cd /tmp/workspace/attachments/48ddea76-2a13-437e-b3dc-64f45c91ea38/ && python3 -c " import pdfplumber with pdfplumber.open('Block_N_Surgery_260721_185719.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): print(f'\n===== PAGE {i+1} =====') text = page.extract_text() print(text) "

python3 -c " import pdfplumber from pypdf import PdfReader # Check metadata and structure reader = PdfReader('/tmp/workspace/attachments/48ddea76-2a13-437e-b3dc-64f45c91ea38/Block_N_Surgery_260721_185719.pdf') print('Pages:', len(reader.pages)) print('Metadata:', reader.metadata) # Check if there are fonts or special elements with pdfplumber.open('/tmp/workspace/attachments/48ddea76-2a13-437e-b3dc-64f45c91ea38/Block_N_Surgery_260721_185719.pdf') as pdf: page = pdf.pages[1] # page 2 print('Page size:', page.width, page.height) # Get all text objects with positions words = page.extract_words() print('Sample words:', words[:20]) "

mkdir -p /tmp/workspace/surgery-notes && ls /tmp/workspace/