app.py

# Importing the required libraries
import streamlit as st
import pandas as pd
import PyPDF2
import docx2pdf
from io import BytesIO

# Creating a title and a sidebar
st.title("All files to single pdf")
st.sidebar.header("Upload your files")

# Creating a function to convert docx files to pdf
def docx_to_pdf(docx_file):
  pdf_file = BytesIO()
  docx2pdf.convert(docx_file.name, pdf_file)
  pdf_file.seek(0)
  return pdf_file

# Creating a function to merge multiple pdf files
def merge_pdfs(pdf_files):
  merger = PyPDF2.PdfMerger()
  for pdf_file in pdf_files:
    merger.append(PyPDF2.PdfReader(pdf_file))
  merged_pdf = BytesIO()
  merger.write(merged_pdf)
  merged_pdf.seek(0)
  return merged_pdf

# Creating a list to store the uploaded files
uploaded_files = []

# Allowing the user to upload multiple files of different formats
uploaded_files = st.sidebar.file_uploader("Choose your files", type=["pdf", "docx", "txt", "xlsx", "csv"], accept_multiple_files=True)

# Checking if any files are uploaded
if uploaded_files:
  st.write("You have uploaded {} files.".format(len(uploaded_files)))

  # Creating a list to store the pdf files
  pdf_files = []

  # Looping through the uploaded files and converting them to pdf if needed
  for uploaded_file in uploaded_files:
    # Getting the file name and extension
    file_name = uploaded_file.name
    file_ext = file_name.split(".")[-1]

    # Checking the file format and converting it to pdf if needed
    if file_ext == "pdf":
      # No conversion needed, just append to the pdf list
      pdf_files.append(uploaded_file)
    elif file_ext == "docx":
      # Converting docx to pdf using the function defined earlier
      pdf_file = docx_to_pdf(uploaded_file)
      pdf_files.append(pdf_file)
    elif file_ext == "txt":
      # Reading the text file and creating a pandas dataframe
      df = pd.read_csv(uploaded_file, sep="\n", header=None, names=["Text"])
      # Converting the dataframe to a pdf file using pandas
      pdf_file = BytesIO()
      df.to_pdf(pdf_file)
      pdf_file.seek(0)
      pdf_files.append(pdf_file)
    elif file_ext == "xlsx" or file_ext == "csv":
      # Reading the excel or csv file and creating a pandas dataframe
      df = pd.read_excel(uploaded_file) if file_ext == "xlsx" else pd.read_csv(uploaded_file)
      # Converting the dataframe to a pdf file using pandas
      pdf_file = BytesIO()
      df.to_pdf(pdf_file)
      pdf_file.seek(0)
      pdf_files.append(pdf_file)

  # Merging the pdf files using the function defined earlier
  merged_pdf = merge_pdfs(pdf_files)

  # Displaying the merged pdf file using streamlit
  st.write("Here is your merged PDF file:")
  st.write("")
  #st.pdf(merged_pdf)

  # Allowing the user to download the merged pdf file using streamlit
  st.write("You can download your merged PDF file here:")
  st.download_button(label="Download PDF", data=merged_pdf, mime="application/pdf", file_name="merged.pdf")
else:
  st.write("No files uploaded yet. Please upload your files in the sidebar.")