cd /home/daytona/workspace/attachments/d003e320-a17a-46a3-8060-fcaa633b59db && python3 -c " import pdfplumber with pdfplumber.open('micro spots Copy.pdf') as pdf: print(f'Pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(text) print() "

cd /home/daytona/workspace/attachments/d003e320-a17a-46a3-8060-fcaa633b59db && python3 -c " import fitz # PyMuPDF doc = fitz.open('micro spots Copy.pdf') print(f'Pages: {len(doc)}') for i, page in enumerate(doc): text = page.get_text() print(f'--- PAGE {i+1} ---') print(repr(text[:500])) print() "

cd /home/daytona/workspace/attachments/d003e320-a17a-46a3-8060-fcaa633b59db && python3 -c " from pypdf import PdfReader import base64, io reader = PdfReader('micro spots Copy.pdf') print(f'Pages: {len(reader.pages)}') # Check for images on first page page = reader.pages[0] print(dir(page)) images = page.images print(f'Images on page 1: {len(images)}') if images: img = images[0] print(f'Image name: {img.name}, size: {len(img.data)} bytes') with open('/tmp/page1_img0.png', 'wb') as f: f.write(img.data) print('Saved image') "