Spaces:
Sleeping
Sleeping
File size: 1,673 Bytes
9a256f9 576dfa7 9a256f9 d40eb05 576dfa7 9a256f9 d40eb05 576dfa7 9a256f9 576dfa7 ecb38ba 576dfa7 9a256f9 576dfa7 |
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 47 48 49 50 51 |
import streamlit as st
from PyPDF2 import PdfReader
from docx import Document
from io import BytesIO
from pdf2image import convert_from_bytes
import pytesseract
def pdf_to_word(pdf_file, password=None):
"""Convert a PDF file to a Word file with optional decryption and OCR."""
reader = PdfReader(pdf_file)
# Decrypt the PDF if it's encrypted
if reader.is_encrypted:
if password:
try:
reader.decrypt(password)
except Exception as e:
raise ValueError("Failed to decrypt the PDF. Check the password.") from e
else:
raise ValueError("The PDF is encrypted. Please provide a password.")
document = Document()
# Extract text from each page
pdf_bytes = pdf_file.read()
for page in reader.pages:
if page.extract_text(): # Use PyPDF2 for text extraction
text = page.extract_text()
document.add_paragraph(text)
else:
# Use OCR for non-extractable pages
images = convert_from_bytes(pdf_bytes)
for image in images:
ocr_text = pytesseract.image_to_string(image)
if ocr_text.strip():
document.add_paragraph(ocr_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,
|