Ejen Penghurai Penyata Bank

import pdfplumber
from collections import defaultdict

CATEGORY_DICTIONARY = { ... }  # Income, Food, Transport, Shopping...

def categorize(desc):
    desc = desc.lower()
    for cat, kws in CATEGORY_DICTIONARY.items():
        if any(k in desc for k in kws): return cat
    return "Other"

def parse_maybank_pdf(path):
    txns = []
    with pdfplumber.open(path) as pdf:
        for page in pdf.pages:
            for row in page.extract_tables()[0]:
                txns.append({"date": row[0], "desc": row[1], ...})
    return summarize(txns)