Beispiel #1
0
    def province_parser(self, province_information):
        provinces = json.loads(province_information.group(0))
        for province in provinces:
            province.pop('id')
            province.pop('tags')
            province.pop('sort')
            province['comment'] = province['comment'].replace(' ', '')

            province['provinceEnglishName'] = city_name_map[province['provinceShortName']]['engName']
            province['country'] = country_type_map.get(province['countryType'])
        return provinces
    def province_parser(self, province_information):
        provinces = json.loads(province_information.group(0))
        for province in provinces:
            province.pop('id')
            province.pop('tags')
            province.pop('sort')
            province['comment'] = province['comment'].replace(' ', '')

            if self.db.find_one(collection='DXYProvince', data=province):
                continue

            province['provinceEnglishName'] = city_name_map[province['provinceShortName']]['engName']
            province['crawlTime'] = self.crawl_timestamp
            province['country'] = country_type_map.get(province['countryType'])

            self.db.insert(collection='DXYProvince', data=province)