example used in PI4

crawler_example.py

class GetTopSitesListAditionalInformation(LogIntoAlexa):
    def __init__(self):
        super().__init__()
        self.top_list = json.load(open('../data/data.json'))
        self.url = 'https://www.alexa.com/siteinfo/'

    def get_additional_informations(self):
        self.log_into_alexa()
        i = 0
        for key, value in self.top_list.items():
            i += 1
            print(i)
            url = self.url + key

            request = self.session_requests.get(
                url, headers=dict(referer=url))

            soup = BeautifulSoup(request.text, "html.parser")
            self.top_list[key]['audience_geography'] = \
                self.__get_audience_geography(soup)