cd /tmp/workspace/attachments/b900bc4f-2514-4fb6-96ad-8e5e3972b65c/ && python3 -c " import pdfplumber with pdfplumber.open('Shock but modified .pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): text = page.extract_text() if text: print(f'\\n===PAGE {i+1}===') print(text) " 2>&1 | head -500

cd /tmp/workspace/attachments/b900bc4f-2514-4fb6-96ad-8e5e3972b65c/ && python3 -c " import pdfplumber with pdfplumber.open('Shock but modified .pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): text = page.extract_text() print(f'PAGE {i+1}: {repr(text[:200]) if text else \"EMPTY\"}') " 2>&1

python3 -c " from pypdf import PdfReader import base64, sys reader = PdfReader('/tmp/workspace/attachments/b900bc4f-2514-4fb6-96ad-8e5e3972b65c/Shock but modified .pdf') print(f'Pages: {len(reader.pages)}') # Try extracting text with pypdf for i, page in enumerate(reader.pages): text = page.extract_text() print(f'PAGE {i+1}: {repr(text[:300]) if text else \"EMPTY\"}') " 2>&1

python3 -c " from pypdf import PdfReader import io reader = PdfReader('/tmp/workspace/attachments/b900bc4f-2514-4fb6-96ad-8e5e3972b65c/Shock but modified .pdf') page = reader.pages[0] # Check for images print('Resources:', list(page['/Resources'].keys()) if '/Resources' in page else 'No resources') if '/Resources' in page and '/XObject' in page['/Resources']: xobj = page['/Resources']['/XObject'] print('XObjects:', list(xobj.keys())) " 2>&1

python3 -c " from pypdf import PdfReader import os reader = PdfReader('/tmp/workspace/attachments/b900bc4f-2514-4fb6-96ad-8e5e3972b65c/Shock but modified .pdf') os.makedirs('/tmp/workspace/shock_images', exist_ok=True) for page_num, page in enumerate(reader.pages): if '/Resources' in page and '/XObject' in page['/Resources']: xobj = page['/Resources']['/XObject'] for obj_name in xobj.keys(): obj = xobj[obj_name] if obj.get('/Subtype') == '/Image': img_data = obj.get_data() filter_type = obj.get('/Filter', '') if 'DCT' in str(filter_type): ext = 'jpg' elif 'PNG' in str(filter_type) or 'Flate' in str(filter_type): ext = 'png' else: ext = 'bin' fname = f'/tmp/workspace/shock_images/page_{page_num+1}.{ext}' with open(fname, 'wb') as f: f.write(img_data) print(f'Saved page {page_num+1}: {fname} ({len(img_data)} bytes)') " 2>&1

python3 -c " from PIL import Image import os # Resize large images to under 500KB img_dir = '/tmp/workspace/shock_images' for fname in sorted(os.listdir(img_dir)): fpath = os.path.join(img_dir, fname) size = os.path.getsize(fpath) if size > 400000: img = Image.open(fpath) # Reduce to 50% quality out = fpath.replace('.jpg', '_small.jpg') img.save(out, 'JPEG', quality=40, optimize=True) new_size = os.path.getsize(out) print(f'{fname}: {size} -> {new_size}') else: print(f'{fname}: {size} (ok)') " 2>&1

python3 -c " from PIL import Image import os img_dir = '/tmp/workspace/shock_images' for i in range(3, 17): # Try original first, then _small for suffix in ['', '_small']: fname = f'page_{i}{suffix}.jpg' fpath = os.path.join(img_dir, fname) if os.path.exists(fpath): img = Image.open(fpath) w, h = img.size # Scale to max width 900 if w > 900: ratio = 900/w img = img.resize((900, int(h*ratio)), Image.LANCZOS) out = os.path.join(img_dir, f'page_{i}_tiny.jpg') img.save(out, 'JPEG', quality=35) sz = os.path.getsize(out) print(f'page_{i}_tiny.jpg: {sz}') break " 2>&1