Spaces:
Running
Running
File size: 1,487 Bytes
9a256f9 ecb38ba 9a256f9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import streamlit as st
from PyPDF2 import PdfReader
from docx import Document
from io import BytesIO
def pdf_to_word(pdf_file):
"""Convert a PDF file to a Word file."""
reader = PdfReader(pdf_file)
document = Document()
for page in reader.pages:
if page.extract_text(): # Ensure text is extracted
text = page.extract_text()
document.add_paragraph(text)
else:
document.add_paragraph("[This page contains non-extractable content or images]")
word_file = BytesIO()
document.save(word_file)
word_file.seek(0)
return word_file
# Streamlit app configuration
st.set_page_config(page_title="PDF to Word Converter", page_icon="🖋", layout="centered")
# App header
st.title("PDF to Word Converter")
st.write("Upload a PDF file, and we will convert it into a Word document for you.")
# File uploader
uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
if uploaded_file is not None:
with st.spinner("Converting PDF to Word..."):
try:
word_file = pdf_to_word(uploaded_file)
st.success("Conversion successful!")
st.download_button(
label="Download Word file",
data=word_file,
file_name="converted.docx",
mime="application/vnd.openxmlformats-officedocument.wordprocessingml.document"
)
except Exception as e:
st.error(f"An error occurred: {str(e)}")
|