"""Check why some multi-page PDFs aren't being imported."""
import pdfplumber
from pathlib import Path

pdfs = ["JEI Supplier Invoice.pdf", "Supplier Invoices.pdf",
        "JEI Drilling Invoices.pdf", "JEI SA Invoice 147842.pdf",
        "JEI SA Proforma 148931.pdf", "newJEI Drilling Invoices (1).pdf"]
for name in pdfs:
    p = Path("invoices") / name
    if not p.exists():
        print(f"NOT FOUND: {name}")
        continue
    try:
        with pdfplumber.open(p) as pdf:
            for i, page in enumerate(pdf.pages):
                t = page.extract_text() or ""
                print(f"  {name:<45} page {i+1}/{len(pdf.pages)}: {len(t):>5} chars")
    except Exception as e:
        print(f"  ERR {name}: {e}")