UlSTU_Timetable/DownloadTools.py at master · KuzarinM/UlSTU_Timetable · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
# -*- coding: utf-8 -*-
from requests import request
from requests import Session

import EEPROM
from Settings import *
from time import sleep
import os
from bs4 import BeautifulSoup


def get_url(i):
    return timetable_url + str(i) + ".html"


def normalise_html(html):
    html = html.replace("</br>", "<br>")
    html = html.replace(".", "")
    return html


def get_html(id, ses):
    global session_id
    for i in range(100):
        try:
            sleep(0.2)
            # на случай, если появится желание использовать session_id
            res = ses.get(get_url(id), cookies={"AMS_LAST_LOGIN": username, "AMS_SESSION_ID": session_id})
            if res.status_code != 200:
                sleep(2)
                print(f"код{res.status_code} на позиции {id} всего{i + 1}")
                continue
            return res
        except Exception:
            sleep(2)
            print(f"остановка на позиции {id} всего{i + 1}")
    return None


def download(password, login=username):
    my_session = authentication(login, password)
    check_teachers_count(my_session)

    teachers_count = EEPROM.read_data("teachers_count")
    for i in range(1, teachers_count):
        data = get_html(i, my_session)
        if data is not None:
            data = normalise_html(data.content.decode('cp1251'))
            if os.path.exists(f"{html_save_path}{str(i)}.html"):
                with open(f"{html_save_path}{str(i)}.html", "r") as last:
                    last_html = last.read()
                    last_html = last_html[last_html.find("<BODY>"):last_html.find("</BODY>")]

                    new_html = data[data.find("<BODY>"):data.find("</BODY>")]
                    new_html = new_html.replace("\r", "\n")

                    if last_html != new_html:
                        with open(f"{html_save_path}{str(i)}.html", "w") as f:
                            f.write(data)
                            print(f"Страница {str(i)} была изменена!")
                    else:
                        print(f"Страница {str(i)}")
            else:
                with open(f"{html_save_path}{str(i)}.html", "w+") as f:
                    f.write(data)
                    print(f"Страница {str(i)} была создана!")


def authentication(login, password):
    global session_id
    ses = Session()
    response = ses.post(authentication_url, data={"login": login, "password": password})
    if response.status_code == 200:
        ses_id = response.history[0].cookies.get("AMS_SESSION_ID")
        if ses_id is not None:
            session_id = ses_id
            return ses
    return Session()


def check_teachers_count(ses):
    global session_id
    teachers_count = EEPROM.read_data("teachers_count")
    for i in range(100):
        try:
            sleep(0.2)
            res = ses.get(teachers_cont_url, cookies={"AMS_LAST_LOGIN": username, "AMS_SESSION_ID": session_id})
            if res.status_code != 200:
                sleep(2)
                print(f"код{res.status_code} при получении всписка учителей")
                continue
            soup = BeautifulSoup(normalise_html(res.content.decode('cp1251')), 'lxml')
            count = len(soup.body.table.find_all("tr")) - 1
            if count != teachers_count:
                print(f"колличесто преподавателей изменилось: раньше - {teachers_count}, теперь их {count}")
                if teachers_count != count:
                    EEPROM.write_data("teachers_count", count)
            return
        except Exception:
            sleep(2)
            print(f"остановка на получение учителей")
    return


if __name__ == '__main__':
    download("")  # пароль писсать сюда