PyPDF2 import PdfReader

Open and read the uploaded PDF file

pdf_path = '/mnt/data/1734121148107ud3s9fs4.pdf' pdf_reader = PdfReader(pdf_path)

Extract text from all pages in the PDF

pdf_text = '' for page in pdf_reader.pages: pdf_text += page.extract_text()

Check the extracted text to find the relevant questions

pdf_text[:1000] # Show first 1000 characters to understand the contentIt seems that the text extracted from the PDF is not very clear and is filled with non-readable characters. To properly assist you, I may need to look directly at the content of the questions (3, 4, and 9). Could you either upload a clearer version of the document or provide details for those specific questions? Alternatively, you could share a screenshot of the pages in which the questions are located, and I will be able to process them effectively.