python3 << 'EOF' import pdfplumber files = [ "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/DR SUDHA BLOOD REPORTS - HLA B27, ANA.pdf", "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/DR SUDHA REPORTS - THYROID LIPID.pdf", "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/DR SUDHA REPORTS JUNE 2026.pdf" ] for f in files: print(f"\n{'='*60}") print(f"FILE: {f.split('/')[-1]}") print('='*60) try: with pdfplumber.open(f) as pdf: for i, page in enumerate(pdf.pages): text = page.extract_text() if text: print(f"\n--- Page {i+1} ---") print(text) tables = page.extract_tables() if tables: for t in tables: print(f"\n[TABLE on page {i+1}]") for row in t: print(row) except Exception as e: print(f"Error: {e}") EOF

python3 << 'EOF' from pypdf import PdfReader files = [ "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/DR SUDHA REPORTS - THYROID LIPID.pdf", "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/DR SUDHA REPORTS JUNE 2026.pdf" ] for f in files: print(f"\n{'='*60}") print(f"FILE: {f.split('/')[-1]}") print('='*60) try: reader = PdfReader(f) print(f"Pages: {len(reader.pages)}") for i, page in enumerate(reader.pages): text = page.extract_text() print(f"\n--- Page {i+1} ---") print(text if text else "[No text extracted]") except Exception as e: print(f"Error: {e}") EOF

python3 << 'EOF' import subprocess import os # Try to render PDFs as images using PIL/pypdf approach # First check what image libraries are available try: from pdf2image import convert_from_path print("pdf2image available") except ImportError: print("pdf2image NOT available") try: import fitz # PyMuPDF print("PyMuPDF (fitz) available") except ImportError: print("PyMuPDF NOT available") try: from PIL import Image print("PIL available") except ImportError: print("PIL NOT available") EOF

python3 << 'EOF' from pdf2image import convert_from_path import os os.makedirs("/tmp/workspace/pdf_images", exist_ok=True) files = { "thyroid_lipid": "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647161a/DR SUDHA REPORTS - THYROID LIPID.pdf", "june2026": "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647161a/DR SUDHA REPORTS JUNE 2026.pdf" } # Use the correct path base = "/tmp/workspace/attachments/e499c8ca-37a4-437b-9439-fb249647167a/" for key, fname in [ ("thyroid_lipid", "DR SUDHA REPORTS - THYROID LIPID.pdf"), ("june2026", "DR SUDHA REPORTS JUNE 2026.pdf") ]: fpath = base + fname print(f"Converting {fname}...") try: pages = convert_from_path(fpath, dpi=150) for i, page in enumerate(pages): out = f"/tmp/workspace/pdf_images/{key}_page{i+1}.png" page.save(out, "PNG") print(f" Saved: {out} ({page.size})") except Exception as e: print(f" Error: {e}") EOF

# Start a simple HTTP server in background to serve the images cd /tmp/workspace/pdf_images && python3 -m http.server 8765 & sleep 2 echo "Server started" curl -s http://localhost:8765/ | head -20

python3 << 'EOF' # Check OCR options try: import pytesseract print("pytesseract available") import subprocess result = subprocess.run(['tesseract', '--version'], capture_output=True, text=True) print(result.stdout[:100]) except Exception as e: print(f"pytesseract: {e}") # Try easyocr try: import easyocr print("easyocr available") except ImportError: print("easyocr NOT available") EOF

# Try installing pytesseract and tesseract pip install --user pytesseract 2>/dev/null | tail -1 # Check if tesseract binary exists anywhere which tesseract 2>/dev/null || echo "tesseract not in PATH" ls /usr/bin/tesseract 2>/dev/null || echo "not at /usr/bin/tesseract" ls /usr/local/bin/tesseract 2>/dev/null || echo "not at /usr/local/bin/tesseract"

# Compress/resize the images to smaller size for reading python3 << 'EOF' from PIL import Image import os os.makedirs("/tmp/workspace/pdf_small", exist_ok=True) for fname in os.listdir("/tmp/workspace/pdf_images"): if fname.endswith(".png"): img = Image.open(f"/tmp/workspace/pdf_images/{fname}") # Resize to max 800px width w, h = img.size if w > 800: ratio = 800 / w new_size = (800, int(h * ratio)) img = img.resize(new_size, Image.LANCZOS) out = f"/tmp/workspace/pdf_small/{fname.replace('.png', '.jpg')}" img.convert('RGB').save(out, 'JPEG', quality=70) size_kb = os.path.getsize(out) // 1024 print(f"{fname} -> {img.size}, {size_kb}KB") EOF