1import scrapy
2
3class bookScraper(scrapy.Spider):
4 name = "bookscrape"
5
6 start_urls = [
7 'http://books.toscrape.com/'
8 ]
9 def parse(self, response):
10 all_books = response.css('.col-lg-3 ')
11
12 for book in all_books:
13 img_link = book.css('a img::attr(src)').extract()
14 title = book.css('h3 a::attr(title)').extract()
15 price = book.css('div.product_price p.price_color::text').extract()
16
17 yield {
18 'image_url' : img_link,
19 'book_title' : title,
20 'product_price' : price
21 }
22 next_page = response.css('li.next a::attr(href)').get()
23 if next_page is not None:
24 yield response.follow(next_page, callback = self.parse)