cd /tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511/ python3 << 'EOF' import pdfplumber import os files = [ "DOC-20260413-WA0011_260802234828.pdf", "DOC-20260413-WA0012_260802234820.pdf", "DOC-20260709-WA0006_260802234807.pdf", "LNCT 2nd sessional paper (1).pdf", "1st sessional 3rd prof Lnct (1).pdf", "3rd year ln paper (1).pdf", "3rd prof university paper Lnct(2).pdf" ] base = "/tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511/" for f in files: path = base + f print(f"\n{'='*60}") print(f"FILE: {f}") print('='*60) try: with pdfplumber.open(path) as pdf: print(f"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) else: print(f"\n--- Page {i+1}: [No text extracted] ---") except Exception as e: print(f"ERROR: {e}") EOF

python3 -c " import subprocess result = subprocess.run(['python3', '-c', 'import markitdown; print(\"ok\")'], capture_output=True, text=True) print(result.stdout, result.stderr) result2 = subprocess.run(['python3', '-c', 'import pytesseract; print(\"ok\")'], capture_output=True, text=True) print('pytesseract:', result2.stdout, result2.stderr) result3 = subprocess.run(['python3', '-c', 'import fitz; print(\"ok\")'], capture_output=True, text=True) print('pymupdf/fitz:', result3.stdout, result3.stderr) "

BASE="/tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511" # Try markitdown on the scanned/empty PDFs python3 << 'EOF' from markitdown import MarkItDown md = MarkItDown() files = [ "LNCT 2nd sessional paper (1).pdf", "1st sessional 3rd prof Lnct (1).pdf", "3rd prof university paper Lnct(2).pdf", "3rd year ln paper (1).pdf", ] base = "/tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511/" for f in files: path = base + f print(f"\n{'='*60}") print(f"FILE: {f}") print('='*60) try: result = md.convert(path) text = result.text_content if text and text.strip(): print(text[:3000]) else: print("[No text extracted by markitdown]") except Exception as e: print(f"ERROR: {e}") EOF

python3 << 'EOF' from pypdf import PdfReader from PIL import Image import io, os base = "/tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511/" outdir = "/tmp/workspace/psm_images/" os.makedirs(outdir, exist_ok=True) files = [ "LNCT 2nd sessional paper (1).pdf", "1st sessional 3rd prof Lnct (1).pdf", "3rd prof university paper Lnct(2).pdf", ] for fname in files: path = base + fname prefix = fname.replace(".pdf","").replace(" ","_").replace("(","").replace(")","") reader = PdfReader(path) print(f"\n{fname}: {len(reader.pages)} pages") for i, page in enumerate(reader.pages): for j, img_obj in enumerate(page.images): img_data = img_obj.data img = Image.open(io.BytesIO(img_data)) out_path = f"{outdir}{prefix}_page{i+1}_img{j+1}.png" img.save(out_path) print(f" Saved: {out_path} ({img.size})") EOF

# Start a simple HTTP server in background to serve images cd /tmp/workspace/psm_images/ python3 -m http.server 8765 & sleep 2 echo "Server started, PID: $!" ls /tmp/workspace/psm_images/

python3 << 'EOF' # Try extracting images from the 50-page scanned PDF from pypdf import PdfReader import io, os base = "/tmp/workspace/attachments/b0ed0c88-fa80-49e2-b122-1c5d4c9a7511/" outdir = "/tmp/workspace/psm_images/" fname = "3rd year ln paper (1).pdf" path = base + fname reader = PdfReader(path) print(f"{fname}: {len(reader.pages)} pages") # Extract first few pages images to check what's there for i in range(min(5, len(reader.pages))): page = reader.pages[i] imgs = list(page.images) print(f" Page {i+1}: {len(imgs)} images") for j, img_obj in enumerate(imgs): from PIL import Image img = Image.open(io.BytesIO(img_obj.data)) out_path = f"{outdir}ln3rd_page{i+1}_img{j+1}.png" img.save(out_path) print(f" Saved: {out_path} ({img.size})") EOF