Newer
Older
import scrapy
class QuotesSpider(scrapy.Spider):
name = "quotes"
page = 1
start_urls = [
'http://quotes.toscrape.com/page/1/',
]
def parse(self, response):
yield {'page': self.page}
item = MyItem()
for quote in response.css('div.quote'):
yield {
'text': quote.css('span.text::text').get(),
'author': quote.css('small.author::text').get(),
'tags': quote.css('div.tags a.tag::text').getall(),
}
self.page += 1
next_page = response.css('li.next a::attr(href)').get()
if next_page is not None:
# next_page = response.urljoin(next_page)
# yield scrapy.Request(next_page, callback=self.parse)
yield response.follow(next_page, callback=self.parse)