Вот мой код:
import scrapy
class BookingSpider(scrapy.Spider):
name = 'booking-spider'
allowed_domains = ['booking.com']
start_urls = [
'https://www.booking.com/country.de.html?aid=356980;label=gog235jc-1DCAIoLDgcSAdYA2gsiAEBmAEHuAEHyAEP2AED6AEB'
'-AECiAIBqAIDuAK7q7DyBcACAQ;sid=8de61678ac61d10a89c13a3941fd3dcd'
]
# get country page
def parse(self, response):
for countryurl in response.xpath('//a[contains(text(),"Schweiz")]/@href'):
url = response.urljoin(countryurl.extract())
print("COUNTRYURL", url)
yield scrapy.Request(url, callback=self.parse_country)
# get page of all hotels in a country
def parse_country(self, response):
for hotelsurl in response.xpath('//a[@class="bui-button bui-button--secondary"]/@href'):
url = response.urljoin(hotelsurl.extract())
print("HOTELURL", url)
yield scrapy.Request(url, callback=self.parse_hotel)
def parse_hotel(self, response):
print("entering parse_hotel")
hotelurl = response.xpath('//*[(@ id = "hp_hotel_name")]')
print("URL", hotelurl)
Это не go в функции parse_hotel
. Не могу понять почему? Где моя ошибка? Заранее благодарю за ваши предложения!