cd /home/daytona/workspace/attachments/a1861630-e8e4-48d9-a92f-dbd59c17c322 && python3 -c " import pdfplumber with pdfplumber.open('2.pdf') as pdf: for i, page in enumerate(pdf.pages): print(f'=== PAGE {i+1} ===') print(page.extract_text()) "

cd /home/daytona/workspace/attachments/a1861630-e8e4-48d9-a92f-dbd59c17c322 && pandoc --track-changes=all "Case activity.docx" -o /tmp/case_activity.md && cat /tmp/case_activity.md

cd /home/daytona/workspace/attachments/a1861630-e8e4-48d9-a92f-dbd59c17c322 && python3 -c " import pdfplumber with pdfplumber.open('2.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]') # also try tables tables = page.extract_tables() if tables: print('TABLES:') for t in tables: for row in t: print(row) "

cd /home/daytona/workspace/attachments/a1861630-e8e4-48d9-a92f-dbd59c17c322 && python3 -c " from pypdf import PdfReader import base64, io reader = PdfReader('2.pdf') print('Pages:', len(reader.pages)) for i, page in enumerate(reader.pages): print(f'Page {i+1} images:', len(page.images)) for img in page.images: print(f' Image name: {img.name}, size: {len(img.data)} bytes') with open(f'/tmp/page{i+1}_img.png', 'wb') as f: f.write(img.data) print(f' Saved to /tmp/page{i+1}_img.png') "