AkahuSync/EmoneyScraper/scraper.py

from playwright.sync_api import sync_playwright, Playwright
import os
from dotenv import load_dotenv
import re
from datetime import datetime

load_dotenv()
class Scraper:
    def __init__(self, playwright: Playwright, headless: bool = True):
        self.playwright = playwright
        self.firefox = self.playwright.firefox # or "firefox" or "webkit".
        self.browser = self.firefox.launch(headless=headless)
        self.page = self.browser.new_page()
        self.response = self.page.goto(os.getenv("URL"))
        self.page.fill("input#ctl00_ContentPlaceHolder1_txtLoginID", os.getenv("USERNAME"))
        self.page.fill("input#ctl00_ContentPlaceHolder1_txtPassword", os.getenv("PASSWORD"))
        self.page.click("input#ctl00_ContentPlaceHolder1_btnLogin")

    def get_balance(self):
        current_balance = self.page.locator("xpath=/html/body/form/div[3]/div[3]/div[2]/div[3]/div[5]/span[2]").inner_text()
        return current_balance

    def get_transactions(self):
        self.page.click("xpath=/html/body/form/div[3]/div[3]/div[2]/div[3]/div[1]/span[2]/a")
        transaction_body = self.page.locator("xpath=/html/body/form/div[3]/div[3]/div[2]/div/div[2]/div[3]/table/tbody").inner_text()
        return transaction_body

    def parse_transactions(self, raw: str = None) -> list[dict[str, any]]:
        """
        Parse raw transactions text into a list of dicts:
        [{'date': date, 'description': str, 'amount': float, 'balance': float}, ...]
        Lines containing 'INSUFF FUNDS' (case-insensitive) are ignored.
        If raw is None, get_transactions() is called to fetch the data.
        """
        if raw is None:
            raw = self.get_transactions() or ""
        lines = [ln.strip() for ln in raw.splitlines() if ln.strip()]
        pattern = re.compile(
            r'^(?P<date>\d{2}-\d{2}-\d{4})\s+(?P<desc>.*?)\s+(?P<amount>[-\$\d,\.]+)\s+(?P<balance>[-\$\d,\.]+)\s*$'
        )
        parsed: list[dict[str, any]] = []
        for ln in lines:
            m = pattern.match(ln)
            if not m:
                # skip lines that don't match the expected pattern
                continue
            desc = m.group('desc').strip()
            if 'INSUFF FUNDS' in desc.upper():
                continue
            def _to_float(s: str) -> float:
                return float(s.replace('$', '').replace(',', '').strip())
            try:
                amount = _to_float(m.group('amount'))
                balance = _to_float(m.group('balance'))
                date_obj = datetime.strptime(m.group('date'), '%d-%m-%Y').date()
            except Exception:
                continue
            parsed.append({
                'date': date_obj,
                'description': desc,
                'amount': amount,
                'balance': balance,
            })
        return parsed

    def close(self):
        self.browser.close()

#xpathbody=/html/body/form/div[3]/div[3]/div[2]/div/div[2]/div[3]/table/tbody
#xpathaccountbutton = /html/body/form/div[3]/div[3]/div[2]/div[3]/div[1]/span[2]/a
#xpath = /html/body/form/div[3]/div[3]/div[2]/div[3]/div[5]/span[2]