python3 -c " import pdfplumber pdf_path = '/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf' with pdfplumber.open(pdf_path) as pdf: print(f'Total pages: {len(pdf.pages)}') for i, page in enumerate(pdf.pages): print(f'\\n=== PAGE {i+1} ===') text = page.extract_text() if text: print(text) else: print('[No text extracted]') "

python3 -c " from pypdf import PdfReader import base64 pdf_path = '/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf' reader = PdfReader(pdf_path) print(f'Pages: {len(reader.pages)}') # Check if there are images in the pages for i in range(min(3, len(reader.pages))): page = reader.pages[i] print(f'Page {i+1} resources: {list(page.get(\"/Resources\", {}).keys()) if page.get(\"/Resources\") else \"none\"}') if '/XObject' in str(page.get('/Resources', {})): print(f' Has XObjects (likely images)') "

python3 -c " import fitz # PyMuPDF import os pdf_path = '/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf' output_dir = '/home/daytona/workspace/ipd_pages/' os.makedirs(output_dir, exist_ok=True) doc = fitz.open(pdf_path) print(f'Total pages: {len(doc)}') # Convert first 10 pages to images for i in range(min(10, len(doc))): page = doc[i] mat = fitz.Matrix(2, 2) # 2x zoom for better quality pix = page.get_pixmap(matrix=mat) img_path = f'{output_dir}page_{i+1:02d}.png' pix.save(img_path) print(f'Saved page {i+1}: {img_path} ({pix.width}x{pix.height})') doc.close() print('Done!') "

mkdir -p /home/daytona/workspace/ipd_pages && pdftoppm -r 200 -png "/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf" /home/daytona/workspace/ipd_pages/page && ls /home/daytona/workspace/ipd_pages/ | head -15

mkdir -p /home/daytona/workspace/ipd_pages && pdftoppm -r 150 -png -f 1 -l 5 "/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf" /home/daytona/workspace/ipd_pages/page && ls /home/daytona/workspace/ipd_pages/

python3 -c " import base64 import json # Read page 1 as base64 to use with vision with open('/home/daytona/workspace/ipd_pages/page-01.png', 'rb') as f: data = base64.b64encode(f.read()).decode() print(f'Page 1 base64 length: {len(data)}') print('First 100 chars:', data[:100]) "

tesseract /home/daytona/workspace/ipd_pages/page-01.png /home/daytona/workspace/ipd_pages/page-01_ocr -l eng+urd 2>&1 && cat /home/daytona/workspace/ipd_pages/page-01_ocr.txt

# Try OCR on multiple key pages with English only for page in 01 02 03 04 05 06 07 08; do echo "=== PAGE $page ===" tesseract /home/daytona/workspace/ipd_pages/page-${page}.png stdout -l eng 2>/dev/null echo "" done

for page in 09 10 11 12 13 14 15 16 17 18 19 20; do echo "=== PAGE $page ===" tesseract /home/daytona/workspace/ipd_pages/page-${page}.png stdout -l eng 2>/dev/null echo "" done

pdftoppm -r 150 -png -f 21 -l 38 "/home/daytona/workspace/attachments/ef38ac52-78ea-476f-8448-5745e2b031c1/ICU2 Abu Osama(pdfgear.com) (1).pdf" /home/daytona/workspace/ipd_pages/page && ls /home/daytona/workspace/ipd_pages/ | grep -E "page-2[1-9]|page-3"

for page in 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38; do echo "=== PAGE $page ===" tesseract /home/daytona/workspace/ipd_pages/page-${page}.png stdout -l eng 2>/dev/null echo "" done

for page in 21 22 23 24 25; do echo "=== PAGE $page ===" timeout 10 tesseract /home/daytona/workspace/ipd_pages/page-${page}.png stdout -l eng 2>/dev/null || echo "[timeout]" echo "" done

for page in 26 27 28 29 30 31 32; do echo "=== PAGE $page ===" timeout 10 tesseract /home/daytona/workspace/ipd_pages/page-${page}.png stdout -l eng 2>/dev/null || echo "[timeout/error]" echo "" done