import re
import requests
from bs4 import BeautifulSoup
from typing import List


class AttendanceScraper:
    def __init__(self, username: str, password: str):
        self.username = username
        self.password = password
        self.base_url = "https://agenda.colsys.cz/dochazka/index.php"

    @staticmethod
    def normalize_date(date_str: str) -> str:
        return re.sub(r'\s+', '', date_str)

    def scrape_month(self, month: str) -> List[str]:
        """
        Scrape attendance data for a given month.
        Returns list of dates with sick days, vacation, or unpaid leave.
        """
        url = f"{self.base_url}?kdy={month}-01"

        response = requests.get(url, auth=(self.username, self.password), verify=False)
        response.raise_for_status()

        soup = BeautifulSoup(response.content, 'html.parser')
        table = soup.find('table', class_='restrikce')

        if not table:
            raise ValueError("Attendance table not found")

        attendance_dates = []
        for row in table.find_all('tr')[1:]:
            cells = row.find_all('td')
            if len(cells) >= 3:
                date = cells[0].text.strip()
                presence = cells[2].text.strip()

                if ("sick day" in presence.lower() or
                    "dovolená" in presence.lower() or
                    "neplacené volno" in presence.lower()):
                    attendance_dates.append(self.normalize_date(date))

        return attendance_dates