python3 << 'EOF' import pdfplumber # Extract text from both PDFs files = { "uni_library": "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochem uni library.pdf", "paper": "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochemistry paper'.pdf" } for key, path in files.items(): print(f"\n{'='*60}") print(f"FILE: {key}") print('='*60) try: with pdfplumber.open(path) as pdf: print(f"Total pages: {len(pdf.pages)}") for i, page in enumerate(pdf.pages): text = page.extract_text() if text: print(f"\n--- Page {i+1} ---") print(text[:3000]) except Exception as e: print(f"Error: {e}") EOF

python3 << 'EOF' from pypdf import PdfReader files = { "uni_library": "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochem uni library.pdf", "paper": "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochemistry paper'.pdf" } for key, path in files.items(): print(f"\n{'='*60}") print(f"FILE: {key}") print('='*60) try: reader = PdfReader(path) print(f"Total pages: {len(reader.pages)}") for i, page in enumerate(reader.pages[:5]): text = page.extract_text() if text and text.strip(): print(f"\n--- Page {i+1} ---") print(text[:2000]) else: print(f"Page {i+1}: [no extractable text]") except Exception as e: print(f"Error: {e}") EOF

python3 << 'EOF' # Try to convert PDF pages to images using pdf2image or pymupdf import subprocess result = subprocess.run(['pip', 'show', 'pymupdf'], capture_output=True, text=True) print("pymupdf:", result.stdout[:200] if result.stdout else result.stderr[:200]) result2 = subprocess.run(['pip', 'show', 'fitz'], capture_output=True, text=True) print("fitz:", result2.stdout[:200] if result2.stdout else result2.stderr[:200]) result3 = subprocess.run(['python3', '-c', 'import fitz; print("fitz version:", fitz.__version__)'], capture_output=True, text=True) print("fitz import:", result3.stdout, result3.stderr[:200]) result4 = subprocess.run(['python3', '-c', 'import pdf2image; print("ok")'], capture_output=True, text=True) print("pdf2image:", result4.stdout, result4.stderr[:100]) EOF

python3 << 'EOF' from pdf2image import convert_from_path import os # Convert first few pages of both PDFs to images for OCR os.makedirs("/tmp/workspace/pdf_pages", exist_ok=True) pdf1 = "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochem uni library.pdf" pdf2 = "/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochemistry paper'.pdf" # Convert all pages but at lower DPI to save time print("Converting PDF 1...") images1 = convert_from_path(pdf1, dpi=150) print(f"PDF1: {len(images1)} pages") for i, img in enumerate(images1): img.save(f"/tmp/workspace/pdf_pages/uni_{i+1}.png") print("Converting PDF 2...") images2 = convert_from_path(pdf2, dpi=150) print(f"PDF2: {len(images2)} pages") for i, img in enumerate(images2): img.save(f"/tmp/workspace/pdf_pages/paper_{i+1}.png") print("Done!") EOF

python3 -c "import pytesseract; print('tesseract ok'); print(pytesseract.get_tesseract_version())"

pip install --user pytesseract 2>&1 | tail -3; which tesseract 2>&1; tesseract --version 2>&1 | head -3

python3 -c "from markitdown import MarkItDown; md = MarkItDown(); result = md.convert('/tmp/workspace/attachments/b7fc7ea1-cb44-4193-94a1-c59b3911fae3/biochem uni library.pdf'); print(result.text_content[:3000])" 2>&1

python3 << 'EOF' # Try EasyOCR try: import easyocr print("easyocr available") except: print("easyocr not available") # Try using Pillow to read image and check if readable from PIL import Image img = Image.open("/tmp/workspace/pdf_pages/uni_1.png") print(f"Image size: {img.size}, mode: {img.mode}") img.save("/tmp/workspace/pdf_pages/uni_1_small.jpg", quality=85) import os print(f"File size: {os.path.getsize('/tmp/workspace/pdf_pages/uni_1.png')} bytes") EOF

python3 << 'EOF' # Compress images to smaller size so read_file can handle them from PIL import Image import os pages_dir = "/tmp/workspace/pdf_pages" output_dir = "/tmp/workspace/pdf_small" os.makedirs(output_dir, exist_ok=True) # Process all pages for both PDFs for prefix in ["uni", "paper"]: for i in range(1, 32): src = f"{pages_dir}/{prefix}_{i}.png" if os.path.exists(src): img = Image.open(src) # Resize to smaller and save as JPEG img_small = img.resize((850, int(850 * img.height / img.width)), Image.LANCZOS) out_path = f"{output_dir}/{prefix}_{i}.jpg" img_small.save(out_path, "JPEG", quality=75) size = os.path.getsize(out_path) if i <= 3: print(f"{prefix}_{i}: {size} bytes") print("Done compressing") EOF