# Copyright Stanislav Mironov


import random
import re
import time
from urllib.parse import urljoin
import requests
from requests.structures import CaseInsensitiveDict
from bs4 import BeautifulSoup

BASE_URL = "https://www.vstu.ru/"
RASP_PREFIX = "https://www.vstu.ru/student/raspisaniya/zanyatiy/index.php?dep="

def sibling_clear_to_date(s: str):
    if s is None:
        return "!!!Python None!!!"
    return s.lower().replace("(последнее изменение:", "").replace(")", "").strip()

# Парсит ссылки на эксель .xls & .xlsx файлы и выдаёт их
def parse_links(facultets):
    session = requests.Session()
    session.headers = CaseInsensitiveDict(
        {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:132.0) Gecko/20100101 Firefox/132.0",
            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
            "Accept-Language: ru-RU,ru;q=0.8,en-US;q=0.5,en;q=0.3",
            "Accept-Encoding": "gzip, deflate",
            "Connection": "keep-alive",
            "Upgrade-Insecure-Requests": "1",
            "Priority": "u=0, i",
            "Pragma": "no-cache",
            "Cache-Control": "no-cach"
        }
    )

    EXCEL_LINKS = []
    for facultet in facultets:
        url = RASP_PREFIX + facultet
        print("getting...")
        r = session.get(url)
        print(f"GET {url}")
        soup = BeautifulSoup(r.text, 'html.parser')
        excel_pattern = re.compile(r'\.xlsx?$')

        # Ищем все теги <a>, у которых атрибут href соответствует нашему паттерну
        excel_tags = soup.find_all('a', href=excel_pattern)
        for a in excel_tags:
            last_changed = sibling_clear_to_date(a.next_sibling)
            url = urljoin(BASE_URL, a.get('href'))
            disp = a.decode_contents()
            record = {
                "uniqpath": f"vstu.ru/rasp?dep={facultet}/{disp.strip()}",
                "facultet": facultet,
                "url": url,
                "display_filename": disp,
                "last_changed": last_changed
            }
            print("Found in vstu.ru: ", record)
            EXCEL_LINKS.append(record)
            st = random.randint(1, 10)/10
            print(f"sleep {st}s")
            time.sleep(st)

    return sorted(EXCEL_LINKS, key=lambda x: x['url'])