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