Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from docx import Document | |
| import PyPDF2 | |
| import pdfplumber | |
| import pytesseract | |
| import difflib | |
| import base64 | |
| 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 = list(d.compare(text1.splitlines(), text2.splitlines())) | |
| result = [] | |
| page_no = 1 | |
| for line in diff: | |
| if 'Page' in line: # if a new page starts | |
| page_no += 1 | |
| elif line.startswith('+ '): # text present in text2 but not in text1 | |
| result.append(f'Additional text detected on page {page_no}') | |
| elif line.startswith('- '): # text present in text1 but not in text2 | |
| result.append(f'Less text detected on page {page_no}') | |
| return "\n".join(set(result)) # using set to remove duplicates | |
| 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) | |
| b64_pdf = base64.b64encode(pdf_file.read()).decode() # some strings <-> bytes conversions necessary here | |
| href = f'<a href="data:file/pdf;base64,{b64_pdf}" download="file.pdf">Download PDF File</a> (right-click and save as <some_name>.pdf)' | |
| st.markdown(href, unsafe_allow_html=True) | |
| st.markdown(f'<iframe src="data:application/pdf;base64,{b64_pdf}" width="50%" height="600px" type="application/pdf"></iframe>', unsafe_allow_html=True) | |
| st.markdown("### DOCX Content:") | |
| st.text(docx_text) | |
| 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.') |