app.py

import streamlit as st
from docx import Document
import PyPDF2
import pdfplumber
import pytesseract
import difflib

def read_pdf(file):
    try:
        pdf_reader = PyPDF2.PdfFileReader(file)
        total_pages = pdf_reader.numPages
        text = []
        for page_num in range(total_pages):
            page = pdf_reader.getPage(page_num)
            text.append(page.extract_text())
        return "\n".join(text)
    except:
        st.warning('Failed to directly read PDF, trying OCR...')
        try:
            with pdfplumber.open(file) as pdf:
                text = "\n".join([page.extract_text() for page in pdf.pages])
            return text
        except Exception as e:
            st.error(f"Error in OCR: {str(e)}")
            return None

def read_docx(file):
    doc = Document(file)
    return "\n".join([p.text for p in doc.paragraphs])

def compare_texts(text1, text2):
    d = difflib.Differ()
    diff = d.compare(text1.splitlines(), text2.splitlines())
    return '\n'.join(diff)

st.title('PDF and DOCX Comparison Tool')

pdf_file = st.file_uploader('Upload a PDF file', type=['pdf'])
docx_file = st.file_uploader('Upload a DOCX file', type=['docx'])

if pdf_file and docx_file:
    pdf_text = read_pdf(pdf_file)
    docx_text = read_docx(docx_file)

    if pdf_text and docx_text:
        comparison_result = compare_texts(pdf_text, docx_text)
        st.text(comparison_result)
    else:
        st.error('Failed to read text from one or both files.')