cd "/tmp/workspace/attachments/d7bb5eef-6792-4f17-b6ff-2e68746d3eca/" && python3 -c " import pdfplumber with pdfplumber.open('paper 1.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): print(f'--- PAGE {i+1} ---') text = page.extract_text() if text: print(text) else: print('[No text extracted]') "

python3 -c " from pypdf import PdfReader import base64 reader = PdfReader('/tmp/workspace/attachments/d7bb5eef-6792-4f17-b6ff-2e68746d3eca/paper 1.pdf') print(f'Pages: {len(reader.pages)}') # Try to extract images from first page page = reader.pages[0] print('Page keys:', page.keys()) if '/Resources' in page: resources = page['/Resources'] print('Resources:', resources.keys() if hasattr(resources, 'keys') else resources) if '/XObject' in resources: xobj = resources['/XObject'] print('XObjects:', list(xobj.keys())[:5]) "

python3 -c " from pypdf import PdfReader import os reader = PdfReader('/tmp/workspace/attachments/d7bb5eef-6792-4f17-b6ff-2e68746d3eca/paper 1.pdf') os.makedirs('/tmp/workspace/pdf_images', exist_ok=True) for page_num, page in enumerate(reader.pages): resources = page['/Resources'] xobj = resources['/XObject'] for name, obj in xobj.items(): obj = obj.get_object() if obj.get('/Subtype') == '/Image': data = obj.get_data() filter_type = obj.get('/Filter', '') print(f'Page {page_num+1}, {name}: filter={filter_type}, size={len(data)} bytes') ext = 'jpg' if 'DCT' in str(filter_type) else 'png' with open(f'/tmp/workspace/pdf_images/page_{page_num+1}.{ext}', 'wb') as f: f.write(data) print(f' Saved as page_{page_num+1}.{ext}') "

python3 -c " import base64, os # Check sizes are reasonable for i in range(1,9): path = f'/tmp/workspace/pdf_images/page_{i}.jpg' size = os.path.getsize(path) print(f'page_{i}.jpg: {size} bytes ({size/1024:.1f} KB)') "

cd /tmp/workspace/pdf_images && python3 -m http.server 8765 & sleep 1 echo "Server started" curl -s -o /dev/null -w "%{http_code}" http://localhost:8765/page_1.jpg

mkdir -p /tmp/workspace/surgery-answers && echo "ready"