cd /home/daytona/workspace/attachments/388abe5b-00d8-4d2d-b468-f020f6ca535c/ && python3 -c " import pdfplumber with pdfplumber.open('Git patho2.pdf') as pdf: print(f'Total pages: {len(pdf.pages)}') # Extract first 3 pages to see structure for i, page in enumerate(pdf.pages[:3]): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(text[:2000]) print() "

cd /home/daytona/workspace/attachments/388abe5b-00d8-4d2d-b468-f020f6ca535c/ && python3 -c " from pypdf import PdfReader reader = PdfReader('Git patho2.pdf') print(f'Total pages: {len(reader.pages)}') for i, page in enumerate(reader.pages[:5]): text = page.extract_text() print(f'--- PAGE {i+1} ---') print(repr(text[:500])) print() "

python3 -c "import pdf2image; print('pdf2image ok')" && python3 -c "import pytesseract; print('tesseract ok')"

python3 -c " import pdf2image import pytesseract from PIL import Image pdf_path = '/home/daytona/workspace/attachments/388abe5b-00d8-4d2d-b468-f020f6ca535c/Git patho2.pdf' pages = pdf2image.convert_from_path(pdf_path, dpi=200) print(f'Converted {len(pages)} pages') all_text = [] for i, page_img in enumerate(pages): text = pytesseract.image_to_string(page_img) all_text.append(f'=== PAGE {i+1} ===\n{text}') print(f'Page {i+1} done, chars: {len(text)}') full_text = '\n\n'.join(all_text) with open('/home/daytona/workspace/patho2_ocr.txt', 'w') as f: f.write(full_text) print('Saved to patho2_ocr.txt') " 2>&1