cd /home/daytona/workspace/attachments/53271fda-9081-4540-bbc7-dae337b0b22e/ && python3 -c " import pdfplumber with pdfplumber.open('CCB.pdf') as pdf: print(f'Pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages[:3]): print(f'--- Page {i+1} ---') print(page.extract_text()[:2000]) "

cd /home/daytona/workspace/attachments/53271fda-9081-4540-bbc7-dae337b0b22e/ && python3 -c " from pypdf import PdfReader reader = PdfReader('CCB.pdf') print(f'Pages: {len(reader.pages)}') print('Metadata:', reader.metadata) for i, page in enumerate(reader.pages): text = page.extract_text() print(f'--- Page {i+1} (chars: {len(text) if text else 0}) ---') if text: print(text[:3000]) "

cd /home/daytona/workspace/attachments/53271fda-9081-4540-bbc7-dae337b0b22e/ && python3 -c " import subprocess result = subprocess.run(['pdftoppm', '-r', '150', 'CCB.pdf', '/tmp/ccb_page'], capture_output=True, text=True) print('stdout:', result.stdout) print('stderr:', result.stderr) print('returncode:', result.returncode) import os files = sorted(os.listdir('/tmp/')) print([f for f in files if f.startswith('ccb')]) "

python3 -c " from PIL import Image import base64, os # Convert PPM to PNG for easier handling for i in range(1, 6): img = Image.open(f'/tmp/ccb_page-{i}.ppm') img.save(f'/tmp/ccb_page-{i}.png') print(f'Page {i}: {img.size}') "

python3 -c " # Copy images to workspace so they can be served import shutil for i in range(1, 6): shutil.copy(f'/tmp/ccb_page-{i}.png', f'/home/daytona/workspace/attachments/53271fda-9081-4540-bbc7-dae337b0b22e/ccb_page-{i}.png') print('Done copying') "

mkdir -p /home/daytona/workspace/ccb_pages && cp /tmp/ccb_page-*.png /home/daytona/workspace/ccb_pages/ && ls /home/daytona/workspace/ccb_pages/

python3 -c " import pytesseract from PIL import Image full_text = '' for i in range(1, 6): img = Image.open(f'/tmp/ccb_page-{i}.png') text = pytesseract.image_to_string(img) full_text += f'\n\n=== PAGE {i} ===\n' + text print(full_text[:8000]) " 2>&1

python3 -c " import pytesseract from PIL import Image img = Image.open('/tmp/ccb_page-1.png') text = pytesseract.image_to_string(img) print(text[:5000]) " 2>&1