python-tutorial/website_checker.py at main · Hamidmirzapour/python-tutorial · 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
# pip install requests
# pip install fake_useragent

import csv
import requests
from fake_useragent import UserAgent
from http import HTTPStatus


def get_websites(csv_path: str) -> list[str]:
    websites: list[str] = []
    with open(csv_path, 'r') as file:
        reader = csv.reader(file)
        for row in reader:
            if 'https://' not in row[1]:
                websites.append(f'https://{row[1]}')
            else:
                websites.append(row[1])
        return websites


def get_user_agent() -> str:
    ua = UserAgent()
    return ua.firefox


def get_status_description(status_code: int) -> str:
    for value in HTTPStatus:
        if status_code == value:
            description: str = f'({value} {value.name}) {value.description}'
            return description
    return '(???) Unknown status code ...'

def check_websites(website: str, user_agent):
    try:
        code: int = requests.get(website, headers={'User-Agent': user_agent}).status_code
        print(website, get_status_description(code))
    except Exception:
        print(f'*** Could not get information for website: {website}')


def main():
    sites: list[str] = get_websites('websites.csv')
    user_agent: str = get_user_agent()

    for site in sites:
        check_websites(site, user_agent)

if __name__ == '__main__':
    main()