cd /home/daytona/workspace/attachments/1a9fb842-5be9-4702-b4ec-56457a2371d3/ && python3 -c " import pdfplumber with pdfplumber.open('CCB.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages[:5]): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(text[:2000] if text else '[no text]') print() "

cd /home/daytona/workspace/attachments/1a9fb842-5be9-4702-b4ec-56457a2371d3/ && python3 -c " from pdf2image import convert_from_path import pytesseract from PIL import Image pages = convert_from_path('CCB.pdf', dpi=200) print(f'Converted {len(pages)} pages') for i, page in enumerate(pages): text = pytesseract.image_to_string(page) print(f'=== PAGE {i+1} ===') print(text[:3000]) print() " 2>&1 | head -300

cd /home/daytona/workspace/attachments/1a9fb842-5be9-4702-b4ec-56457a2371d3/ && python3 -c " from pdf2image import convert_from_path pages = convert_from_path('CCB.pdf', dpi=150, first_page=1, last_page=1) pages[0].save('/home/daytona/workspace/ccb_page1.png') print('saved page 1') " 2>&1

cd /home/daytona/workspace/attachments/1a9fb842-5be9-4702-b4ec-56457a2371d3/ && python3 -c " import pytesseract from PIL import Image img = Image.open('/home/daytona/workspace/ccb_page1.png') text = pytesseract.image_to_string(img) print(text) " 2>&1

cd /home/daytona/workspace/attachments/1a9fb842-5be9-4702-b4ec-56457a2371d3/ && python3 -c " from pdf2image import convert_from_path import pytesseract from PIL import Image all_text = '' for pg in range(1, 6): pages = convert_from_path('CCB.pdf', dpi=150, first_page=pg, last_page=pg) text = pytesseract.image_to_string(pages[0]) all_text += f'\n=== PAGE {pg} ===\n' + text with open('/home/daytona/workspace/ccb_full_text.txt', 'w') as f: f.write(all_text) print('Done. Chars:', len(all_text)) " 2>&1