57 lines
2.1 KiB
Python
57 lines
2.1 KiB
Python
# Copyright Stanislav Mironov
|
||
|
||
|
||
import re
|
||
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="
|
||
|
||
# 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)
|
||
excel_links = [tag.get('href') for tag in excel_tags]
|
||
|
||
# Предположим, вы уже получили excel_links из одного из методов выше
|
||
# excel_links = ['../../../upload/raspisanie/z/ОН_ХТФ_1 курс.xlsx', ...]
|
||
|
||
absolute_links = [urljoin(BASE_URL, relative_link) for relative_link in excel_links]
|
||
|
||
if facultet not in EXCEL_LINKS.keys():
|
||
EXCEL_LINKS[facultet] = set()
|
||
|
||
for excel_url in absolute_links:
|
||
EXCEL_LINKS[facultet].add(excel_url)
|
||
print(f"+url {excel_url}")
|
||
|
||
return EXCEL_LINKS
|
||
|