slo_control_scrape

gistfile1.txt

import requests
from bs4 import BeautifulSoup
from datetime import datetime, timedelta
import pytz
import re

# the URL of the page you want to scrape
url = "https://www.sloveniacontrol.si/Strani/Summary-C.aspx"

# send a GET request to the URL
response = requests.get(url)

# get the HTML content of the page
html_content = response.text

soup = BeautifulSoup(html_content, 'html.parser')

# find all elements with the NOTAM class
notam_data_elements = soup.find_all(class_="kzps-notam-item")

# check if any NOTAM data elements were found
if not notam_data_elements:
    print("No NOTAM data elements found.")
else:
    # get today's date
    today = datetime.now(pytz.timezone('Europe/Ljubljana'))

    # initialize a dictionary to store NOTAMs for each day
    notams_by_day = {today + timedelta(days=i): [] for i in range(7)}

    # timezone abbreviations mapping
    tz_mapping = {'EST': 'US/Eastern', 'CET': 'Europe/Paris', 'UTC': 'UTC'}

    # regular expression for matching date strings
    date_pattern = re.compile(r'^(PERM|\d{2}\.\d{2}\.\d{4}( \d{2}:\d{2}( EST| CET)?)?)$')

    # loop through each NOTAM data element
    for notam_data in notam_data_elements:
        # extract the NOTAM number
        notam_number = notam_data.find('h1').get_text()

        # initialize start_date and end_date to None
        start_date = None
        end_date = None

        # extract the NOTAM details
        notam_details = notam_data.find_all('p')
        for detail in notam_details:
            if detail.find(class_='kzps-notam-item-b') is not None:
                # check if the text contains a date
                potential_date_str = detail.find(class_='kzps-notam-item-b').get_text().strip()
                if potential_date_str.startswith('B)'):  # check if the string starts with 'B) '
                    start_date_str = potential_date_str[3:]  # remove the 'B) ' prefix
                    if date_pattern.match(start_date_str):  # check if the date string matches the pattern
                        start_date_tz_str = start_date_str.split()[-1]  # get the timezone abbreviation
                        start_date_str = ' '.join(start_date_str.split()[:-1])  # remove the timezone abbreviation from the date string
                        if ' ' in start_date_str:  # check if time is specified
                            start_date = datetime.strptime(start_date_str, "%d.%m.%Y %H:%M")
                        else:
                            start_date = datetime.strptime(start_date_str, "%d.%m.%Y")
                        start_date = pytz.timezone(tz_mapping.get(start_date_tz_str, 'Europe/Ljubljana')).localize(start_date)
            if detail.find(class_='kzps-notam-item-c') is not None:
                end_date_str = detail.find(class_='kzps-notam-item-c').get_text().strip()[3:]  # remove the 'C) ' prefix
                if date_pattern.match(end_date_str):  # check if the date string matches the pattern
                    if end_date_str == 'PERM':
                        end_date = start_date + timedelta(hours=48)
                    else:
                        end_date_tz_str = end_date_str.split()[-1]  # get the timezone abbreviation
                        end_date_str = ' '.join(end_date_str.split()[:-1])  # remove the timezone abbreviation from the date string
                        if ' ' in end_date_str:  # check if time is specified
                            end_date = datetime.strptime(end_date_str, "%d.%m.%Y %H:%M")
                        else:
                            end_date = datetime.strptime(end_date_str, "%d.%m.%Y")
                        end_date = pytz.timezone(tz_mapping.get(end_date_tz_str, 'Europe/Ljubljana')).localize(end_date)

        # check if the NOTAM is or will be active in the next 7 days
        for day, notams in notams_by_day.items():
            if start_date is not None and end_date is not None and start_date <= day <= end_date:
                notams.append((notam_number, notam_details))

    # print NOTAMs for each day
    for day, notams in notams_by_day.items():
        print("\n\n" + day.strftime('%A:') + "\n")
        if notams:
            for notam_number, notam_details in notams:
                print("----------------------------------------")
                print(f"NOTAM Number: {notam_number}")
                for detail in notam_details:
                    print(detail.get_text())
        else:
            print("No NOTAMs. Yay!")
    print(f"\nStart date: {start_date.strftime('%d.%m.%Y %H:%M')} {start_date.tzinfo}" if start_date else "Start date: None")
    print(f"End date: {end_date.strftime('%d.%m.%Y %H:%M')} {end_date.tzinfo}" if end_date else "End date: None")
    print(f"Today's date: {today.strftime('%d.%m.%Y %H:%M')}")