gruene-oehringer-nachrichten/scrape.py

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

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


def scrape():
    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')

        output = ''

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

        # time
        timespan = data[1].text.strip()
        time = timespan.split(' ')[0]

        output += time
        output += ' Uhr'
        output += ', '

        # place
        #output += data[2].text.strip()
        output += ', '

        # title
        output += '<b>'
        output += event_soup.select('.calendarize h1')[0].text.strip()
        output += '</b>'

        try:
            description = event_soup.select('.calendarize .text p')[0].text.strip()
            output += ' '
            output += description
        except IndexError:
            pass

        return output




class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
    def do_GET(self):
        self.send_response(200)
        self.end_headers()
        self.wfile.write(scrape().encode('utf-8'))

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