cd /home/daytona/workspace/attachments/f7d44c29-72c7-4b82-959b-fa6bf15349fb/ && python3 -c " import pdfplumber with pdfplumber.open('Pharmacology Mid-2 with ans_250429_152045_250501_150153.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} ---') print(text) print() "

cd /home/daytona/workspace/attachments/f7d44c29-72c7-4b82-959b-fa6bf15349fb/ && python3 -c " from pypdf import PdfReader import sys reader = PdfReader('Pharmacology Mid-2 with ans_250429_152045_250501_150153.pdf') print(f'Pages: {len(reader.pages)}') # Try raw extraction for i in range(min(3, len(reader.pages))): page = reader.pages[i] print(f'Page {i+1} raw:', repr(page.extract_text()[:200])) # Check for images if '/XObject' in page['/Resources']: xobjects = page['/Resources']['/XObject'] print(f' XObjects: {list(xobjects.keys())}') "

python3 -c "import pytesseract; import pdf2image; print('both available')"

python3 -c " import pdf2image import pytesseract from pathlib import Path pdf_path = '/home/daytona/workspace/attachments/f7d44c29-72c7-4b82-959b-fa6bf15349fb/Pharmacology Mid-2 with ans_250429_152045_250501_150153.pdf' print('Converting pages...') pages = pdf2image.convert_from_path(pdf_path, dpi=200, first_page=1, last_page=10) print(f'Got {len(pages)} pages') all_text = [] for i, img in enumerate(pages): text = pytesseract.image_to_string(img) all_text.append(f'=== PAGE {i+1} ===\n{text}') print(f'Page {i+1} chars: {len(text)}') full = '\n'.join(all_text) print(full[:5000]) " 2>&1 | head -200

python3 -c " import pdf2image import pytesseract pdf_path = '/home/daytona/workspace/attachments/f7d44c29-72c7-4b82-959b-fa6bf15349fb/Pharmacology Mid-2 with ans_250429_152045_250501_150153.pdf' pages = pdf2image.convert_from_path(pdf_path, dpi=200) print(f'Total pages: {len(pages)}') all_text = [] for i, img in enumerate(pages): text = pytesseract.image_to_string(img) all_text.append(f'=== PAGE {i+1} ===\n{text}') full = '\n'.join(all_text) with open('/home/daytona/workspace/pharm_ocr.txt', 'w') as f: f.write(full) print('Done. Total chars:', len(full)) " 2>&1

python3 << 'EOF' import pdf2image import pytesseract pdf_path = '/home/daytona/workspace/attachments/f7d44c29-72c7-4b82-959b-fa6bf15349fb/Pharmacology Mid-2 with ans_250429_152045_250501_150153.pdf' all_text = [] batch_size = 8 total_pages = 64 for start in range(1, total_pages + 1, batch_size): end = min(start + batch_size - 1, total_pages) pages = pdf2image.convert_from_path(pdf_path, dpi=180, first_page=start, last_page=end) for j, img in enumerate(pages): page_num = start + j text = pytesseract.image_to_string(img) all_text.append(f'=== PAGE {page_num} ===\n{text}') print(f'Done pages {start}-{end}') full = '\n'.join(all_text) with open('/home/daytona/workspace/pharm_ocr.txt', 'w') as f: f.write(full) print(f'Complete. Total chars: {len(full)}') EOF