2022-02-16 18:13:44 +03:00
|
|
|
import requests
|
|
|
|
import json
|
|
|
|
import datetime
|
|
|
|
from datetime import datetime as dt
|
|
|
|
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
|
|
try:
|
|
|
|
from load import config
|
|
|
|
except: config = None
|
|
|
|
from .utils import *
|
|
|
|
|
|
|
|
|
|
|
|
headers = {
|
|
|
|
'user-agent':(
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; WOW64) "
|
|
|
|
"AppleWebKit/537.36 (KHTML, like Gecko) "
|
|
|
|
"Chrome/62.0.3202.9 Safari/537.36"
|
|
|
|
)
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
def date_parser_helper(days:int, parse:str="%d.%m.20%y"):
|
|
|
|
return dt.strftime(
|
|
|
|
dt.now() +
|
|
|
|
datetime.timedelta(days=days),
|
|
|
|
parse
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
def docs_parse():
|
|
|
|
|
|
|
|
output = {
|
|
|
|
"data":{},
|
|
|
|
"another_teacher":None
|
|
|
|
}
|
|
|
|
|
|
|
|
page = requests.get(config.bot("link"), headers=headers)
|
|
|
|
page.encoding = 'utf-8'
|
|
|
|
|
2022-02-22 15:29:44 +03:00
|
|
|
soup = BeautifulSoup(page.text, "lxml")
|
2022-02-16 18:13:44 +03:00
|
|
|
|
|
|
|
# Это в идеале нужно переписать...
|
|
|
|
try: output = table_parser(soup, output); #print(output)
|
|
|
|
except Exception: pass
|
2022-02-22 15:29:44 +03:00
|
|
|
try: output = test_parser(soup, output)
|
2022-02-18 14:38:22 +03:00
|
|
|
except Exception as e: raise(e)
|
2022-02-22 15:29:44 +03:00
|
|
|
|
2022-02-16 18:13:44 +03:00
|
|
|
|
|
|
|
with open(config.data_file, 'w') as f:
|
|
|
|
json.dump(output, f, ensure_ascii=False)
|
|
|
|
f.close()
|
|
|
|
|
|
|
|
|
|
|
|
def get_about_replacements() -> dict:
|
|
|
|
with open(config.data_file, 'r') as f:
|
|
|
|
data = json.loads(f.read())
|
|
|
|
f.close()
|
|
|
|
return data
|