gruene-oehringer-nachrichten/scrape.py

import requests
from bs4 import BeautifulSoup
from time import time
from datetime import datetime
from http.server import BaseHTTPRequestHandler, HTTPServer

def scrape():
    output = {
        'print': '',
        'digital': '',
        'markdown': ''
    }

    overview_url = 'https://gruene-hohenlohe.de/kalender'
    overview_html = requests.get(overview_url, timeout=60).text
    overview_soup = BeautifulSoup(overview_html, 'html.parser')

    month = None
    for href in overview_soup.select('.media-body h2 a'):
        event_url = 'https://gruene-hohenlohe.de/' + href.attrs['href']
        event_html = requests.get(event_url, timeout=60).text
        event_soup = BeautifulSoup(event_html, 'html.parser')

        data = event_soup.select('.calendarize dl dd')

        # date
        date = data[0].text.strip()

        output['print'] += date
        output['print'] += ' '

        # day of week and month
        date_splitted = date.split('.')
        year = int(date_splitted[2])
        previous_month = month
        if (month := int(date_splitted[1].lstrip('0'))) != previous_month:
            output['digital'] += '<br>'
            output['markdown'] += '<br>'
            match month:
                case 1:
                    month_formatted = 'Januar'
                case 2:
                    month_formatted = 'Februar'
                case 3:
                    month_formatted = 'März'
                case 4:
                    month_formatted = 'April'
                case 5:
                    month_formatted = 'Mai'
                case 6:
                    month_formatted = 'Juni'
                case 7:
                    month_formatted = 'Juli'
                case 8:
                    month_formatted = 'August'
                case 9:
                    month_formatted = 'September'
                case 10:
                    month_formatted = 'Oktober'
                case 11:
                    month_formatted = 'November'
                case 12:
                    month_formatted = 'Dezember'
            output['digital'] += '<b>' + month_formatted + ' ' + str(year) + '</b><br>'
            output['markdown'] += '<b>*' + month_formatted + ' ' + str(year) + '*</b><br>'
        day = int(date_splitted[0].lstrip('0'))

        match datetime(year, month, day).weekday():
            case 0:
                weekday_formatted = 'Montag'
            case 1:
                weekday_formatted = 'Dienstag'
            case 2:
                weekday_formatted = 'Mittwoch'
            case 3:
                weekday_formatted = 'Donnerstag'
            case 4:
                weekday_formatted = 'Freitag'
            case 5:
                weekday_formatted = 'Samstag'
            case 6:
                weekday_formatted = 'Sonntag'
        output['digital'] += weekday_formatted
        output['digital'] += ', '
        output['digital'] += date
        output['digital'] += ' '
        output['markdown'] += '* '
        output['markdown'] += weekday_formatted
        output['markdown'] += ', '
        output['markdown'] += date
        output['markdown'] += ', '

        # time
        timespan = data[1].text.strip()
        time = timespan.split(' ')[0]
        time_formatted = time
        if time != 'Ganztags':
            time_formatted += ' Uhr'

        output['print'] += time_formatted
        output['print'] += ', '

        output['digital'] += time_formatted
        output['digital'] += ', '

        output['markdown'] += time_formatted

        # place
        if len(data) > 2:
            place = data[2].text.strip()

            output['print'] += place
            output['print'] += ', '

            output['digital'] += place
            output['digital'] += ', '

            output['markdown'] += ', '
            output['markdown'] += place
        output['markdown'] += ': '

        # title
        title = event_soup.select('.calendarize h1')[0].text.strip()

        output['print'] += '<b>'
        output['print'] += title
        output['print'] += '</b>'

        output['digital'] += '<b>'
        output['digital'] += title
        output['digital'] += '</b>'

        output['markdown'] += title

        # description
        try:
            description = event_soup.select('.calendarize .text p')[0].text.strip()

            output['print'] += ' '
            output['print'] += description

            output['digital'] += ' '
            output['digital'] += description

            output['markdown'] += ' '
            output['markdown'] += description
        except IndexError:
            pass

        output['print'] += '<br>'

        output['digital'] += '<br>'

        output['markdown'] += '<br>'

    return output['print'] + '<br><hr>' + output['digital'] + '<br><hr>' + output['markdown']

class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
    def do_GET(self):
        current_time = time()
        if cache['time'] < current_time - 30:
            html = templateHtml.replace('--body--', scrape())
            cache['output'] = html.encode('utf-8')
            cache['time'] = current_time

        self.send_response(200)
        self.end_headers()
        self.wfile.write(cache['output'])



with open('template.html', 'r') as templateFile:
    templateHtml = templateFile.read()

cache = {
    'time': 0,
    'output': None
}

httpd = HTTPServer(('', 8000), SimpleHTTPRequestHandler)
httpd.serve_forever()