json")
    # client.process("processFulltextDocument",
    #                "./uploads/",
    #                consolidate_citations=True, 
    #                tei_coordinates=True)
                   
    output_file_path = os.path.splitext(saved_file_path)[0] + ".grobid.tei.xml"
    monkeyReader = reader.MonkeyReader(option)
    outline = monkeyReader.readOutline(output_file_path)
    for pre, fill, node in outline:
        st.write("%s%s" % (pre, node.name))
    
    
    # read paper content
    essay = monkeyReader.readEssay(output_file_path)
    for key, values in essay.items():
        st.write(f"{key}: {', '.join(values)}")